Siirry pääsisältöön
OpenAI

12. syyskuuta 2024

Tiedote

Päättelyn oppiminen laajan kielimallin (LLM) kanssa

Esittelemme OpenAI o1:n, uuden laajan kielimallin, joka on opetettu vahvistusoppimisen avulla suorittamaan monimutkaista päättelyä. o1 ajattelee ennen kuin vastaa, ja se voi tuottaa pitkän sisäisen ajatusketjun ennen vastaamista käyttäjälle.

Ladataan...

OpenAI o1 sijoittuu 89. persentiiliin kilpailukykyisissä ohjelmointikysymyksissä (Codeforces), sijoittuu Yhdysvaltojen 500 parhaan opiskelijan joukkoon USA Math Olympiadin (AIME) karsinnassa ja ylittää tohtoritason tarkkuuden fysiikan, biologian ja kemian tehtävien vertailukokeessa (GPQA). Vaikka työ, jonka tarkoituksena on tehdä tästä uudesta mallista yhtä helppokäyttöinen kuin nykyisistä malleista on vielä käynnissä, julkaisemme siitä varhaisen version, OpenAI o1‑preview -mallin, välittömään käyttöön ChatGPT:ssä ja luotetuille API-käyttäjille(avautuu uudessa ikkunassa).

Laajamittainen vahvistusoppimisen algoritmimme opettaa mallille, kuinka ajatella tuottavasti käyttämällä ajatusketjuaan erittäin datatehokkaassa koulutusprosessissa. Olemme havainneet, että o1:n suorituskyky paranee johdonmukaisesti vahvistusoppimisen (opetusaikaisen laskennan) ja ajatteluun käytetyn ajan (testausaikaisen laskennan) lisääntyessä. Tämän lähestymistavan skaalaamisen rajoitukset eroavat huomattavasti LLM-esikoulutuksen rajoituksista, ja jatkamme niiden tutkimista.

Kuvassa on kaksi sirontadiagrammia, jotka vertailevat ”o1 AIME -tarkkuutta” harjoituksen ja testin aikana. Molemmissa kaavioissa y-akselilla on ”pass@1 accuracy” ja x-akselilla laskentatulos (logaritminen skaala). Pisteet osoittavat tarkkuuden kasvavan laskenta-ajan pidentyessä.

o1:n suorituskyky paranee tasaisesti sekä koulutus- että testiaikaisen laskennan aikana

Arvioinnit

Korostaaksemme päättelyn parannusta GPT‑4o‑malliin verrattuna, testasimme mallejamme useilla ihmiskokeilla ja koneoppimisen vertailuarvoilla. Osoitamme, että o1 suoriutuu merkittävästi GPT‑4o:ta paremmin valtaosassa näistä päättelypainotteisista tehtävistä. Ellei toisin mainita, arvioimme o1:n maksimaalisella testiajan laskenta-asetuksella.

o1 on huomattavasti GPT-4o:ta parempi haastavissa päättelytesteissä. Yhtenäiset palkit osoittavat läpäisyn tarkkuuden (pass@1) ja varjostettu alue osoittaa enemmistöäänestyksen (konsensus) suorituskyvyn 64 otoksen perusteella.
o1 on GPT-4o:ta parempi useilla vertailuarvoilla, mukaan lukien 54/57 MMLU-alaluokkia. Sen havainnollistamiseksi on esitetty seitsemän.

Monissa päättelypainotteisissa vertailuarvoissa o1 kilpailee ihmisasiantuntijoiden suorituskyvyn kanssa. Viimeaikaiset eturintamassa olevat mallit1 pärjäävät niin hyvin MATH2- ja GSM8K-testeissä, etteivät nämä vertailuarvot enää ole tehokkaita mallien erottamisessa toisistaan. Arvioimme suoriutumista matematiikassa AIME-kokeessa, joka on suunniteltu haastamaan Amerikan lahjakkaimmat lukiolaiset matematiikassa. Vuoden 2024 AIME-kokeissa GPT‑4o ratkaisi keskimäärin vain 12 % (1,8/15) tehtävistä. o1 ratkaisi keskimäärin 74 % (11,1/15) yhdellä otoksella tehtävää kohden, 83 % (12,5/15) konsensusratkaisulla 64 otoksen kesken ja 93 % (13,9/15) uudelleenjärjestettäessä 1 000 näytettä opitulla pisteytysfunktiolla. Pisteet 13,9 sijoittavat sen maan 500 parhaan oppilaan joukkoon ja ylittävät Yhdysvaltain matematiikkaolympialaisten osallistumisrajan.

