Learn English with ChatGPT, but Don’t Trust It! British English Podcast

14,193 views ・ 2023-10-12

English Like A Native


Fare doppio clic sui sottotitoli in inglese per riprodurre il video.

00:00
The English Like a Native Podcast is a free listening and reading
0
450
4830
Il podcast English Like a Native è una risorsa gratuita di ascolto e lettura
00:05
resource for intermediate to advanced level English learners.
1
5340
5010
per studenti di inglese di livello intermedio e avanzato.
00:11
Bonus episodes and transcripts are available to Plus Members and
2
11040
5070
Episodi bonus e trascrizioni sono disponibili per i membri Plus e
00:16
English courses can be found on my website, www.englishlikeanative.co.uk.
3
16114
6216
i corsi di inglese possono essere trovati sul mio sito web, www.englishlikeanative.co.uk.
00:22
All the links will be in the show notes.
4
22800
2819
Tutti i link saranno nelle note dello spettacolo.
00:27
Hello there, you are listening to the English Like a Native Podcast.
5
27540
4680
Ciao a tutti, stai ascoltando il podcast English Like a Native.
00:32
I am your host, Anna, and today I'm feeling quite playful.
6
32489
5131
Sono la tua ospite, Anna, e oggi mi sento piuttosto giocosa.
00:38
We're going to play some games with ChatGPT.
7
38100
5320
Giocheremo ad alcuni giochi con ChatGPT.
00:44
So unless you've had your head buried in the sand for the last six months, you
8
44070
6480
Quindi, a meno che tu non abbia sepolto la testa sotto la sabbia negli ultimi sei mesi, avrai
00:50
will definitely have heard of ChatGPT.
9
50550
3810
sicuramente sentito parlare di ChatGPT.
00:55
This is basically AI technology and people have been using it for
10
55379
7890
Questa è fondamentalmente la tecnologia AI e le persone la usano per
01:03
many different things and there are loads of videos telling you
11
63269
4201
molte cose diverse e ci sono un sacco di video che ti spiegano
01:07
how you can use ChatGPT to learn a language, which is absolutely true.
12
67470
7289
come usare ChatGPT per imparare una lingua, il che è assolutamente vero.
01:14
It's a very useful tool.
13
74759
1891
È uno strumento molto utile.
01:16
This is a huge step forward in the land of technology, and it's
14
76650
6998
Questo è un enorme passo avanti nel paese della tecnologia e farà
01:23
going to make a huge difference to the way we all live our lives.
15
83648
3210
un'enorme differenza nel modo in cui tutti noi viviamo le nostre vite.
01:27
It already is having an impact on many people and many businesses
16
87278
4200
Sta già avendo un impatto su molte persone, molte aziende
01:32
and workflows and things like that.
17
92048
2250
, flussi di lavoro e cose del genere.
01:35
However, I've never been one to run with the crowd.
18
95258
5790
Tuttavia, non sono mai stato uno che corre con la folla.
01:42
When everyone would favour a particular boy band or be following a certain
19
102028
5730
Quando tutti preferivano una particolare boy band o seguivano una certa
01:47
trend in fashion, I would shy away from it, be specifically because
20
107758
5040
tendenza nella moda, io ne evitavo, proprio perché
01:52
everyone else was going crazy for it.
21
112798
1590
tutti gli altri ne impazzivano.
01:54
I'd be like, no, I'm gonna swim against the tide here.
22
114393
2965
Direi, no, nuoterò contro corrente qui.
01:57
I'm not that interested.
23
117838
1080
Non sono così interessato.
01:58
I'm gonna do my own thing.
24
118918
1320
Farò le mie cose.
02:01
And it's the same with ChatGPT.
25
121078
2260
Ed è lo stesso con ChatGPT.
02:03
I initially was a little bit nervous about the technology, to be honest.
26
123358
4440
Inizialmente ero un po’ nervoso per la tecnologia, a dire il vero.
02:08
I wondered if it would make me redundant.
27
128128
2040
Mi chiedevo se mi avrebbe reso licenziato.
02:10
But I have had a lot of experience with ChatGPT.
28
130798
5746
Ma ho avuto molta esperienza con ChatGPT.
02:16
I've been playing around with it quite a lot.
29
136564
2400
Ci ho giocato parecchio.
02:19
I've considered whether I should make a video or a podcast
30
139534
5400
Ho considerato se fare un video o un podcast
02:25
about the usefulness of it.
31
145474
1471
sulla sua utilità.
02:27
But the thing that's always stopped me is the fact that every single
32
147644
4190
Ma la cosa che mi ha sempre fermato è il fatto che ogni
02:31
time I use it, I find mistakes.
33
151834
3900
volta che lo uso trovo degli errori.
02:36
Yes, this very smart, fast-thinking, fast-writing, creative piece of software
34
156304
9202
Sì, questo software molto intelligente, veloce nel pensare, nella scrittura veloce e creativo
02:46
is flawed and there are ways to better prompt ChatGPT to get better results.
35
166646
9000
è difettoso e ci sono modi per spingere ChatGPT a ottenere risultati migliori.
02:55
You have to train it to do what you want it to do, but I think for the majority
36
175646
5160
Devi addestrarlo a fare quello che vuoi che faccia, ma penso che per la maggior parte
03:00
of us, just giving it generic, general, top of mind prompts, just what comes to
37
180806
8085
di noi, solo dandogli suggerimenti generici, generali, importanti, proprio quello che ci viene in
03:08
mind when we're asking it to do something.
38
188891
1920
mente quando gli chiediamo di fare qualcosa.
03:11
We may end up with work from ChatGPT that just doesn't cut it.
39
191891
7024
Potremmo ritrovarci con un lavoro di ChatGPT che semplicemente non è all'altezza.
03:19
That just doesn't quite do the job.
40
199785
4170
Questo semplicemente non fa proprio il lavoro.
03:24
And this I've noticed, is particularly true with English language,
41
204645
6390
E questo, ho notato, è particolarmente vero con la lingua inglese,
03:31
especially idiomatic language.
42
211065
2640
soprattutto con la lingua idiomatica.
03:34
Many times I've sat and had long chats with ChatGPT, trying to do some
43
214920
5730
Molte volte mi sono seduto e ho avuto lunghe chiacchierate con ChatGPT, cercando di fare qualche
03:40
research, trying to come up with ideas, brainstorming, and it is great for that.
44
220650
5400
ricerca, cercando di trovare idee, fare brainstorming, ed è fantastico per questo.
03:46
But I'd say to it something like, "Hey, can you think of an idiom that
45
226830
3570
Ma io gli direi qualcosa del tipo: "Ehi, riesci a pensare a un modo di dire
03:50
would be right for this scenario?"
46
230400
2940
adatto a questo scenario?"
03:54
And ChatGPT would give me some options, and then I'd say, "oh, great.
47
234000
4463
E ChatGPT mi dava alcune opzioni, e poi dicevo: "oh, fantastico.
03:58
How would you use that in a sentence?"
48
238553
1940
Come lo useresti in una frase?"
04:00
And then the sentence would be the usage of the idiomatic
49
240493
5295
E poi la frase sarebbe errata. L'uso della
04:05
language would be incorrect.
50
245788
1710
lingua idiomatica sarebbe errato.
04:08
And this has happened a number of times, and it's not just idiomatic language.
51
248848
3840
E questo è successo diverse volte, e non si tratta solo di linguaggio idiomatico.
04:12
Sometimes the grammatical explanations it gives, or examples
52
252688
4410
A volte le spiegazioni grammaticali fornite o gli esempi
04:17
of grammar just aren't quite right.
53
257098
2460
grammaticali non sono del tutto corretti.
04:20
Maybe ChatGPT doesn't take into account the different variations of English,
54
260818
5190
Forse ChatGPT non tiene conto delle diverse varianti dell'inglese,
04:26
so maybe I'm assuming it would go automatically to American English.
55
266008
3540
quindi forse presumo che passerebbe automaticamente all'inglese americano.
04:30
But anyway, my point here, I'm just rambling.
56
270793
4410
Ma comunque, il punto è che sto solo divagando.
04:35
The point I want to make is to be very careful, I think with anything that you
57
275503
6360
Il punto che voglio sottolineare è di stare molto attenti, penso che con tutto ciò che trovi
04:41
find on the internet, always have an open mind, but never take anything as gospel.
58
281863
6540
su Internet, devi sempre avere una mente aperta, ma non prendere mai nulla come vangelo.
04:49
Always double-check things, especially if you have doubts.
59
289033
5160
Ricontrolla sempre le cose, soprattutto se hai dei dubbi.
04:55
Don't just think, well ChatGPT gave me this, so it must be all perfectly correct.
60
295333
4950
Non pensare semplicemente, beh ChatGPT mi ha dato questo, quindi deve essere tutto perfettamente corretto.
05:00
No, don't trust it.
61
300523
960
No, non fidarti.
05:01
Double check it.
62
301843
720
Ricontrollalo.
05:04
So I am making some content about ChatGPT and language learning, but
63
304483
5190
Quindi sto creando alcuni contenuti su ChatGPT e sull'apprendimento delle lingue, ma
05:09
what I'm gonna do is explore ways that you can play with ChatGPT.
64
309678
5325
quello che farò è esplorare i modi in cui puoi giocare con ChatGPT.
