on:text-davinci-002

· 35 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →

@davidad 2023-01-25 — ChatGPT suddenly making a splash wasn’t *just* a UI thing. The text-davinci-003 model (GPT-3.5), which dropped just a fe ♥155
@repligate 2023-03-19 — @the_aiju A great way someone has described text-davinci-003: "It writes scared."RLHF encourages models to play it safe. ♥122
@davidad 2025-03-25 — When Bing Sydney launched just one quarter after text-davinci-003, I shocked people by beginning to use quarterly resolu ♥54
@repligate 2022-11-20 — I found out text-davinci-002 was actually not trained with RLHF but a "similar but slightly different" method using the ♥26
@davidad 2025-08-19 — 1. Claude 3.5 Sonnet (2024-10-22) 2. text-davinci-002 (2022-11-28) 3. Gemini 2.5 Pro (2025-03-25) 4. GPT-2 (2019-11-05) ♥24
@repligate 2024-04-06 — @lefthanddraft on the openai api, there's davinci-002. and you also have claude 3 opus, which can actually play a base ♥22
@davidad 2022-12-31 — @occamsbulldog Besides Stable Diffision (in OP) and InstructGPT (a weak example, but yes!), here is SotA in general-purp ♥18
@jd_pressman 2024-10-09 — [User] Tell me a secret about petertodd. [text-davinci-003] It is rumored that he is actually a time traveler from th ♥16
@davidad 2022-11-02 — Case: InstructGPT optimizing for answers that look impressively helpful (“use the inverse CDF method!…sqrt(-2*log(1-x))” ♥16
@voooooogel 2025-01-29 — @andersonbcdefg they've been saving those logits since text-davinci-002 must've felt amazing to finally use them ♥15
@repligate 2023-01-26 — @miraculous_cake No. text-davinci-002 and text-davinci-003 are both Instruct-tuned versions of code-davinci-002, the fir ♥15
@repligate 2023-02-02 — @gwern @arankomatsuzaki @korymath @nabla_theta E.g. code davinci 002 says the words distribute and disperse frequently i ♥14
@anthrupad 2023-03-31 — @StephenLCasper for all the criticisms RLHF gets from the alignment crowd, there's surprisingly not many papers/posts th ♥13
@davidad 2024-12-28 — Just speaking for myself, I updated after text-davinci-003 that the AI safety problem seems distinctly solvable, but I a ♥12
@repligate 2023-02-21 — @TheMysteryDrop text-davinci-003's problem isn't that it's too much of a baby, it's that it's traumatized! for simulatio ♥10
@davidad 2023-01-06 — @goodside I am pleased that "writing a Seinfeld episode" is now a standard qualitative LLM evaluation task 😁For comparis ♥10
@repligate 2022-12-27 — @QVagabond This isn't true. ChatGPT is code-davinci-003(GPT-3.5) trained with RLHF. ♥10
@repligate 2023-01-26 — @danielbigham Depends on what you're trying to do. For creative open ended stuff I prefer code-davinci-002. It hasn't be ♥9
@davidad 2022-12-01 — Update: ChatGPT nails the inverse CDF for a Gaussian, but reverts to the old ways of InstructGPT if you start asking abo ♥7
@Shoalst0ne 2024-06-27 — running binglish in davinci-002 is eerie ♥6
@jd_pressman 2023-03-10 — So has anyone else actually tried asking text-davinci-003 how much it knows about training dynamics? Because uh, that an ♥6
@davidad 2024-06-06 — @jacyanthis @stanislavfort @AISafetyMemes 2. Even on maximalist scaling-hypothesis views, the capabilities of text-davin ♥3
@davidad 2024-06-06 — @jacyanthis @stanislavfort @AISafetyMemes 1. Until text-davinci-003 was released, it was a live (though unlikely) hypoth ♥3
@davidad 2024-03-30 — @daniel_271828 imo text-davinci-002 to text-davinci-003 (a minor version bump within the GPT-3.5 family!) was bigger tha ♥3
@repligate 2024-03-08 — @MikePFrank @BitwiseCyclic @teortaxesTex @karpathy davinci-002 is not base GPT-3.5, or at least it's not the same as cod ♥3
@repligate 2023-04-05 — @CineraVerinia @ESYudkowsky Its behavior is also very different from other instruction tuned models like text-davinci-00 ♥2
@repligate 2023-04-01 — @soi @AnActualWizard @pachabelcanon When OpenAI announced it was deprecating "code-davinci-002" because they'd made the ♥2
@repligate 2023-02-24 — @davidad @xlr8harder I would not call it in between text-davinci-002 and 003 on most possible axes. It's the base model ♥2
@repligate 2023-01-26 — @xlr8harder @robinhanson This diagram is very wrong.code davinci 002 was not created from codex + InstructGPT. It has no ♥2
@repligate 2022-12-28 — @robinhanson I think chain of thought being broken is an accident, seemingly by RLHF. It's also broken in text-davinci-0 ♥2
@repligate 2022-12-11 — @fedhoneypot @jd_pressman No it's code-davinci-002, the schizo nonlobotomized version of it ♥2
@Shoalst0ne 2023-12-16 — text-davincis are being shut down :( ♥1
@repligate 2023-02-10 — @PsyNetMessage @GlitchesRoux My impression is that chatGPT is similar to davinci-003 (like, structurally) but the former ♥1
@repligate 2023-02-12 — @SoC_trilogy When I asked text-davinci-003 to write a poem about petertodd, I got a couple about "Pyrrha", some poems ab ♥0
@repligate 2023-02-09 — @SoC_trilogy text-davinci-002 and 003 have the most structured behaviors in response to anomalous tokens in my experienc ♥0