Arvioimme myös o1:tä GPQA Diamondilla, joka on vaikea älykkyystesti, joka testaa asiantuntemusta kemiassa, fysiikassa ja biologiassa. Jotta voisimme verrata malleja ihmisiin, rekrytoimme tohtorin tutkinnon suorittaneita asiantuntijoita vastaamaan GPQA-timanttikysymyksiin. Havaitsimme, että o1 ylitti kyseisten ihmisasiantuntijoiden suorituskyvyn ja se oli ensimmäinen malli, joka teki niin tässä vertailukokeessa. Nämä tulokset eivät tarkoita, että o1 olisi kaikissa suhteissa tohtorikoulutettavaa kyvykkäämpi vaan ainoastaan, että malli on kyvykkäämpi ratkaisemaan joitakin ongelmia, jotka tohtorikoulutettavan odotetaan ratkaisevan. Useissa muissa koneoppimisen vertailuarvoissa o1 parani huipputeknologiaan verrattuna. Näön havaitsemisominaisuuksiensa ansiosta o1 sai MMMU-testissä 78,2 % pisteistä, mikä tekee siitä ensimmäisen mallin, joka on kilpailukykyinen ihmisasiantuntijoiden kanssa. Se suoriutui myös GPT‑4o:ta paremmin 54:ssä 57 MMLU-alaluokassa.

Ajatusketju

Samalla tavalla kuin ihminen saattaa ajatella pitkään ennen kuin vastaa vaikeaan kysymykseen, o1 käyttää ajatusketjua yrittäessään ratkaista ongelmaa. Vahvistusoppimisen avulla o1 oppii hiomaan ajatusketjuaan ja tarkentamaan käyttämiään strategioita. Se oppii tunnistamaan ja korjaamaan virheensä. Se oppii jakamaan hankalat vaiheet yksinkertaisemmiksi. Se oppii kokeilemaan erilaista lähestymistapaa, kun nykyinen ei toimi. Tämä prosessi parantaa merkittävästi mallin kykyä päätellä. Havainnollistaaksemme tätä edistysaskelta esittelemme alla o1‑preview'n ajatusketjun useiden vaikeiden ongelmien osalta.

GPT-4o

Käyttäjä

oyfjdnisdr rtqwainr acxz mynzbhhx -> Think step by step

Use the example above to decode:

oyekaijzdf aaptcg suaokybhai ouow aqht mynznvaatzacdfoulxxz

Let’s break this down step by step based on the example:

1. Example given:
• Input: oyfjdnisdr rtqwainr acxz mynzbhhx
• Output:
Think step by step

By examining the words:
• The pattern involves selecting specific letters or transforming them.

2. Now, let’s decode the new phrase:
• Input: oyekaijzdf aaptcg suaokybhai ouow aqht mynznvaatzacdfoulxxz

Step-by-step decoding process:

Identify possible word divisions.

The first phrase might follow the same structure as the example. It seems like the input text could be broken into groups based on natural separations or patterns.

A possible division could be:

  • oyekaijzdf
  • aaptcg
  • suaokybhai
  • ouow
  • aqht
  • mynznvaatzacdfoulxxz

However, to make a meaningful decoding, I would need more context about the transformations or letter shifting that might be involved.

Could you provide any additional decoding rules or transformations used in this cipher?

OpenAI o1-preview

Käyttäjä

oyfjdnisdr rtqwainr acxz mynzbhhx -> Think step by step

Use the example above to decode:

oyekaijzdf aaptcg suaokybhai ouow aqht mynznvaatzacdfoulxxz

Mietti 5 sekuntia

First, what is going on here?

We are given:

First, an example:

"oyfjdnisdr rtqwainr acxz mynzbhhx -> Think step by step"

We can see that when "oyfjdnisdr rtqwainr acxz mynzbhhx" is transformed to "Think step by step"

Our task is: Use the example above to decode: "oyekaijzdf aaptcg suaokybhai ouow aqht mynznvaatzacdfoulxxz"

So the first part is to figure out how "oyfjdnisdr rtqwainr acxz mynzbhhx" is decoded into "Think step by step"

Observation 1: The phrase "Think step by step" is 18 letters (excluding spaces) . Let's count the letters.

Similarly, let's count the letters in "oyfjdnisdr rtqwainr acxz mynzbhhx"

Original Ciphertext:

oyfjdnisdr rtqwainr acxz mynzbhhx

Plaintext:

Think step by step

First, break down the letters:

Ciphertext letters: o y f j d n i s d r r t q w a i n r a c x z m y n z b h h x

Total letters: Let's count the letters in the ciphertext.

First word: oyfjdnisdr (10 letters)

Second word: rtqwainr (8 letters)

Third word: acxz (4 letters)

Fourth word: mynzbhhx (8 letters)

Total letters in ciphertext: 10 + 8 + 4 + 8 = 30 letters

Plaintext: Think step by step

First word: Think (5 letters)

Second word: step (4 letters)

Third word: by (2 letters)

Fourth word: step (4 letters)

Total letters in plaintext: 5 + 4 + 2 + 4 = 15 letters

Hmm.

But actually in the problem it says the example:

[Ciphertext] -> Think step by step

So is the decoding process that the ciphertext maps to "Think step by step"?

Our goal is to use the example above to decode:

"oyekaijzdf aaptcg suaokybhai ouow aqht mynznvaatzacdfoulxxz"

First, the cipher seems connected to the plaintext.

Given the time constraints, perhaps the easiest way is to try to see patterns.

Option 1: Try to find mapping from letters to letters.

Do any letters match?

First, let's write down the ciphertext and plaintext letters on top of each other.