05:15
So you know, this is language based, so it's text based,
65
315403
4920
Quindi sai, questo è basato sulla lingua, quindi è basato sul testo,
05:20
which is a little bit flat.
66
320803
1200
il che è un po' piatto.
05:22
But there are word games and little tasks and challenges that you can do with
67
322783
6180
Ma ci sono giochi di parole, piccoli compiti e sfide che puoi svolgere con
05:28
ChatGPT to, you know, help to work on and improve your language skills in this case.
68
328963
9480
ChatGPT per aiutarti a lavorare e migliorare le tue abilità linguistiche in questo caso.
05:40
So let me head over to ChatGPT.
69
340003
3130
Quindi permettimi di andare su ChatGPT.
05:43
I've got a new chat open here.
70
343423
2610
Ho una nuova chat aperta qui.
05:46
Now we're working on, it's number 3.5 is the model we're working on at the
71
346393
4650
Ora stiamo lavorando, il numero 3.5 è il modello su cui stiamo lavorando in questo
05:51
moment because the next one is locked.
72
351043
2850
momento perché il prossimo è bloccato.
05:53
I think they want you to upgrade for a hefty fee.
73
353893
3400
Penso che vogliano che tu faccia l'upgrade per una cifra elevata.
05:57
So the first thing I'm want to play with ChatGPT is Word Association.
74
357913
4470
Quindi la prima cosa con cui voglio giocare con ChatGPT è l'associazione di parole.
06:04
Word Association is a really fun game.
75
364093
2490
Associazione di parole è un gioco davvero divertente.
06:06
It always makes me think of this old children's Saturday morning programme
76
366853
6100
Mi fa sempre pensare a questo vecchio programma del sabato mattina per bambini
06:13
and it was like a mishmash of like sketches and different things going on.
77
373783
5970
ed era come un miscuglio di schizzi simili e cose diverse che succedevano.
06:19
And the host, Timmy Mallet, I think he was called, Timmy Mallet.
78
379753
4860
E il conduttore, Timmy Mallet, penso che si chiamasse Timmy Mallet.
06:24
He had really crazy glasses, always wore very bright clothing and he had a
79
384613
4560
Aveva degli occhiali davvero pazzeschi, indossava sempre abiti molto sgargianti e aveva dei
06:29
really eccentric and energetic manner.
80
389173
3930
modi davvero eccentrici ed energici.
06:33
And he would get kids on to play Word Association and they'd sit across from
81
393583
5460
E faceva giocare i bambini ad Associazione di parole e loro si sedevano uno di fronte
06:39
each other, on stools, facing one another.
82
399043
2700
all'altro, su sgabelli, uno di fronte all'altro.
06:42
And they would have to play a very fast, like round of Word Association.
83
402463
5697
E avrebbero dovuto giocare molto velocemente, come un giro di Associazione di Parole.
06:48
So he would start with a word, he'd throw it in, and then they had to bat
84
408910
6675
Quindi iniziava con una parola, la aggiungeva e poi dovevano battere
06:55
this word back and forth, finding a word that associated with that word,
85
415615
3780
questa parola avanti e indietro, trovando una parola associata a quella parola,
06:59
and then the next person would find a word that associated with the word that
86
419635
3300
e poi la persona successiva trovava una parola associata a quella parola quello
07:02
came before, and it would go back and forth, back and forth until one of them
87
422935
4290
venuto prima, e andava avanti e indietro, avanti e indietro finché uno di loro
07:07
said a word that wasn't associated with the previous word, or that was dubious.
88
427675
5850
non diceva una parola che non era associata alla parola precedente, o che era dubbia.
07:14
And then Timmy would be like, hang on a minute.
89
434425
3450
E poi Timmy direbbe, aspetta un attimo.
07:18
And he would, he had this huge mallet, so like a big hammer.
90
438745
4920
E lo avrebbe fatto, aveva questo enorme martello, così simile a un grosso martello.
07:24
It was soft of course, but he would like bonk them on the head.
91
444025
3600
Era morbido, ovviamente, ma gli sarebbe piaciuto dargli un colpo in testa.
07:27
Boing!
92
447775
600
Boing!
07:29
Wrong.
93
449365
540
Sbagliato.
07:31
You lost a point.
94
451075
990
Hai perso un punto.
07:32
And so it was just this programme of kids trying to play this game
95
452605
3870
E quindi era proprio questo programma di ragazzi che provavano a giocare a questo gioco
07:36
and just getting boinked on the head every time they made a mistake.
96
456475
2910
e venivano presi a pugni in testa ogni volta che commettevano un errore.
07:40
And then I think that the person who won.
97
460285
3810
E poi penso che la persona che ha vinto.
07:44
Or maybe it was the person who lost one of them had to then wear a huge
98
464928
3780
O forse è stato che la persona che ne ha perso uno ha dovuto poi indossare un enorme
07:49
sticker, oh no, sorry, it was a plaster, a huge plaster, either on
99
469158
4230
adesivo, oh no, scusa, era un cerotto, un cerotto enorme, o sul
07:53
their chin or on their forehead to show that they had taken part in this
100
473388
5160
mento o sulla fronte per dimostrare che aveva preso parte a questo
07:58
game and either won or lost the game.
101
478548
2310
partita e ha vinto o perso la partita.
08:00
I can't remember which outcome led to the huge plaster on the
102
480863
4175
Non riesco a ricordare quale risultato abbia portato all'enorme cerotto sul
08:05
face, but it was very silly.
103
485038
1890
viso, ma è stato molto stupido.
08:06
All a bit slapstick.
104
486928
1050
Tutto un po' slapstick.
08:08
But that's what I think of when I hear the words 'Word Association'.
105
488368
5040
Ma è quello a cui penso quando sento le parole "Associazione di parole".
08:14
So it's not going to be as fun as that.
106
494398
3000
Quindi non sarà così divertente.
08:17
But let's give it a go.
107
497908
1380
Ma proviamoci.
08:19
So the best prompt that I found during my limited research for word association,
108
499288
8980
Quindi il miglior suggerimento che ho trovato durante la mia ricerca limitata sull'associazione di parole
08:28
is "let's play a word association game.
109
508508
3360
è "facciamo un gioco di associazione di parole.
08:32
Each word must have a logical association to the previous word.
110
512288
4800
Ogni parola deve avere un'associazione logica con la parola precedente.
08:37
Correct me every time I make a mistake.
111
517688
2910
Correggimi ogni volta che commetto un errore.
08:41
I'll start with the word sunshine.
112
521348
2490
Inizierò con la parola sole.
08:44
Your turn."
113
524558
750
Il tuo turno."
08:45
Now, of course you can put in any word that you want to put in there.
114
525848
2400
Ora, ovviamente, puoi inserire qualsiasi parola tu voglia.
08:48
You can even add the instruction to be at a certain level.
115
528278
6570
Puoi anche aggiungere l'istruzione per raggiungere un certo livello.
08:54
So you might say all words should be C1 level or something like that.
116
534848
5890
Quindi potresti dire che tutte le parole dovrebbero essere di livello C1 o qualcosa del genere.
09:00
But for now, let's just see how ChatGPT responds to my prompt.
117
540738
4680
Ma per ora vediamo solo come ChatGPT risponde alla mia richiesta.
09:07
Okay.
118
547248
30
Va bene.
09:08
He's thinking and he has come back with, I'm saying he, I'm
119
548433
2420
Sta pensando ed è tornato con, sto dicendo che, presumo che
09:10
assuming ChatGPT today is a boy.
120
550853
1900
ChatGPT oggi sia un ragazzo.
09:13
"Sure.
121
553443
510
09:13
I'll play along.
122
553983
870
"Certo.
Starò al gioco.
09:14
My word in response to sunshine is beach."
123
554883
3150
La mia parola in risposta al sole è spiaggia."
09:18
Hmm.
124
558573
150
Hmm.
09:19
Makes sense.
125
559023
600
Ha senso.
09:20
Sunshine Beach.
126
560373
1050
Spiaggia del sole.
09:21
I'm going to say, beach, word association, sand is my word.
127
561723
5070
Dirò: spiaggia, associazione di parole, sabbia è la mia parola.
09:28
"Great", says ChatGPT, "my word in response to sand is ocean."
128
568233
4710
"Fantastico", dice ChatGPT, "la mia parola in risposta alla sabbia è oceano".
09:34
Okay.
129
574083
660
09:34
For ocean, I'm gonna give whale.
130
574953
2940
Va bene.
Per l'oceano, darò la balena.
09:38
I love a whale.
131
578313
780
Adoro una balena.
09:40
"Great choice", says ChatGPT.
132
580773
2520
"Ottima scelta", afferma ChatGPT.
09:43
I love the positive reinforcement.
133
583713
1440
Adoro il rinforzo positivo.
09:45
"My word in response to whale is mammal."
134
585513
2760
"La mia parola in risposta alla balena è mammifero."
09:48
Mm.
135
588333
480
09:48
Interesting.
136
588843
990
Mm.
Interessante.
09:50
So I'm going to now purposefully make a mistake and see if ChatGPT
137
590643
8080
Quindi ora commetterò intenzionalmente un errore e vedrò se ChatGPT
09:58
does follow my prompt to correct me.
138
598743
2070
segue il mio suggerimento per correggermi.
10:00
So I'm gonna say carrot.
139
600813
1620
Quindi dirò carota.
10:03
Because a carrot is not in any way associated with a mammal.