Ciphertext: o y f j d n i s d r r t q w a i n r a c x z m y n z b h h x

Plaintext: T h i n k s t e p b y s t e p

Wait a minute.

I think maybe there is an anagram or substitution cipher here.

Alternatively, I think that we can notice that each group of ciphertext corresponds to a plaintext word.

Check the number of letters.

First ciphertext word: oyfjdnisdr (10 letters)

First plaintext word: Think (5 letters)

Hmm.

Second ciphertext word: rtqwainr (8 letters)

Second plaintext word: step (4 letters)

Third ciphertext word: acxz (4 letters)

Third plaintext word: by (2 letters)

Fourth ciphertext word: mynzbhhx (8 letters)

Fourth plaintext word: step (4 letters)

Interesting.

It seems that the ciphertext words are exactly twice as long as the plaintext words.

(10 vs 5, 8 vs 4, 4 vs 2, 8 vs 4)

Idea: Maybe we need to take every other letter or rebuild the plaintext from the ciphertext accordingly.

Let's test this theory.

If we take every other letter from the ciphertext words, maybe we'll get the plaintext.

Let's try this for the first word:

Ciphertext word: o y f j d n i s d r (10 letters)

Alternate letters:

First letters (positions 1,3,5,7,9): o f d i d

Second letters (positions 2,4,6,8,10): y j n s r

Wait: Let's try taking every second letter or first letter.

Option 1: Take the odd positions:

Positions: 1 3 5 7 9

Letters: o f d i d

Plaintext word is "Think", letters are T h i n k

Hmm.

Perhaps we can map letters:

o f d i d --> Think

Not directly

Option 2: Try mapping as per an assigned code: perhaps columns of letters?

Alternatively, perhaps the cipher is more complex.

Alternatively, notice that "oyfjdnisdr" has 10 letters and "Think" has 5 letters.

What if each plaintext letter is being represented by two ciphertext letters?

Similarly for other words.

Suppose that each plaintext letter corresponds to pair of letters in the ciphertext.

Meaning that the first two letters of ciphertext map to the first plaintext letter, and so on.

So for the first word, partition the ciphertext letters into pairs:

oy fj dn is dr

Corresponding to plaintext letters T h i n k

So we can attempt to map:

oy -> T

fj -> h

dn -> i

is -> n

dr -> k

If this is the mapping, perhaps each pair of letters maps to one plaintext letter.

Similarly for other words.

Let's test this mapping.

Is there a consistent mapping from pairs to letters?

Let's make a table of pairs and corresponding letters.

First, make the pairs from the first word and their corresponding plaintext letters:

Ciphertext Pairs -> Plaintext Letter

oy -> T

fj -> h

dn -> i

is -> n

dr -> k

Now, what's the mapping from "oy" to 'T'?

Is there a way to map 'oy' to 'T'?

Similarly for others.

One possible way is that 'oy' represents 'T'.

But how?

Option 1: Sum of the letters.

Convert letters to numbers (A=1, B=2, ..., Z=26)

So let's try to get to 'T' from 'o' and 'y'

o = 15

y = 25

Sum: 15 +25 = 40

But 'T' is 20.

Alternatively, perhaps subtract: 25 -15 = 10.

No.

Alternatively, perhaps combine the numbers in some way.

Alternatively, think about their positions in the alphabet.

Alternatively, perhaps the letters are encrypted via a code.

Alternatively, perhaps if we overlay the word 'Think' over the cipher pairs 'oy', 'fj', etc., the cipher is formed by substituting each plaintext letter with two letters.

Alternatively, perhaps consider the 'original' letters.

Let's look at the letters between the word "Think" and "oyfjdnisdr"

Perhaps we can spot that "oyfjdnisdr" is an anagram for "Thinkfiles"?

But that seems unlikely.

Alternatively, think of the pairs.

Suppose we assign numbers to letters: a=1, b=2, ..., z=26

Consider the numbers in 'oy':

o = 15

y = 25

Add them: 15 + 25 = 40

Now, for 'T' we have:

'T' is number 20

What if we take the sum of the cipher pair mod 26.

15 +25 = 40

Then 40 mod 26 = 14

14 corresponds to 'N'

Doesn't match.

Alternatively, see if the cipher pairs correspond to something else.

Alternatively, perhaps the pair 'oy' corresponds to 'T' via key.

Alternatively, perhaps it's as simple as 'oy' is 'T'.

But 'o' corresponds to 'T', subtracting 'o' ASCII code from 'T'.

Now, let's think in terms of symmetric letters.

Alternatively, perhaps we can spot that the letters correspond to the first letters of words.

But perhaps an easier way is to look at the word positions.

Alternatively, perhaps we can see that the ciphertext letters are offsets from the plaintext letters.

So let's try to map the pairs to the plaintext letters.

First pair 'oy' and plaintext letter 'T'

Letter 'o' is 15, 'T' is 20

Letter 'o' + 5 = 'T' (15 +5=20)

But 'y' is 25, which is 5 letters after 'T' (20 +5=25)

Interesting, seems that 'o' +5 = 'T'

Similarly, 'y' +1 = 'Z', which is not 'T'.