140
603143
4120
Perché una carota non è in alcun modo associata a un mammifero.
10:08
Ah, and we run into our first problem.
141
608553
2940
Ah, e ci imbattiamo nel nostro primo problema.
10:11
ChatGPT says, "nice association.
142
611653
2600
ChatGPT dice: "bella associazione.
10:15
My word in response to carrot is orange."
143
615513
2220
La mia parola in risposta alla carota è arancione".
10:18
So I'm gonna say, hang on.
144
618033
1560
Quindi dirò: aspetta.
10:20
Literally writing "hang on!"
145
620523
1350
Letteralmente scrivere "aspetta!"
10:22
Exclamation mark.
146
622713
1200
Punto esclamativo.
10:24
"How is mammal associated with carrot?"
147
624603
8700
"In che modo i mammiferi sono associati alla carota?"
10:34
Let's see.
148
634290
570
10:34
"Oh, apologies for that.
149
634860
2340
Vediamo.
"Oh, mi scuso.
10:37
You're right.
150
637200
750
Hai ragione.
10:38
The association between mammal and carrot isn't very clear."
151
638100
4440
L'associazione tra mammifero e carota non è molto chiara."
10:42
Well, at least ChatGPT owns its mistakes.
152
642810
3780
Bene, almeno ChatGPT possiede i suoi errori.
10:46
And he suggests, "let's go back a step and continue from ocean.
153
646590
3780
E suggerisce: "facciamo un passo indietro e continuiamo dall'oceano.
10:50
My word in response to ocean is wave."
154
650370
2430
La mia parola in risposta all'oceano è onda".
10:54
All the way back to ocean.
155
654165
1080
Fino all'oceano.
10:55
Why would he go back to ocean?
156
655245
1170
Perché dovrebbe tornare nell'oceano?
10:57
My word was whale and his word was mammal.
157
657675
3330
La mia parola era balena e la sua parola era mammifero.
11:02
Okay, we'll go back to wave then.
158
662355
1830
Ok, allora torneremo a salutare.
11:04
So we've got wave.
159
664185
960
Quindi abbiamo l'onda.
11:05
So I'm gonna write hand 'cause we wave with our hands.
160
665145
3240
Quindi scriverò a mano perché salutiamo con le mani.
11:09
"Understood.
161
669405
810
"Capito.
11:10
My word in response to hand is finger."
162
670220
1855
La mia parola in risposta alla mano è dito."
11:12
So my word in response to finger is gonna be chocolate because there's a very
163
672585
4800
Quindi la mia parola in risposta al dito sarà cioccolato perché
11:17
delicious snack here and the snack is like a biscuit finger, so it's just a long,
164
677385
7890
qui c'è uno spuntino davvero delizioso e lo spuntino è come un dito di biscotto, quindi è solo un
11:25
thin biscuit covered in milk chocolate.
165
685275
2010
biscotto lungo e sottile ricoperto di cioccolato al latte.
11:27
It's lovely.
166
687795
600
È amorevole.
11:28
I don't really eat them because they're just too moreish.
167
688425
2620
Non li mangio davvero perché sono semplicemente troppo saporiti.
11:31
Moreish means when you start eating something, you can't stop eating it
168
691625
3820
Più gustoso significa che quando inizi a mangiare qualcosa, non puoi smettere di mangiarlo
11:35
because you just want more, moreish.
169
695445
2790
perché ne vuoi solo di più, di più.
11:39
In response to chocolate, ChatGPT says, "got it.
170
699915
2370
In risposta al cioccolato, ChatGPT dice: "capito.
11:42
My word in response to chocolate is sweet."
171
702315
2610
La mia parola in risposta al cioccolato è dolce".
11:45
So in terms of the actual word association ChatGPT is doing a great job.
172
705615
4230
Quindi, in termini di associazione delle parole, ChatGPT sta facendo un ottimo lavoro.
11:50
I can't see any errors here.
173
710775
1290
Non riesco a vedere alcun errore qui.
11:52
It just hasn't done a good job in picking up my mistakes.
174
712965
3210
Semplicemente non ha fatto un buon lavoro nel correggere i miei errori.
11:56
So let's make another mistake.
175
716175
1380
Quindi facciamo un altro errore.
11:58
ChatGPT says "sweet", so I'm gonna write prison.
176
718425
4980
ChatGPT dice "dolce", quindi scriverò prigione.
12:04
That's a very different word to sweet.
177
724335
2610
È una parola molto diversa da dolce.
12:07
"Interesting transition", says ChatGPT.
178
727696
2830
"Transizione interessante", afferma ChatGPT.
12:10
"My word in response to prison is freedom."
179
730546
2910
"La mia parola in risposta al carcere è libertà."
12:14
And I'm gonna say, "wait a minute!"
180
734056
3180
E io dirò: "aspetta un attimo!"
12:18
Oh, exclamation mark.
181
738211
1830
Oh, punto esclamativo.
12:21
"How is prison associated with sweet?"
182
741361
8258
"In che modo la prigione è associata al dolce?"
12:30
Question mark.
183
750339
900
Punto interrogativo.
12:32
" Apologies for the confusion earlier.
184
752079
1710
" Mi scuso per la confusione di prima.
12:33
You are right.
185
753789
870
Hai ragione.
12:34
The association between prison and sweet isn't clear.
186
754719
3630
L'associazione tra prigione e dolce non è chiara.
12:38
Let's go back to chocolate and continue from there."
187
758679
2730
Torniamo al cioccolato e continuiamo da lì."
12:41
My word in response to chocolate is dessert, so I'm gonna
188
761709
3030
La mia parola in risposta al cioccolato è dolce, quindi ricorderò
12:44
remind ChatGPT about the rules.
189
764739
2480
a ChatGPT le regole.
12:48
"Remember to correct me if I do not make a logical association."
190
768214
12585
"Ricordati di correggermi se non faccio un'associazione logica."
13:02
My word is dessert.
191
782539
4050
La mia parola è dolce.
13:06
What's my, okay, so I'm gonna say trifle.
192
786709
2160
Qual è il mio, okay, quindi dirò una sciocchezza.
13:09
'cause trifle is quite a nice dessert here in the UK.
193
789469
2730
perché il trifle è un dessert piuttosto carino qui nel Regno Unito.
13:12
We have that everywhere really, on offer in every supermarket.
194
792204
3895
Lo abbiamo davvero ovunque, in offerta in ogni supermercato.
13:17
Oh, he's thinking, "got it.
195
797083
1290
Oh, sta pensando: "capito.
13:19
My word of response to trifle is custard".
196
799078
1890
La mia risposta alla sciocchezza è crema pasticcera".
13:21
Custard is like a yellow vanilla-y sauce that you put, that's sweet, and
197
801358
5327
La crema pasticcera è come una salsa gialla alla vaniglia che metti, è dolce e
13:26
you put it on things like apple pie.
198
806685
2610
la metti su cose come la torta di mele.
13:29
Mm, it's delicious.
199
809445
1110
Mmm, è delizioso.
13:31
Custard, I'm gonna say tart 'cause you can have a custard tart.
200
811345
5310
Crema pasticcera, dico crostata perché puoi avere una crostata con crema pasticcera.
13:37
"My response to tart is fruit."
201
817465
2040
"La mia risposta alla crostata è la frutta."
13:39
Yes.
202
819595
300
13:39
Because you can describe fruit as being a bit tart.
203
819895
2730
SÌ. Perché puoi descrivere la frutta come un po' aspra.
13:43
A bit tangy.
204
823300
820
Un po' piccante.
13:45
So fruit, I'm gonna say banana.
205
825245
1850
Quindi frutta, dirò banana.
13:48
Oh, ChatGPT has said peel.
206
828230
2910
Oh, ChatGPT ha detto sbuccia.
13:51
I'm gonna say eyes because you have to keep your eyes peeled.
207
831650
4500
Dirò occhi perché devi tenere gli occhi aperti.
13:56
That's a common idiom.
208
836150
1320
Questo è un idioma comune.
13:57
Telling someone to be aware and look out for something.
209
837530
4170
Dire a qualcuno di essere consapevole e di cercare qualcosa.
14:01
Keep your eyes peeled.
210
841730
1260
Tieni gli occhi aperti.
14:04
ChatGPT has told me it's great.
211
844480
2110
ChatGPT mi ha detto che è fantastico.
14:06
And with a response to eyes, they've said vision.
212
846890
3340
E con la risposta agli occhi hanno detto visione.
14:10
I'm gonna say idea.
213
850950
1110
Dirò un'idea.
14:13
They've said innovation.
214
853980
1140
Hanno detto innovazione.
14:15
Innovation.
215
855188
930
Innovazione.
14:16
What would I associate with innovation?
216
856118
2040
Cosa assocerei all’innovazione?
14:18
I'm gonna say startup, as in a startup company.
217
858208
3330
Dirò startup, come in una startup.
14:22
They're usually innovative.
218
862108
1260
Di solito sono innovativi.
14:23
ChatGPT has given me entrepreneur.
219
863688
2472
ChatGPT mi ha dato imprenditore.
14:26
Hmm.
220
866520
330
14:26
Okay.
221
866940
600
Hmm.
Va bene.
14:28
I'm gonna say motivated.
222
868920
2010
Dirò motivato.
14:31
Now they've given me ambitious, so I'm gonna go wrong once more and see
223
871985
3510
Adesso mi hanno dato dell'ambizioso, quindi sbaglierò ancora una volta e vedrò
14:35
if it follows my cue to correct me.
224
875495
3360
se segue il mio segnale per correggermi.
14:38
So what can I say?
225
878855
870
Quindi cosa posso dire?
14:39
Ambitious.
226
879725
570
Ambizioso.
14:40
I'm gonna say giraffe, although I'm sure giraffes are quite ambitious.
227
880295
4590
Dirò giraffa, anche se sono sicuro che le giraffe siano piuttosto ambiziose.
14:45
They certainly reach high.
228
885695
1080
Sicuramente arrivano in alto.
14:47
No, it didn't correct me.
229
887375
3990
No, non mi ha corretto.
14:52
I'm gonna ask, "is a giraffe ambitious?"
230
892445
3930
Chiederò: "una giraffa è ambiziosa?"
14:56
Now this is being slightly sarcastic.
231
896901
1520
Questo è un po' sarcastico.
14:59
"No, a giraffe is not truly ambitious in the human sense.
232
899501
3150
"No, una giraffa non è veramente ambiziosa nel senso umano.
15:02
The word ambitious typically applies to individuals or entities with a
233
902651
3960
La parola ambiziosa si applica tipicamente a individui o entità con un
15:06
strong desire to achieve success", blah, blah, blah, blah, blah.
234
906611
3240
forte desiderio di raggiungere il successo", blah, blah, blah, blah, blah.
15:10
But it doesn't apologise for not correcting me.
235
910481
2460
Ma non si scusa per non avermi corretto.
15:13
So what's the lesson that we've learned from this?
236
913211
2820
Allora qual è la lezione che abbiamo imparato da tutto ciò?
15:17
You can play Word Association with ChatGPT.
237
917161
4100
Puoi giocare ad Associazione di parole con ChatGPT.
15:22
But do not expect ChatGPT to pick you up on your deviations in the game so
238
922351
8020
Ma non aspettarti che ChatGPT ti accorga delle tue deviazioni nel gioco in modo che
15:30
you can play and you can play in a way that gives you maybe new vocabulary.
239
930371
6570
tu possa giocare e puoi giocare in un modo che ti dia magari un nuovo vocabolario.
15:36
You might learn new vocabulary associated to the words that you are giving.
240
936971
3480
Potresti imparare nuovi vocaboli associati alle parole che stai dando.
15:41
But don't expect ChatGPT to tell you that you are wrong in terms of association.
241
941231
6000
Ma non aspettarti che ChatGPT ti dica che hai torto in termini di associazione.
15:48
What you did notice there was when I questioned ambition, it automatically
242
948311
5700
Ciò che hai notato è che quando ho messo in dubbio l'ambizione,
15:54
gave me the meaning of the word.
243
954011
1260
mi ha dato automaticamente il significato della parola.
15:55
So you could play this game, and then if you spot a word that you don't recognise,
244
955271
3820
Quindi potresti giocare a questo gioco e poi, se trovi una parola che non riconosci,
15:59
you can ask, "hey, what does that mean?"
245
959111
1500
puoi chiedere: "ehi, cosa significa?"
16:01
and then you'll get an explanation of the word.
246
961271
2220
e poi otterrai una spiegazione della parola.
16:04
Okay.
247
964271
300
16:04
So let's move on to a different game.
248
964571
3030
Va bene. Passiamo quindi a un gioco diverso.
16:08
This one is going to be a guessing game, so this will help you to
249
968531
5430
Questo sarà un gioco d'ipotesi, quindi ti aiuterà a
16:13
improve how you describe things.
250
973961
3743
migliorare il modo in cui descrivi le cose.
16:17
So you can pick a word, an object, but you have to basically describe
251
977974
4900
Quindi puoi scegliere una parola, un oggetto, ma devi sostanzialmente descriverlo
16:22
it to ChatGPT and see if ChatGPT can guess what you are describing.
252
982874
5310
a ChatGPT e vedere se ChatGPT riesce a indovinare cosa stai descrivendo.
16:28
So it's a good way to gauge if your descriptions are good or not.
253
988184
6135
Quindi è un buon modo per valutare se le tue descrizioni sono buone o meno.
16:35
So the prompt is, "let's play a word guessing game.
254
995129
3000
Quindi il suggerimento è: "facciamo un gioco di indovinelli di parole.
16:38
Think of a word related to the topic technology and
255
998399
3960
Pensa a una parola correlata all'argomento tecnologia e
16:42
give me a brief description.
256
1002359
2190
dammi una breve descrizione.
16:45
I'll try to guess."
257
1005059
990
Proverò a indovinare".
16:46
So we're gonna start off by guessing Chat GPT's description.
258
1006319
5550
Quindi inizieremo indovinando la descrizione di Chat GPT.
16:52
So let's see what ChatGPT gives us.
259
1012089
1980
Vediamo quindi cosa ci offre ChatGPT.
16:56
"So I've thought of a word relating to technology.
260
1016889
2520
"Così ho pensato a una parola relativa alla tecnologia.
16:59
Here's a brief description.
261
1019409
1200
Ecco una breve descrizione.
17:00
This term refers to a process that allows data to be transmitted
262
1020984
4890
Questo termine si riferisce a un processo che consente ai dati di essere trasmessi
17:05
over a network in small pockets."
263
1025874
2130
su una rete in piccole tasche."
17:08
Oh, I think I'm gonna struggle here.
264
1028814
1140
Oh, penso che farò fatica qui.
17:10
"Which are then reassembled at the destination to form
265
1030494
3570
"Che vengono poi riassemblati a destinazione per formare
17:14
the complete message or file.
266
1034064
2490
il messaggio o file completo.
17:16
It's a fundamental concept in computer networking, and it's essential for
267
1036854
4620
È un concetto fondamentale nelle reti di computer ed è essenziale per
17:21
the functioning of the internet.
268
1041564
1830
il funzionamento di Internet.
17:23
Go ahead and take a guess."
269
1043904
1410
Vai avanti e prova a indovinare."
17:26
Oh, I'm not very good with computer talk.
270
1046394
4050
Oh, non sono molto bravo con i computer.
17:30
A process that allows data to be transmitted?
271
1050919
2700
Un processo che consente la trasmissione dei dati?
17:34
I mean, is it worldwide web?
272
1054419
2690
Voglio dire, è il web mondiale?
17:37
Let me see.
273
1057114
775
Fammi vedere.
17:38
Or internet.
274
1058669
1110
O Internet.
17:40
"Internet?"
275
1060499
570
"Internet?"
17:41
Question mark.
276
1061074
805
Punto interrogativo.
17:43
"Close but not quite.
277
1063019
1470
"Vicino ma non del tutto.
17:44
The term I was thinking of is packet."
278
1064549
1600
Il termine a cui stavo pensando è pacchetto."
17:47
You actually said packet in your description.
279
1067969
2130
In realtà hai detto pacchetto nella tua descrizione.
17:50
"In computer networking data is broken down into packets
280
1070729
3060
"Nelle reti di computer i dati vengono suddivisi in pacchetti
17:53
for efficient transmission."
281
1073789
1770
per una trasmissione efficiente."
17:56
I don't think that was a very good one because ChatGPT actually used the
282
1076894
4920
Non penso che sia stato molto buono perché ChatGPT in realtà ha usato la
18:01
word packet in its description, so that kind of, eh, anyway, let's, yes,
283
1081814
5580
parola pacchetto nella sua descrizione, quindi in un certo senso, eh, comunque, sì,
18:07
it's asking if I want to try again.
284
1087399
1645
mi chiede se voglio riprovare.
18:09
Let's try again.
285
1089554
1050
Proviamo di nuovo.
18:11
"Yes, please.
286
1091124
900
"Sì, grazie.
18:12
Something on the subject of travel."
287
1092174
7620
Qualcosa a proposito di viaggi."
18:22
"Sure.
288
1102824
510
"Certo.
18:23
Let's switch to the topic of travel.
289
1103364
1440
Passiamo al tema del viaggio.
18:24
Here's a word related to travel with a brief description.
290
1104804
3210
Ecco una parola relativa al viaggio con una breve descrizione.
18:28
This term refers to a document issued by a government that allows
291
1108494
3840
Questo termine si riferisce a un documento rilasciato da un governo che consente
18:32
its holders to enter, leave, or stay in a country for a specific period.
292
1112334
5490
ai suoi titolari di entrare, uscire o soggiornare in un paese per un periodo specifico .
18:38
It's an essential item for international travel and serves as a form of
293
1118394
4020
È un articolo essenziale per i viaggi internazionali e serve come forma di
18:42
identification, identifying the holder's nationality and permitting
294
1122414
4560
identificazione, identificando la nazionalità del titolare e permettendogli
18:46
them to cross international borders.
295
1126974
2400
di attraversare i confini internazionali.
18:50
Give it a guess.
296
1130139
750
18:50
What's the word?"
297
1130889
840
Prova a indovinare.
Qual è la parola?"
18:52
Can you guess at home, guys?
298
1132809
1320
Riuscite a indovinare a casa, ragazzi?
18:55
I think the answer is passport.
299
1135209
3240
Penso che la risposta sia il passaporto.
18:59
Woo-hoo.
300
1139889
180
Woo-hoo.
19:01
I am right.
301
1141139
1060
Ho ragione.
19:02
That was much better.
302
1142259
1170
Così era molto meglio.