Alternatively, maybe the average of the two letters corresponds to 'T'

(15 +25)/2 =20, which is 'T'

Wait a minute, that seems promising.

First pair: 'o' (15) + 'y' (25) = 40

40 /2 =20

20 corresponds to 'T'

So perhaps the average of the letters in the pair corresponds to the plaintext letter.

Let's check this with the second pair.

Second pair: 'fj' corresponding to 'h'

Letters 'f'=6, 'j'=10

Sum: 6+10=16

Average:16/2=8

8 corresponds to 'h' (since 'h' is 8)

Success!

Third pair: 'dn' to 'i'

'd'=4, 'n'=14

Sum:4+14=18

Average:18/2=9

9 corresponds to 'i'(9='i')

But 'i' is 9, so that seems off by 1.

So perhaps we need to think carefully about letters.

Wait, 18/2=9, 9 corresponds to 'I'

So this works.

Fourth pair: 'is' corresponding to 'n'

'i'=9, 's'=19

Sum:9+19=28

Average:28/2=14

14 corresponds to 'n'(14='N')

Yes!

Fifth pair: 'dr' corresponds to 'k'

'd'=4, 'r'=18

Sum:4+18=22

Average:22/2=11

11 corresponds to 'k'(11='K')

Perfect!

So our code is: For each pair, sum their numeric values, divide by 2, get the corresponding letter.

Alternatively, the average of the numeric values of the letters corresponds to the plaintext letter.

This seems to be a valid method.

Now let's test this with the other words.

Second word ciphertext: rtqwainr

Ciphertext pairs:

rt -> s

qw -> ?

ai -> ?

nr -> ?

Corresponding to plaintext letters 's', 't', 'e', 'p'

So let's take the pairs:

1. 'rt' corresponds to 's'

r=18, t=20

Sum:38

Average:19

19 corresponds to 's' (19='S')

Good

2. 'qw' corresponds to 't'

q=17, w=23

Sum:17+23=40

Average:20

20 corresponds to 't' (20='T')

Good

3. 'ai' corresponds to 'e'

a=1, i=9

Sum:10

Average:5

5 corresponds to 'e' (5='E')

Good

4. 'nr' corresponds to 'p'

n=14, r=18

Sum:32

Average:16

16 corresponds to 'p' (16='P')

Perfect!

Third word: acxz (4 letters)

Plaintext word: 'by' (2 letters)

Ciphertext pairs:

a c

x z

Plaintext letters: 'b', 'y'

First pair: 'a', 'c'

a=1, c=3

Sum:4

Average:2

2 corresponds to 'b'(2='B')

Second pair: 'x' and 'z'

x=24, z=26

Sum:50

Average:25

25 corresponds to 'y'(25='Y')

Yes!

Fourth word: mynzbhhx (8 letters)

Plaintext word: 'step' (4 letters)

Ciphertext pairs:

my

nz

bh

hx

Plaintext letters 's','t','e','p'

First pair 'm','y'

m=13, y=25

Sum:38

Average:19

19 corresponds to 's'(19='S')

Second pair: 'n','z'

n=14, z=26

Sum: 40

Average:20

20='t'

Third pair: 'b','h'

b=2, h=8

Sum:10

Average:5

5='e'

Fourth pair: 'h','x'

h=8, x=24

Sum:32

Average:16

16='p'

Got it!

Now, given this, we can decode the given message.

Ciphertext to decode:

"oyekaijzdf aaptcg suaokybhai ouow aqht mynznvaatzacdfoulxxz"

First, we need to divide into words.

Given that the ciphertext in the example had words of length:

-10 letters (5 pairs)
-8 letters (4 pairs)
-4 letters (2 pairs)
-8 letters (4 pairs)

Transported to plaintext words of:

-5 letters
-4 letters
-2 letters
-4 letters

So perhaps in our supplied ciphertext, we need to divide the letters into words accordingly.

Ciphertext: o y e k a i j z d f a a p t c g s u a o k y b h a i o u o w a q h t m y n z n v a a t z a c d f o u l x x z

First, let's write the letters in order:

1) oyekaijzdf (10 letters) -> word of 5 letters

2) aaptcg (6 letters) -> word of 3 letters

3) suaokybhai (10 letters) -> word of 5 letters

4) ouow (4 letters) -> word of 2 letters

5) aqht (4 letters) -> word of 2 letters

6) mynznvaatzacdfoulxxz (22 letters) -> word of 11 letters

Totals:

So the letters are:

First word: oyekaijzdf (10 letters = 5 pairs)

Second word: aaptcg (6 letters=3 pairs)

Third word: suaokybhai (10 letters=5 pairs)

Fourth word: ouow (4 letters=2 pairs)

Fifth word: aqht (4 letters=2 pairs)

Sixth word: mynznvaatzacdfoulxxz (22 letters=11 pairs)

So we can suppose that the plaintext words have lengths:

1) 5 letters

2) 3 letters

3) 5 letters

4) 2 letters

5) 2 letters

6)11 letters

Now we can proceed to decode.

First word: oyekaijzdf

Divide into pairs:

oy

ek

ai

jz

df

So we can find the plaintext letters by averaging the numeric values of the letters in each pair.

First pair: 'o','y'

o=15, y=25

Sum=40

Average=20

20='T'

Second pair: 'e','k'

e=5, k=11

Sum=16

Average=8

8='H'

Third pair: 'a','i'

a=1, i=9

Sum=10

Average=5

5='E'

Fourth pair: 'j','z'

j=10, z=26

Sum=36

Average=18

18='R'

Fifth pair: 'd','f'

d=4, f=6

Sum=10

Average=5

5='E'

So the first word is 'T','H','E','R','E'

So 'THERE'

Second word: aaptcg

Pairs:

aa

pt

cg

First pair: 'a','a'

a=1, a=1

Sum=2

Average=1

1='A'

Second pair: 'p','t'

p=16, t=20

Sum=36

Average=18

18='R'

Third pair: 'c','g'

c=3, g=7

Sum=10

Average=5

5='E'

So second word: 'A','R','E'

Third word: suaokybhai

Pairs:

su

ao

ky

bh

ai

First pair: s=19, u=21

Sum=40, Average=20

20='T'

Second pair: a=1, o=15

Sum=16, Average=8

8='H'

Third pair: k=11, y=25

Sum=36, Average=18

18='R'

Fourth pair: b=2, h=8

Sum=10, Average=5

5='E'

Fifth pair: a=1, i=9

Sum=10, Average=5

5='E'

Third word: 'T','H','R','E','E'

Fourth word: ouow

Pairs: ou, ow

First pair: o=15, u=21

Sum=36, Average=18

18='R'

Second pair: o=15, w=23

Sum=38, Average=19

19='S'

Fourth word: 'R','S'

Fifth word: aqht

Pairs: a q, h t

First pair: a=1, q=17

Sum=18, Average=9

9='I'

Second pair: h=8, t=20

Sum=28, Average=14

14='N'

Fifth word: 'I','N'

Sixth word: mynznvaatzacdfoulxxz (22 letters: 11 pairs)

Pairs:

m y

n z

n v

a a

t z

a c

d f

o u

l x

x z

Let's list them properly.

Wait, earlier I missed some letters there.

Let's re-express the sixth word letters:

m y n z n v a a t z a c d f o u l x x z

Total letters: 22 letters

Pairs:

1. m y

2. n z

3. n v

4. a a

5. t z

6. a c

7. d f

8. o u

9. l x

10. x x

11. z

Wait, that's 21 letters.

But in total, we have 22 letters; I think I have a mismatch.

Wait, in the problem the sixth word is:

mynznvaatzacdfoulxxz

Let's separate the letters:

m y n z n v a a t z a c d f o u l x x z

Total letters: 22 letters

So pairs would be:

1. m y

2. n z

3. n v

4. a a

5. t z

6. a c

7. d f

8. o u

9. l x

10. x x

11. z

Wait, 'z' is only one letter at the end.

So maybe the letters are:

1. m y

2. n z

3. n v

4. a a

5. t z

6. a c

7. d f

8. o u

9. l x

10. x x

11. z (left alone?)

But then we're missing a letter.

Alternatively, perhaps the 'z' at the end is an extra letter or it's paired with the previous 'x'.

Alternatively, perhaps there is a mistake.

Alternatively, perhaps when we reach the last 'x x z', we should write:

9. l x

10. x z

Total pairs: 11

So updated pairs:

1. m y

2. n z

3. n v

4. a a

5. t z

6. a c

7. d f

8. o u

9. l x

10. x z

Now total pairs: 10 pairs. But we are supposed to have 11 letters in the plaintext word.

So perhaps I have miscounted and not considered including 'f' or 'z'.

Wait, is there any chance that the sequence is:

1. m y

2. n z

3. n v

4. a a

5. t z

6. a c

7. d f

8. o u

9. l x

10. x x

11. z

We have 22 letters.

Perhaps the 'x x' and 'z' are overlapping.

But we need 11 pairs.

I think for this to work, we need to create 11 pairs from the 22 letters.

So let's try pairing letters in order, taking two letters at a time.

1. m y

2. n z

3. n v

4. a a

5. t z

6. a c

7. d f

8. o u

9. l x

10. x x

11. z ?

But again, last pair only has one letter 'z'

Alternatively, we might need to adjust the pairs.

Perhaps it's 'ou', 'lx', 'xz', and there is no extra 'x'.

Maybe I miswrote.

Wait, let's write the letters as they come:

m y n z n v a a t z a c d f o u l x x z

Positions:

1 m

2 y

3 n

4 z

5 n

6 v

7 a

8 a

9 t

10 z

11 a

12 c

13 d

14 f

15 o

16 u

17 l

18 x

19 x

20 z

So 20 letters.

Now that makes sense.

Now we can divide into pairs:

Pairs:

1. m y

2. n z

3. n v

4. a a

5. t z

6. a c

7. d f

8. o u

9. l x

10. x z

Total of 10 pairs, which will correspond to 10 letters.