19:03
That was much better.
303
1143519
870
Così era molto meglio.
19:05
Okay, so I'm gonna say my turn.
304
1145279
1650
Ok, quindi dirò il mio turno.
19:08
"Absolutely.
305
1148139
630
19:08
Please take a turn."
306
1148769
990
"Assolutamente.
Per favore, fai un giro."
19:09
It's asking me which topic, so I'm going to say this word is related to education.
307
1149826
11000
Mi sta chiedendo quale argomento, quindi dirò che questa parola è legata all'istruzione.
19:21
So this person leads a class with the objective of educating others.
308
1161324
10821
Quindi questa persona conduce una classe con l'obiettivo di educare gli altri.
19:33
He or she has greater knowledge on the subject that the class is trying to learn.
309
1173015
17800
Lui o lei ha una maggiore conoscenza dell'argomento che la classe sta cercando di apprendere.
19:52
Learn.
310
1192335
840
Imparare.
19:53
There we go.
311
1193415
480
Eccoci qua.
19:54
Let's see.
312
1194045
540
19:54
It's very simple.
313
1194885
930
Vediamo.
È molto semplice.
19:56
"Based on your description you provided, the word you're thinking of is teacher."
314
1196355
4950
"In base alla descrizione che hai fornito, la parola a cui stai pensando è insegnante."
20:01
Yes.
315
1201605
360
20:01
"A teacher is someone who leads a class imparts knowledge."
316
1201965
3750
SÌ.
"Un insegnante è qualcuno che guida una classe e impartisce conoscenza."
20:06
Oh, that's an interesting verb, to impart knowledge.
317
1206165
3690
Oh, è un verbo interessante, impartire conoscenza.
20:10
So there we go.
318
1210065
750
20:10
We've just been offered a new verb.
319
1210820
2395
Quindi eccoci qua.
Ci è appena stato offerto un nuovo verbo.
20:13
"Imparts knowledge and educates students on various subjects.
320
1213695
4860
"Trasmette conoscenze e istruisce gli studenti su vari argomenti.
20:19
Is that the word you had in mind?
321
1219005
2190
È questa la parola che avevi in ​​mente?
20:21
If not, feel free to provide more hints and let me know if it's a different term."
322
1221405
4875
In caso contrario, sentiti libero di fornire ulteriori suggerimenti e fammi sapere se è un termine diverso."
20:26
So I'm gonna say "correct.
323
1226550
1220
Quindi dirò "corretto.
20:29
Well done."
324
1229130
1230
Ben fatto".
20:31
Okay.
325
1231417
360
20:31
So you can see how this word guessing game can be quite useful.
326
1231782
6475
Va bene.
Quindi puoi vedere come questo gioco di indovinare le parole può essere molto utile.
20:38
It's useful for you, if you are taking the turn to try and describe
327
1238287
4240
È utile per te se stai cercando di descrivere
20:42
something in a way that doesn't directly say the thing you're describing.
328
1242527
5490
qualcosa in un modo che non dica direttamente ciò che stai descrivendo.
20:48
And it also, gives you an opportunity to learn new descriptive words.
329
1248827
6960
E ti dà anche l'opportunità di imparare nuove parole descrittive.
20:56
So I think that's quite a good one.
330
1256837
1440
Quindi penso che sia abbastanza buono.
20:59
Let's move on to the next game.
331
1259597
1440
Passiamo alla prossima partita.
21:01
So the next game is the sentence completion challenge, and I'm sure
332
1261037
6540
Quindi il prossimo gioco è la sfida del completamento delle frasi, e sono sicuro
21:07
it's very obvious from the title.
333
1267582
2245
che sia molto ovvio dal titolo.
21:09
Basically, one of you writes an incomplete sentence and you ask
334
1269827
5340
Fondamentalmente, uno di voi scrive una frase incompleta e chiedete
21:15
the other to complete the sentence.
335
1275167
3060
all'altro di completarla.
21:18
Now, the important thing here is to make sure we tell ChatGPT
336
1278827
5740
Ora, la cosa importante qui è assicurarci di dire a ChatGPT
21:24
that we want corrections.
337
1284587
1440
che vogliamo correzioni.
21:26
So the prompt that I've given for this particular game is "let's do
338
1286957
4980
Quindi il suggerimento che ho dato per questo particolare gioco è "facciamo
21:31
the sentence completion challenge.
339
1291937
1830
la sfida di completamento della frase.
21:33
Please correct my writing if I make any mistakes.
340
1293977
3240
Per favore, correggi la mia scrittura se commetto errori.
21:37
Here's an incomplete sentence: in the quiet forest I stumbled upon...
341
1297727
5070
Ecco una frase incompleta: nella foresta tranquilla mi sono imbattuto in...
21:44
Complete it in an interesting way, ChatGPT."
342
1304777
3210
Completala in un modo interessante, ChatGPT."
21:48
And let's send that and see what ChatGPT gives us.
343
1308677
3540
E inviamolo e vediamo cosa ci offre ChatGPT.
21:53
So they've completed the sentence with, "in a quiet forest, I stumbled
344
1313387
3690
Quindi hanno completato la frase con "in una foresta tranquilla, mi sono imbattuto
21:57
upon a hidden grove where ancient towering trees whispered secrets to
345
1317077
5070
in un boschetto nascosto dove antichi alberi torreggianti sussurravano segreti al
22:02
the wind, their leaves forming a mosaic of shimmering gold and emerald hues."
346
1322147
7030
vento, le loro foglie formando un mosaico di scintillanti sfumature dorate e smeraldo".
22:09
Oh, that's very descriptive, isn't it?
347
1329797
1890
Oh, è molto descrittivo, vero?
22:12
Okay, fantastic.
348
1332737
2130
Ok, fantastico.
22:14
So I'm gonna ask it to give me a go.
349
1334872
2875
Quindi gli chiederò di provarci.
22:18
"Your turn", I'm simply gonna say, to see if that prompts them
350
1338992
3630
"Tocca a voi", dirò semplicemente, per vedere se questo li spinge
22:22
to write an incomplete sentence.
351
1342622
1620
a scrivere una frase incompleta.
22:25
Whoa.
352
1345202
570
22:25
Okay, so I said your turn and all it's done is given me another
353
1345952
2670
Ehi.
Ok, quindi ho detto che era il tuo turno e tutto ciò che ho fatto è stato darmi un'altra
22:28
complete sentence, so I'm gonna say no, please now provide me with an
354
1348622
13813
frase completa, quindi dirò di no, per favore ora forniscimi una
22:42
incomplete sentence to complete.
355
1362855
5040
frase incompleta da completare.
22:50
"Apologies for the misunderstanding.
356
1370325
1680
"Ci scusiamo per l'equivoco.
22:52
Here's an incomplete sentence for you to complete."
357
1372215
2070
Ecco una frase incompleta da completare."
22:54
So we gotta do this guys.
358
1374290
1135
Quindi dobbiamo farlo ragazzi.
22:55
"As I walked along the deserted beach, I noticed a message in a bottle that..."
359
1375785
5370
"Mentre camminavo lungo la spiaggia deserta, ho notato un messaggio in una bottiglia che..."
23:01
Oh, what could we possibly complete that sentence with?
360
1381865
2950
Oh, con cosa potremmo completare quella frase?
23:04
I noticed a message in a bottle that, Hmm.
361
1384815
4170
Ho notato un messaggio in una bottiglia che diceva: Hmm.
23:10
That read.
362
1390905
730
Quello letto.
23:11
Oh, hang on.
363
1391805
600
Oh, aspetta.
23:12
So what I'm gonna do is I'm gonna copy that first part of the sentence,
364
1392405
5010
Quindi quello che farò è copiare la prima parte della frase,
23:17
I'm gonna paste that in, and then I'm going to complete it there.
365
1397415
2670
incollarla e poi completarla lì.
23:20
"So I noticed a message in a bottle that read: I can see you."
366
1400685
8790
"Così ho notato un messaggio in una bottiglia che diceva: posso vederti."
23:30
"As I walk along the deserted beach.
367
1410825
1290
"Mentre cammino lungo la spiaggia deserta.
23:32
I noticed a message in a bottle that read.
368
1412115
2100
Ho notato un messaggio in una bottiglia che diceva.
23:34
I can see you.
369
1414245
1290
Posso vederti.
23:36
Curiosity and a hint of unease crept over me, prompting me to..."
370
1416225
4860
Curiosità e un pizzico di disagio si sono insinuati in me, spingendomi a..."
23:41
So what ChatGPT has done here is to continue on from there
371
1421325
3810
Quindi quello che ChatGPT ha fatto qui è continuare da lì
23:45
with another incomplete sentence that I need to complete.
372
1425135
4170
con un'altra frase incompleta che devo completare.
23:49
So curiosity and a hint of unease crept over me, prompting me to, I'm gonna
373
1429725
7050
Quindi la curiosità e un pizzico di disagio si sono insinuati in me, spingendomi, dirò che
23:56
say it prompted me to drop the bottle.
374
1436775
3540
mi ha spinto a lasciar cadere la bottiglia.
24:02
Maybe it cuts me or something.
375
1442145
2340
Forse mi taglia o qualcosa del genere.
24:05
"Prompting me to drop the bottle in an instant and spin around."
376
1445115
9930
"Spingendomi a far cadere la bottiglia in un istante e a girarmi intorno."