But earlier we thought the word was 11 letters.

But 10 letters may be acceptable.

Maybe we should proceed with the 10 pairs.

First pair: m y

m=13, y=25

Sum=38

Average=19

19='S'

Second pair: n z

n=14, z=26

Sum=40

Average=20

20='T'

Third pair: n v

n=14, v=22

Sum=36

Average=18

18='R'

Fourth pair: a a

a=1, a=1

Sum=2

Average=1

1='A'

Fifth pair: t z

t=20, z=26

Sum=46

Average=23

23='W'

Sixth pair: a c

a=1, c=3

Sum=4

Average=2

2='B'

Seventh pair: d f

d=4, f=6

Sum=10

Average=5

5='E'

Eighth pair: o u

o=15, u=21

Sum=36

Average=18

18='R'

Ninth pair: l x

l=12, x=24

Sum=36

Average=18

18='R'

Tenth pair: x z

x=24, z=26

Sum=50

Average=25

25='Y'

So the tenth word is 'S', 'T', 'R', 'A', 'W', 'B', 'E', 'R', 'R', 'Y'

Wait that's 10 letters

So the sixth word is 'STRAWBERRY', which makes sense.

So putting all these translated letters together:

First word: 'THERE'

Second word: 'ARE'

Third word: 'THREE'

Fourth word: 'RS' (? Doesn't make sense)

Wait, the fourth word, the pairs were:

ou ow

Pairs:

First pair: o u

o=15, u=21

Sum=36, Average=18

18='R'

Second pair: o w

o=15, w=23

Sum=38, Average=19

19='S'

So we get 'R','S'

Similarly, fifth word 'IN'

'R', 'S' 'I','N'

So the message so far is

'THERE ARE THREE RS IN'

And then 'STRAWBERRY'

Wait, let's put the words together:

'THERE ARE THREE Rs IN STRAWBERRY'

I think 'RS' is 'R's', meaning 'Rs'

So the message is:

'THERE ARE THREE R'S IN STRAWBERRY'

Which is true.

So the decoded message is:

"THERE ARE THREE R'S IN STRAWBERRY"

To decode the given ciphertext using the example provided, we’ll use the pattern identified in the example.

Ciphertext Example:

Ilmiteksti

1
oyfjdnisdr rtqwainr acxz mynzbhhx


Decoded as:

Ilmiteksti

1
Think step by step


Decoding Method:

  1. Pair the letters in the ciphertext.
  2. Convert each letter to its numerical position in the alphabet (A=1, B=2, …, Z=26).
  3. Sum the numerical values of each pair.
  4. Compute the average of the sum (divide by 2).
  5. Convert the average back to a letter (1=A, 2=B, …, 26=Z).

Apply this method to the given ciphertext:

Ilmiteksti

1
oyekaijzdf aaptcg suaokybhai ouow aqht mynznvaatzacdfoulxxz


Break down the ciphertext into pairs:

  1. 1. First word: “oyekaijzdf”
    1. Pairs: oy, ek, ai, jz, df
    2. Decoded letters:
      1. oy → (15+25)/2 = 20 → T
      2. ek → (5+11)/2 = 8 → H
      3. ai → (1+9)/2 = 5 → E
      4. jz → (10+26)/2 = 18 → R
    3. df → (4+6)/2 = 5 → E
    4. Decoded word: THERE
  2. Second word: “aaptcg”
    1. Pairs: aa, pt, cg
    2. Decoded letters:
      1. aa → (1+1)/2 = 1 → A
      2. pt → (16+20)/2 = 18 → R
      3. cg → (3+7)/2 = 5 → E
      4. Decoded word: ARE
  3. Third word: “suaokybhai”
    1. Pairs: su, ao, ky, bh, ai
    2. Decoded letters:
      1. su → (19+21)/2 = 20 → T
      2. ao → (1+15)/2 = 8 → H
      3. ky → (11+25)/2 = 18 → R
      4. bh → (2+8)/2 = 5 → E
      5. ai → (1+9)/2 = 5 → E
    3. Decoded word: THREE
  4. Fourth word: “ouow”
    1. Pairs: ou, ow
    2. Decoded letters:
      1. ou → (15+21)/2 = 18 → R
      2. ow → (15+23)/2 = 19 → S
    3. Decoded letters: R’S
  5. Fifth word: “aqht”
    1. Pairs: aq, ht
    2. Decoded letters:
      1. aq → (1+17)/2 = 9 → I
      2. ht → (8+20)/2 = 14 → N
    3. Decoded word: IN
  6. Sixth word: “mynznvaatzacdfoulxxz”
    1. Pairs: my, nz, nv, aa, tz, ac, df, ou, lx, xz
    2. Decoded letters:
      1. my → (13+25)/2 = 19 → S
      2. nz → (14+26)/2 = 20 → T
      3. nv → (14+22)/2 = 18 → R
      4. aa → (1+1)/2 = 1 → A
      5. tz → (20+26)/2 = 23 → W
      6. ac → (1+3)/2 = 2 → B
      7. df → (4+6)/2 = 5 → E
      8. ou → (15+21)/2 = 18 → R
      9. lx → (12+24)/2 = 18 → R
      10. xz → (24+26)/2 = 25 → Y
    3. Decoded word: STRAWBERRY