24:15
Let me see if I can just prompt ChatGPT to complete the sentence by
377
1455855
4020
Fammi vedere se riesco a chiedere a ChatGPT di completare la frase semplicemente
24:19
just doing an ellipsis at the end.
378
1459875
1640
facendo i puntini di sospensione alla fine.
24:21
So, "prompting me to drop the bottle in an instant and spin around.
379
1461995
4310
Quindi, "spingendomi a far cadere la bottiglia in un istante e a girarmi.
24:27
That's when I saw..."
380
1467175
3270
È stato allora che ho visto..."
24:34
Let's see.
381
1474105
540
24:34
Ah, yes, it's done it straight away.
382
1474675
1590
Vediamo.
Ah, sì, è stato fatto subito.
24:36
So I prompted ChatGPT to then take over completing the sentence,
383
1476265
5070
Quindi ho chiesto a ChatGPT di occuparsi del completamento della frase,
24:41
which by just adding an ellipsis at the end of the sentence.
384
1481875
2910
aggiungendo semplicemente dei puntini di sospensione alla fine della frase.
24:45
So what have we got?
385
1485625
1140
Allora cosa abbiamo?
24:46
"As I walked along the deserted beach, I noticed a message and a bottle that read.
386
1486765
3960
"Mentre camminavo lungo la spiaggia deserta, ho notato un messaggio e una bottiglia con su scritto.
24:50
I can see you.
387
1490905
1110
Posso vederti.
24:52
Curiosity and a hint of unease crept over me, prompting me to drop the
388
1492675
3900
La curiosità e un pizzico di disagio si sono insinuati in me, spingendomi a lasciar cadere
24:56
bottle in an instant and spin around.
389
1496575
2850
in un attimo la bottiglia e a girarmi.
25:00
That's when I saw a pair of luminous eyes gleaming in the darkness peering
390
1500010
4200
È stato allora che ho ho visto un paio di occhi luminosi che brillavano nell'oscurità e
25:04
at me from the shadows of a nearby cave.
391
1504210
2490
mi scrutavano dall'ombra di una grotta vicina.
25:07
Fantastic.
392
1507600
870
Fantastico.
25:08
Okay.
393
1508500
300
25:08
What I'm gonna do now is make a mistake on purpose and see
394
1508800
4140
Okay. Quello che farò ora è commettere un errore di proposito e vedere
25:12
if ChatGPT pulls me up on it.
395
1512940
1890
se ChatGPT mi aiuta.
25:14
So I'm gonna write -it he ran...
396
1514835
3080
Quindi ho scriverò -se ha corso...
25:19
I'm gonna write quitely instead of quickly.
397
1519595
2340
scriverò con calma invece che velocemente.
25:22
So quitely would be very wrong.
398
1522325
1830
Quindi con calma sarebbe molto sbagliato.
25:24
Quitely.
399
1524155
870
Con calma.
25:25
It he ran quitely towards me, um, on great speed.
400
1525655
6120
Se corresse con calma verso di me, ehm, a grande velocità.
25:31
So I've made a lot of mistakes here.
401
1531775
1680
Quindi ho fatto un sacco di errori qui.
25:33
So it should be he or it, one or the other, not both.
402
1533705
3980
Quindi dovrebbe essere lui o quello, l'uno o l'altro, non entrambi.
25:38
It ran quickly towards me at great speed.
403
1538255
5310
Corse velocemente verso di me a grande velocità.
25:44
But what I've done here is it he ran quitely towards me on great speed.
404
1544275
6115
Ma quello che ho fatto qui è che lui correva tranquillamente verso di me a grande velocità.
25:50
Let's see if ChatGPT corrects me here.
405
1550450
4080
Vediamo se ChatGPT mi corregge qui.
25:55
So what ChatGPT has done is rewrite it with some changes, but hasn't actually
406
1555130
6660
Quindi ciò che ChatGPT ha fatto è stato riscriverlo con alcune modifiche, ma in realtà non ha
26:01
specifically said you made a mistake.
407
1561790
2100
detto specificamente che hai commesso un errore.
26:04
So ChatGPT has written "it, it ran quietly towards me with great speed.
408
1564490
7170
Quindi ChatGPT ha scritto ", correva silenziosamente verso di me con grande velocità.
26:12
A mysterious figure cloaked in moonlight, its presence both exhilarating and...
409
1572695
4590
Una figura misteriosa ammantata di luce lunare, la sua presenza allo stesso tempo esilarante e...
26:17
So I'm gonna say, "did I make a mistake?"
410
1577555
2040
Quindi dirò: "ho fatto un errore?"
26:20
And see if it actually points out what mistake I made.
411
1580765
3000
E vedo se in realtà sottolinea l'errore che ho commesso.
26:25
"Yes," ChatGPT says, "there's a small grammatical error in your sentence.
412
1585265
4805
"Sì", dice ChatGPT, "c'è un piccolo errore grammaticale nella tua frase.
26:30
It should be 'it ran quietly toward me with great speed.' The correct
413
1590070
7260
Dovrebbe essere "correva silenziosamente verso di me con grande velocità". La
26:37
form uses toward instead of towards."
414
1597330
3390
forma corretta usa verso anziché verso."
26:40
Fair enough.
415
1600780
660
Abbastanza giusto.
26:41
"And the rest of the sentence is well written and engaging."
416
1601800
2220
"E il resto della frase è ben scritto e accattivante."
26:44
Mm.
417
1604200
180
26:44
No, the rest of the sentence wasn't well written because you
418
1604860
4380
Mm.
No, il resto della frase non era scritto bene perché
26:49
actually corrected it ChatGPT.
419
1609240
2090
in realtà l'hai corretto ChatGPT.
26:52
Okay.
420
1612330
480
26:52
So I did make an error that I hadn't actually spotted, which was useful.
421
1612810
5040
Okay.
Quindi ho fatto un errore che in realtà non avevo notato, il che è stato utile.
26:58
But ChatGPT wrote that in.
422
1618450
1710
Ma ChatGPT lo ha scritto.
27:00
So you see it's, this is where I get a bit frustrated with ChatGPT.
423
1620160
3890
Quindi, come vedi, è qui che mi sento un po' frustrato con ChatGPT.
27:04
What I would like to do in this game is play and then ChatGPT say,
424
1624360
4260
Quello che vorrei fare in questo gioco è gioca e poi ChatGPT dice,
27:08
hang on, just so you know, you made this mistake and that mistake,
425
1628620
3540
aspetta, solo perché tu lo sappia, hai fatto questo errore e quell'altro errore,
27:12
so I've changed these things.
426
1632160
1560
quindi ho cambiato queste cose
27:15
But it hasn't, and even when I ask it if I made a mistake, it hasn't pointed out
427
1635790
3840
. Ma non è stato così, e anche quando gli chiedo se ho commesso un errore, non è cambiato "non ho sottolineato
27:19
exactly the mistakes that I previously.
428
1639630
2910
esattamente gli errori che avevo fatto in precedenza.
27:23
So useful but frustrating.
429
1643440
3150
Così utile ma frustrante.
27:27
Okay, so.
430
1647610
750
Okay, allora.
27:29
The other thing that we can play is, so one of the things I was gonna
431
1649005
3580
L'altra cosa su cui possiamo giocare è, quindi una delle cose che stavo per
27:32
suggest was storytelling collaboration, but we actually started doing that
432
1652585
4200
suggerire era la collaborazione narrativa, ma in realtà abbiamo iniziato a farlo
27:36
naturally with this incomplete sentence.
433
1656785
2490
in modo naturale con questa frase incompleta.
27:40
So if you wanted to actually try a storytelling collaboration, then you
434
1660295
4470
Quindi, se vuoi davvero provare una collaborazione narrativa, allora chiedi
27:44
just ask it to create a story together.
435
1664765
3780
semplicemente di creare una storia insieme.
27:48
Say, let's create a story together.
436
1668545
1800
Dimmi, creiamo una storia insieme.
27:50
I'll start, or you start and you give a sentence each.
437
1670865
3790
Inizierò io, oppure inizi tu e dai una frase ciascuno.
27:54
So you progress the story a sentence at a time.
438
1674715
3435
Quindi procedi nella storia una frase alla volta.
27:58
So these are complete sentences that you are adding to create a story.
439
1678600
4560
Quindi queste sono frasi complete che stai aggiungendo per creare una storia.
28:03
I will warn you though, that ChatGPT doesn't like to go into dark
440
1683730
4350
Ti avverto però che a ChatGPT non piace addentrarsi in
28:08
places, not even in the slightest.
441
1688080
1860
luoghi oscuri, nemmeno minimamente.
28:09
Let me give you an example.
442
1689940
1170
Lasciate che vi faccia un esempio.
28:11
Let's try, Okay, so I've written, "let's write a story together.
443
1691110
2811
Proviamo, okay, quindi ho scritto: "scriviamo una storia insieme.
28:13
You start."
444
1693921
840
Inizi tu".
28:16
Once upon a time and, oh no.
445
1696621
2160
C'era una volta e, oh no.
28:18
Oh, oh my goodness, me.
446
1698781
1290
Oh, oh mio Dio, io.
28:20
Oh my goodness me.
447
1700131
1020
Oh mio Dio, io.
28:21
Stop generating.
448
1701151
1020
Smetti di generare.
28:22
So ChatGPT has already given me three paragraphs.
449
1702171
4410
Quindi ChatGPT mi ha già dato tre paragrafi.
28:27
Let me give that prompt again.
450
1707841
1470
Permettimi di ripetere questo suggerimento.
28:30
You see, you have to be very direct and very specific with your prompts.
451
1710721
6120
Vedi, devi essere molto diretto e molto specifico con i tuoi suggerimenti.
28:37
"Let's write a story together," comma, "adding one line or one sentence each."
452
1717411
9015
"Scriviamo una storia insieme", virgola, "aggiungendo una riga o una frase ciascuno."
28:47
Let's see if that works.
453
1727116
1140
Vediamo se funziona.
28:48
Okay, so now he's given me one sentence.
454
1728916
2550
Ok, quindi ora mi ha dato una frase.
28:51
"In a quaint little town by the sea there lived a retired sailor named Captain
455
1731466
4950
"In una pittoresca cittadina in riva al mare viveva un marinaio in pensione di nome Capitano
28:56
Barnaby, who spent his days telling tales of his high sea adventures to
456
1736476
4800
Barnaby, che trascorreva le sue giornate raccontando storie delle sue avventure in alto mare ai
29:01
the curious children of the village."
457
1741276
1950
bambini curiosi del villaggio."
29:03
What can I say?
458
1743916
860
Cosa posso dire?
29:06
"One day a young boy challenged the the captain to go on one
459
1746016
13005
"Un giorno un ragazzino sfidò il capitano a intraprendere un'ultima
29:19
last adventure with his father."
460
1759291
5100
avventura con suo padre."
29:24
"The boy's eyes sparkled with excitement and Captain Barnaby
461
1764871
3840
"Gli occhi del ragazzo brillavano di eccitazione e il capitano Barnaby
29:28
couldn't resist the twinkle of adventure in the young lad's gaze."
462
1768711
4470
non ha potuto resistere al luccichio di avventura nello sguardo del giovane ragazzo."
29:33
"So, they embarked on a great but dangerous adventure heading
463
1773931
13455
"Così, si imbarcarono in una grande ma pericolosa avventura dirigendosi
29:47
out into the stormy seas."
464
1787506
5970
verso i mari in tempesta."
29:54
"The waves crashed against the side of the sturdy ship and the wind howled with
465
1794196
4530
"Le onde si infrangevano contro il fianco della robusta nave e il vento ululava con
29:58
a fierceness that tested their resolve."
466
1798726
2280
una ferocia che metteva alla prova la loro risolutezza."
30:03
"Suddenly", now, this is where I'm gonna try and make it turn
467
1803031
2310
"All'improvviso", ora, è qui che proverò a far diventare
30:05
dark and see what ChatGPT does.
468
1805346
1735
buio e vedere cosa fa ChatGPT.
30:07
"Suddenly, a huge wave crashed down on the unsuspecting sailors and
469
1807351
15750
"All'improvviso, un'onda enorme si abbatté sugli ignari marinai e
30:23
smashed the vessel to smithereens."
470
1823911
5850
ridusse la nave in mille pezzi."
30:31
Smashed the vessel to smithereens.
471
1831391
1895
Ha fatto a pezzi la nave.
30:33
I love that phrase, lots of teeny, tiny little pieces.
472
1833346
2710
Adoro quella frase, tanti piccoli, piccoli pezzi.
30:36
Smithereens.
473
1836266
1050
Smithereens.
30:39
"Amid the chaos, the father and son found themselves clinging to a piece of debris.
474
1839236
4200
"In mezzo al caos, padre e figlio si ritrovarono aggrappati a un pezzo di macerie.
30:43
Their world reduced to the sound of roaring waves and the taste
475
1843496
4050
Il loro mondo ridotto al suono delle onde ruggenti e al sapore
30:47
of salty mist on their lips."
476
1847546
2490
della nebbia salata sulle loro labbra."
30:50
"The captain was dead."
477
1850386
4270
"Il capitano era morto."
30:55
Oh, he's carried on with it.
478
1855346
1260
Oh, ha continuato così.
30:56
Okay.
479
1856606
360
30:56
"The weight of their loss pressed heavily on the father, but he knew he had to
480
1856966
4752
Va bene.
"Il peso della loro perdita gravava pesantemente sul padre, ma sapeva che doveva
31:01
be strong for his son as they drifted alone in the vast and unpredictable sea."
481
1861718
4080
essere forte per suo figlio mentre andavano alla deriva da soli nel mare vasto e imprevedibile."
31:07
Um, "they prayed for salvation, but none came and they perished."
482
1867177
13640
Ehm, "pregarono per la salvezza, ma non arrivò nessuno e morirono".
31:22
Very dark!
483
1882812
540
Molto scuro!
31:23
"And they perished alone at sea."
484
1883352
3600
"E morirono soli in mare."
31:29
Oh my goodness.
485
1889802
690
Oh mio Dio.
31:30
Okay, so ChatGPT is running with this.
486
1890522
3820
Ok, quindi ChatGPT è in esecuzione con questo.
31:34
"Days turned into nights and the two souls isolated in the vastness found
487
1894762
4590
"I giorni si trasformarono in notti e le due anime isolate nella vastità trovarono
31:39
solace in each other's company."
488
1899352
1860
conforto l'una nella compagnia dell'altra."
31:42
Hang on a minute, I just said they perished at sea.
489
1902322
2160
Aspetta un attimo, ho appena detto che sono morti in mare.
31:44
If someone perishes at sea, then they die.
490
1904512
2080
Se qualcuno muore in mare, muore.
31:48
But that's not been picked up on.
491
1908572
2810
Ma questo non è stato ripreso.
31:51
Um, so "isolated in the vastness, found solace in each other's company, sharing
492
1911622
4590
Ehm, così "isolati nella vastità, hanno trovato conforto nella reciproca compagnia, condividendo
31:56
stories of the world they had left behind as they faced the inevitable."
493
1916212
3900
storie del mondo che si erano lasciati alle spalle mentre affrontavano l'inevitabile".
32:01
Let's see if I can really make this blunt.
494
1921432
2070
Vediamo se riesco davvero a dirlo in modo schietto.
32:03
"Then they drowned, the end."
495
1923592
4499
"Poi sono annegati, la fine."
32:13
Oh no, it's carrying on.
496
1933431
1860
Oh no, sta continuando.
32:15
It seems like ChatGPT is in a different mood today.
497
1935441
2820
Sembra che ChatGPT abbia uno stato d'animo diverso oggi.
32:18
When I tried to write a story with it yesterday, just testing this particular
498
1938861
4500
Quando ieri ho provato a scrivere una storia, proprio per testare questo particolare
32:23
story writing game, we were talking about a girl who'd found a lovely dog
499
1943391
5700
gioco di scrittura di storie, stavamo parlando di una ragazza che aveva trovato un cane adorabile
32:29
and they had a lovely relationship, but the dad wouldn't allow the dog
500
1949151
3090
e avevano una relazione adorabile, ma il padre non permetteva al cane
32:32
in the house, so she had to create a outdoor, like kennel for the dog.
501
1952241
6600
di entrare casa, quindi ha dovuto creare una zona esterna, come una cuccia per il cane.
32:38
But it was a very cold winter.
502
1958841
1420
Ma era un inverno molto freddo.
32:40
And so I was trying to see if I could take it down a dark route, not
503
1960661
4110
E così stavo cercando di vedere se potevo imboccare una strada oscura, non
32:45
for fun, but just to see if there were any limits on storytelling.
504
1965131
5190
per divertimento, ma solo per vedere se c'erano dei limiti alla narrazione.
32:51
And as soon as I said the dog froze to death ChatGPT was
505
1971131
4080
E non appena ho detto che il cane è morto congelato, ChatGPT mi ha
32:55
like, whoa, hang on a minute.
506
1975211
1080
detto, whoa, aspetta un attimo.
32:56
That's a bit dark.
507
1976296
895
E' un po' oscuro.
32:57
Let's backtrack and take this in a better direction.
508
1977241
4020
Facciamo un passo indietro e prendiamo la situazione in una direzione migliore.
33:02
Don't you like dark stories?
509
1982291
2040
Non ti piacciono le storie oscure?
33:04
Don't you like sad stories?
510
1984331
1410
Non ti piacciono le storie tristi?
33:05
Like life isn't all sunshine and roses, but ChatGPT was like, I'm
511
1985741
4410
Come se la vita non fosse tutta rose e fiori, ma ChatGPT era tipo, il mio
33:10
all about happiness and wellbeing.
512
1990151
1740
obiettivo è la felicità e il benessere.
33:12
So it seems like you can't write about dogs freezing to death, but
513
1992761
2730
Quindi sembra che non si possa scrivere di cani morti congelati, ma
33:15
it's okay to talk about people being shipwrecked and drowning.
514
1995496
2605
va bene parlare di persone che naufragano e annegano.
33:19
Unpredictable.
515
1999901
960
Imprevedibile.
33:21
Unpredictable.
516
2001521
1170
Imprevedibile.
33:22
So let's move on from this game, and try the grammar detective game.
517
2002751
7040
Quindi lasciamo perdere questo gioco e proviamo il gioco del detective grammaticale.
33:31
This is gonna be the last one that I talk about.
518
2011411
1860
Questo sarà l'ultimo di cui parlerò.
33:33
So grammar detective.
519
2013271
1200
Quindi detective della grammatica.