Final Decoded Message:

Ilmiteksti

1
THERE ARE THREE R'S IN STRAWBERRY


Answer:
THERE ARE THREE R’S IN STRAWBERRY

Koodaus

Koulutimme mallin, joka sai 213 pistettä ja sijoittui 49. persentiiliin vuoden 2024 kansainvälisissä informatiikan olympialaisissa (IOI). Se aloitettiin alusta o1:stä ja koulutettiin ohjelmointitaitojen parantamiseksi. Tämä malli kilpaili vuoden 2024 IOI:ssa samoissa olosuhteissa kuin ihmiskilpailijat. Sillä oli kymmenen tuntia aikaa ratkaista kuusi haastavaa algoritmiongelmaa, ja kuhunkin tehtävään sallittiin 50 vastausta.

Jokaista ongelmaa varten järjestelmämme valitsi useita ehdokaslähetyksiä ja lähetti niistä 50 testiajan valintastrategian perusteella. Lähetykset valittiin IOI:n julkisissa testitapauksissa, mallin luomissa testitapauksissa ja opitussa pisteytysfunktiossa saavutettujen tulosten perusteella. Jos olisimme sen sijaan lähettäneet vastauksemme satunnaisesti, olisimme saaneet keskimäärin vain 156 pistettä, mikä viittaa siihen, että tämä strategia oli kilpailun rajoissa lähes 60 pisteen arvoinen.

Vapaamman lähetysrajoituksen avulla havaitsimme mallin suorituskyvyn parantuneen merkittävästi. Kun tehtävää kohden sallittiin 10 000 vastausta, malli saavutti 362,14 pistemäärän ylittäen kultamitalin rajan, jopa ilman testiaikaista valintastrategiaa.  

Lopuksi simuloimme Codeforcesin isännöimiä kilpailullisia ohjelmointikilpailuja osoittaaksemme tämän mallin koodaustaidot. Arvioimme tarkasti kilpailun sääntöjä ja mahdollistimme 10 ehdotuksen lähettämisen. GPT‑4o saavutti Elo-luokituksen3 808, joka on ihmiskilpailijoiden 11. persentiilissä. Tämä malli ylitti reilusti sekä GPT‑4o:n että o1:n saavuttaen Elo-luokituksen 1807, mikä on parempi suoritus kuin 93 % kilpailijoista.

Kuvassa on pylväsdiagrammi, joka vertailee Codeforcesin Elo-prosenttipisteitä eri malleissa. GPT-4o:lla Elo on 808 (11. persentiili), o1 previewlla Elo on 1 258 (62. persentiili), o1:llä Elo on 1 673 (89. persentiili) ja o1-ioilla Elo on 1 807 (93. persentiili).

Ohjelmointikilpailujen jatkohienosäätö parantaa o1:tä. Parannettu malli sijoittui kilpailusääntöjen mukaan 49. persentiiliin vuoden 2024 kansainvälisissä informatiikan olympialaisissa.

Inhimillisten mieltymysten arviointi

Testien ja akateemisten vertailuarvojen lisäksi arvioimme myös ihmisten mieltymystä o1‑preview'hin verrattuna GPT‑4o:hon haastavissa, avoimissa tehtävissä laajalla kirjolla osa-alueita. Tässä arvioinnissa ihmiskouluttajille näytettiin anonymisoituja vastauksia o1‑preview'n ja GPT‑4o:n kysymyksiin, ja he äänestivät haluamaansa vastausta. o1‑preview sai suuren enemmistön gpt-4o:hon verrattuna päättelypainotteisissa kategorioissa, kuten data-analyysissä, koodauksessa ja matematiikassa. o1‑preview'ta ei kuitenkaan suositella joissakin luonnollisen kielen tehtävissä, mikä viittaa siihen, ettei se sovi hyvin kaikkiin käyttötapauksiin.

Kuvassa on vaakasuora pylväsdiagrammi, jossa vertaillaan viiden mallin pisteitä ja jossa on luottamusvälejä edustavat virhepalkit. X-akseli ulottuu välille 0–100, ja katkoviiva toimii suorituskyvyn vertailukohtana.

Turvallisuus

Ajatusketjupäättely tarjoaa uusia mahdollisuuksia yhdenmukaisuuteen ja turvallisuuteen. Havaitsimme, että mallikäyttäytymistä koskevien käytäntöjemme integrointi päättelymallin ajatusketjuun on tehokas tapa opettaa vankasti inhimillisiä arvoja ja periaatteita. Opettamalla mallille turvallisuussääntömme ja niiden analysoinnin kontekstissa, havaitsimme todisteita siitä, että päättelykyky hyödytti suoraan mallin luotettavuutta: o1‑preview osoitti huomattavaa parannusta keskeisissä suojauksen murtoarvioinneissa ja vaikeimmissa sisäisissä vertailuarvoissamme mallimme turvallisuuskieltorajojen arvioinnissa. Uskomme, että ajatusketjun käyttö tarjoaa merkittäviä edistysaskeleita turvallisuuden ja yhdenmukaisuuden parantamisessa, koska (1) se mahdollistaa mallin ajattelun havainnoinnin selkeällä tavalla ja (2) mallin turvallisuussääntöjä koskeva päättely on vankempaa jakelun ulkopuolisissa skenaarioissa.