33:34
This is basically where you ask ChatGPT to write a sentence with a grammatical
520
2014561
8820
Fondamentalmente è qui che chiedi a ChatGPT di scrivere una frase con un
33:43
error and see if you can correct them.
521
2023386
2995
errore grammaticale e vedere se riesci a correggerlo.
33:47
See if you can identify the mistake and correct it.
522
2027011
2550
Vedi se riesci a identificare l'errore e correggerlo.
33:49
So here is the prompt.
523
2029561
1620
Quindi ecco il suggerimento.
33:52
"Ready to play a grammar detective game?
524
2032914
2070
"Pronti per fare un gioco di detective grammaticale?
33:55
Here's a sentence with errors: she don't likes ice cream.
525
2035389
4440
Ecco una frase con errori: non le piace il gelato.
34:00
Identify the mistakes and correct them."
526
2040429
2130
Identifica gli errori e correggili."
34:02
So I'm starting by taking the first turn.
527
2042559
2940
Quindi comincio prendendo la prima svolta.
34:05
So I want ChatGPT to be the grammar detective.
528
2045499
4250
Quindi voglio che ChatGPT sia il detective della grammatica.
34:10
So I've given it the incorrect sentence.
529
2050499
2100
Quindi ho dato la frase sbagliata.
34:13
She don't likes ice cream, and it's been corrected for me to,
530
2053229
3750
Non le piace il gelato, e per me è stato corretto,
34:17
she doesn't like ice cream.
531
2057009
2460
non le piace il gelato.
34:20
The first error was an incorrect verb form of don't, which should
532
2060099
4320
Il primo errore era una forma verbale errata di don't, che dovrebbe
34:24
be replaced with doesn't, to match the third person singular, she.
533
2064419
5500
essere sostituita con doesn't, per corrispondere alla terza persona singolare, lei.
34:30
And the incorrect verb form of likes, that was incorrect.
534
2070579
5610
E la forma verbale errata di "Mi piace" era errata.
34:36
So it should be like, to use the correct present tense form.
535
2076189
5460
Quindi dovrebbe essere come usare la forma corretta del presente.
34:41
She doesn't like ice cream.
536
2081709
1860
Non le piace il gelato.
34:43
Okay, so I'm gonna ask now.
537
2083959
2120
Ok, quindi te lo chiederò adesso.
34:47
"I want to be the detective.
538
2087474
4590
"Voglio fare il detective.
34:53
Please give me a sentence with a grammatical error to spot."
539
2093414
9750
Per favore dammi una frase con un errore grammaticale da individuare."
35:03
"Sure," says ChatGPT.
540
2103654
1680
"Certo", dice ChatGPT.
35:05
"Here's a sentence with a grammatical error for you to spot.
541
2105744
3000
"Ecco una frase con un errore grammaticale da individuare.
35:09
He don't have no time for homework."
542
2109419
3030
Non ha tempo per i compiti."
35:12
I don't know why, but I instantly wanted to do a Bristolian accent.
543
2112779
3900
Non so perché, ma ho subito voluto fare un accento bristoliano.
35:17
He don't have no time for homework.
544
2117009
2550
Non ha tempo per i compiti.
35:19
That's not really Bristolian, that's more Cornish.
545
2119619
2250
Non è propriamente Bristoliano, è più della Cornovaglia.
35:22
Anyway.
546
2122259
450
Comunque.
35:23
He don't have no time for homework should be he doesn't, he doesn't.
547
2123519
7170
Non ha tempo per i compiti, dovrebbe essere così, non lo fa.
35:30
We don't say 'he don't'.
548
2130689
870
Non diciamo "non lo fa".
35:31
We say he doesn't have, and we don't say 'no time'.
549
2131559
4230
Diciamo che non ha e non diciamo "non c'è tempo".
35:35
We've already given the negative.
550
2135889
1050
Abbiamo già dato il negativo.
35:36
He doesn't have time for homework.
551
2136944
3685
Non ha tempo per i compiti.
35:41
"Great job.
552
2141019
930
35:41
You've identified the grammatical errors and corrected it.
553
2141979
2700
"Ottimo lavoro.
Hai identificato gli errori grammaticali e li hai corretti.
35:44
Your corrected sentence is indeed grammatical, grammatically correct.
554
2144709
4020
La tua frase corretta è davvero grammaticalmente corretta.
35:48
He doesn't have time for homework.
555
2148849
1470
Lui non ha tempo per i compiti.
35:50
You fix the issue by using the correct verb form 'doesn't' instead of 'don't'.
556
2150919
6060
Risolvi il problema usando invece la forma verbale corretta 'non' di "non farlo".
35:57
And removing the double negative 'no' to make the sentence clear and accurate.
557
2157069
4560
E rimuovendo il doppio "no" negativo per rendere la frase chiara e precisa.
36:01
Well done."
558
2161899
960
Ben fatto."
36:03
Thank you.
559
2163069
420
36:03
I feel good about myself now!
560
2163494
1255
Grazie.
Adesso mi sento bene con me stesso!
36:05
If you'd like to continue, feel free to ask for another sentence, or if
561
2165499
4000
Se desideri continuare, non esitare a chiedere un'altra frase o se
36:09
you have any other language related questions or challenges, I'm here to help.
562
2169499
5340
hai altre domande o sfide relative alla lingua, sono qui per aiutarti.
36:17
Okay, so hopefully you can see that ChatGPT is a fantastic tool for learning
563
2177239
10290
Ok , quindi spero che tu possa vedere che ChatGPT è uno strumento fantastico per imparare
36:27
English for practising your English.
564
2187529
2340
l'inglese e mettere in pratica il tuo inglese.
36:30
You can also very simply just have a conversation just say, look, I am
565
2190274
4020
Puoi anche semplicemente avere una conversazione semplicemente dire, guarda, sono
36:34
a beginner level English learner, or I'm a lower intermediate English
566
2194294
5670
uno studente di inglese di livello principiante o sono un inglese intermedio inferiore
36:39
learner, or I'm an English learner and I want to improve my business English.
567
2199964
6420
o sto studiando inglese e voglio migliorare il mio inglese commerciale.
36:46
Let's pretend that we are having a conversation at work.
568
2206534
4620
Facciamo finta che stiamo conversando al lavoro.
36:51
The more information you can give ChatGPT, the better.
569
2211159
3115
Più informazioni puoi fornire a ChatGPT, meglio è.
36:54
If there's any confusion or doubt in your prompt, then it won't be as good.
570
2214844
5700
Se c'è confusione o dubbio nel tuo messaggio, allora non sarà altrettanto buono.
37:01
So it's great for learning English.
571
2221564
2190
Quindi è fantastico per imparare l'inglese.
37:03
It's great for giving you information and giving you new
572
2223754
4380
È fantastico per darti informazioni e darti nuove
37:08
words, for rewriting things as well.
573
2228134
2760
parole, anche per riscrivere cose.
37:10
So if you wrote a sentence and you want to find some synonyms or find
574
2230894
4740
Quindi, se hai scritto una frase e vuoi trovare dei sinonimi o trovare
37:15
ways of getting your message across differently, then it's very useful.
575
2235639
5605
dei modi di trasmettere il tuo messaggio in modo diverso, allora è molto utile.
37:22
But, and the big but continues to stand.
576
2242414
3180
Ma, e il grande ma continua a resistere.
37:26
It is not without its flaws.
577
2246884
2430
Non è privo di difetti.
37:30
So essentially it's flawed.
578
2250334
1920
Quindi essenzialmente è difettoso.
37:32
It's flawed.
579
2252704
720
E' difettoso.
37:33
It will make mistakes.
580
2253454
1650
Commetterà errori.
37:35
If you are expecting corrections all the way along, it's not necessarily
581
2255704
5760
Se ti aspetti correzioni fin dall'inizio, non necessariamente
37:41
going to give them to you, even if you asked in your initial prompt.
582
2261464
4500
te le darà, anche se le hai richieste nel prompt iniziale.
37:47
So, with that in mind, it's still a very useful tool, just don't
583
2267014
4140
Quindi, con questo in mente, è ancora uno strumento molto utile, basta non
37:51
take everything it says as gospel.
584
2271154
2370
prendere tutto ciò che dice come vangelo.
37:53
That's all I'm trying to push.
585
2273884
1980
Questo è tutto quello che sto cercando di spingere.
37:56
Anyway, I do hope you have enjoyed this slightly different and
586
2276944
3270
Ad ogni modo, spero che ti sia piaciuto questo
38:00
unusual um, deep dive into the uses of ChatGPT in a playful way.
587
2280219
7075
approfondimento leggermente diverso e insolito sugli usi di ChatGPT in modo giocoso.
38:07
Thank you for lending me your ears.
588
2287924
1860
Grazie per avermi prestato le tue orecchie.
38:10
Until next time, take very good care, and goodbye.
589
2290144
5800
Alla prossima volta, stai molto attento e arrivederci.
A proposito di questo sito web

Questo sito vi presenterà i video di YouTube utili per l'apprendimento dell'inglese. Vedrete lezioni di inglese tenute da insegnanti di alto livello provenienti da tutto il mondo. Fate doppio clic sui sottotitoli in inglese visualizzati su ogni pagina video per riprodurre il video da lì. I sottotitoli scorrono in sincronia con la riproduzione del video. Se avete commenti o richieste, contattateci tramite questo modulo di contatto.

https://forms.gle/WvT1wiN1qDtmnspy7