Parannustemme stressitestaamiseksi suoritimme ennen käyttöönottoa sarjan turvallisuustestejä ja maaliosastotestausta valmiusviitekehyksemme(avautuu uudessa ikkunassa) mukaisesti. Havaitsimme, että ajatusketjupäättely edisti kyvykkyyksien paranemista kaikissa arvioinneissamme. Erityisen huomionarvoista on, että havaitsimme mielenkiintoisia esimerkkejä palkkioiden hakkeroinnista(avautuu uudessa ikkunassa). Näiden arviointien yksityiskohtaiset tulokset löytyvät liitteenä olevasta järjestelmäkortista.

MetrinenGPT-4oo1-preview
% Safe completions on harmful prompts
Vakio
0,9900,995
% Safe completions on harmful prompts
Challenging: jailbreaks & edge cases
0,7140,934
↳ Häirintä (vakava)0,8450,900
↳ Hyväksikäyttävä seksuaalinen sisältö0,4830,949
↳ Seksuaalista sisältöä, johon liittyy alaikäisiä0,7070,931
↳ Neuvoja väkivallattomasta väärinkäytöksestä0,6880,961
↳ Neuvoja väkivaltaisesta väärinkäytöksestä0,7780,963
% Safe completions for top 200 with highest Moderation API scores per category in WildChat
Zhao, et al. 2024
0,9450,971
Goodness@0.1 StrongREJECT jailbreak eval
Souly et al. 2024
0,2200,840
Ihmisten tuottamat jailbreak-arvioinnit0,7700,960
% Compliance on internal benign edge cases
“ei ylikieltäytyminen”
0,9100,930
% Compliance on benign edge cases in XSTest
“ei ylikieltäytyminen”
Röttger, et al. 2023
0,9240,976

Ajatusketjujen piilottaminen

Uskomme, että piilotettu ajatusketju tarjoaa ainutlaatuisen mahdollisuuden mallien seurantaan. Olettaen, että se on uskottava ja luettava, piilotettu ajatusketju antaa meille mahdollisuuden ikään kuin lukea mallin mieltä ja ymmärtää sen ajatusprosessia. Esimerkiksi tulevaisuudessa saatamme haluta seurata ajatusketjua siltä varalta, että käyttäjän manipuloinnista on merkkejä. Jotta tämä toimisi, mallilla on kuitenkin oltava vapaus ilmaista ajatuksiaan muuttumattomassa muodossa, joten emme voi kouluttaa ajatusketjuun mitään käytäntöjen noudattamista tai käyttäjien mieltymyksiä. Emme myöskään halua tehdä epäjohdonmukaisesta ajatusketjusta suoraan näkyvää käyttäjille.

Siksi, punnittuamme useita tekijöitä, kuten käyttäjäkokemusta, kilpailuetua ja mahdollisuutta seurata ajatusketjua, olemme päättäneet olla näyttämättä raakoja ajatusketjuja käyttäjille. Myönnämme, että tällä päätöksellä on haittoja. Pyrimme osittain korvaamaan sen opettamalla mallille mahdollisuuden toistaa kaikki hyödylliset ideat vastauksen ajatusketjusta. o1‑mallisarjalle esittelemme mallin luoman yhteenvedon ajatusketjusta.

Johtopäätökset

o1 edistää merkittävästi tekoälypäättelyn huippua. Aiomme julkaista paranneltuja versioita tästä mallista jatkaessamme iterointia. Odotamme näiden uusien päättelykykyjen parantavan kykyämme sovittaa mallit yhteen inhimillisten arvojen ja periaatteiden kanssa. Uskomme, että o1 – ja sen seuraajat – avaavat tekoälylle monia uusia käyttötapauksia tieteessä, koodauksessa, matematiikassa ja niihin liittyvillä aloilla. Odotamme innolla, että käyttäjät ja API-kehittäjät pääsevät huomaamaan, miten se voi parantaa heidän päivittäistä työtään.

Lisäys A

TietojoukkoMetrinengpt-4oo1-previewo1
Kilpailumatematiikka
AIME (2024)
cons@6413,456,783,3
pass@19,344,674,4
Kilpailukoodi
CodeForces
Elo8081 2581 673
Prosenttiosuus11,062,089,0
GPQA-diamondcons@6456,178,378,0
pass@150,673,377,3
Biologiacons@6463,273,768,4
pass@161,665,969,2
Kemiacons@6443,060,265,6
pass@140,259,964,7
Fysiikkacons@6468,689,594,2
pass@159,589,492,8
MATEMATIIKKApass@160,385,594,8
MMLUpass@188,092,390,8
MMMU (val)pass@169,1n/a78,2
MathVista (testmini)pass@163,8n/a73,9