Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

developers.openai.com

Post reply on HN
Print view View original

41–50 of 174 posts

Re: OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

#41

Post by czk »

bakugo wrote: post #40
czk wrote: post #14

API page lists the knowledge cutoff as Dec 01, 2025 but when prompting the model it says June 2024. Knowledge cutoff: 2024-06 Current date: 2026-04-24 You are an AI assistant accessed via an API.

Models don't know what their cutoff dates are unless told via a system prompt. The proper way to figure out the real cutoff date is to ask the model about things that did not exist or did not happen before the date in question. A few quick tests suggest 5.5's general knowledge cutoff is still around early 2025.

i wonder if they put an older cutoff date into the prompt intentionally so that when asked on more current events it leans towards tool calls / web searches for tuning

Re: OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

#43

Post by bakugo »

WarmWash wrote: post #39
swyx wrote: post #19

Earlier quoted context omitted.

can u test it on say who won the 2024 US election

Usually the labs do some kind of post training on major events so the model isn't totally lost. A better test is something like "what is the latest version of NumPy?"

That sort of test isn't super reliable either, in my experience.

You're probably better off asking something like "what are the most notable changes in version X of NumPy?" and repeating until you find the version at which it says "I don't know" or hallucinates.

Re: OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

#45

Post by soco »

bakugo wrote: post #40
czk wrote: post #14

API page lists the knowledge cutoff as Dec 01, 2025 but when prompting the model it says June 2024. Knowledge cutoff: 2024-06 Current date: 2026-04-24 You are an AI assistant accessed via an API.

Models don't know what their cutoff dates are unless told via a system prompt. The proper way to figure out the real cutoff date is to ask the model about things that did not exist or did not happen before the date in question. A few quick tests suggest 5.5's general knowledge cutoff is still around early 2025.

Stupid question: wouldn't it then search the web for that event?

Re: OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

#46

Post by bakugo »

soco wrote: post #45
bakugo wrote: post #40

Earlier quoted context omitted.

Models don't know what their cutoff dates are unless told via a system prompt. The proper way to figure out the real cutoff date is to ask the model about things that did not exist or did not happen before the date in question. A few quick tests suggest 5.5's general knowledge cutoff is still around early 2025.

Stupid question: wouldn't it then search the web for that event?

If you have web search enabled, sure. But if you're testing on the API, you can just not enable it.

Re: OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

#47

Post by syspec »

wincy wrote: post #37

Just tried it out for a prod issue was experiencing. Claude never does this sort of thing, I had it write an update statement after doing some troubleshooting, and I said “okay let’s write this in a transaction with a rollback” and GPT-5.5 gave me the old “okay, BEGIN TRAN; -- put the query here commit; I feel like I haven’t had to prod a model to actually do what I told it to in awhile so that was a shock. I guess t…

Can't tell if above is good or bad.

Re: OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

#48

Post by XCSme »

wincy wrote: post #37

Just tried it out for a prod issue was experiencing. Claude never does this sort of thing, I had it write an update statement after doing some troubleshooting, and I said “okay let’s write this in a transaction with a rollback” and GPT-5.5 gave me the old “okay, BEGIN TRAN; -- put the query here commit; I feel like I haven’t had to prod a model to actually do what I told it to in awhile so that was a shock. I guess t…

I feel like the last 2-3 generations of models (after gpt-5.3-codex) didn't really improve much, just changed stuff around and making different tradeoffs.

Re: OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API

#50

Post by pixel_popping »

XCSme wrote: post #48
wincy wrote: post #37

Just tried it out for a prod issue was experiencing. Claude never does this sort of thing, I had it write an update statement after doing some troubleshooting, and I said “okay let’s write this in a transaction with a rollback” and GPT-5.5 gave me the old “okay, BEGIN TRAN; -- put the query here commit; I feel like I haven’t had to prod a model to actually do what I told it to in awhile so that was a shock. I guess t…

I feel like the last 2-3 generations of models (after gpt-5.3-codex) didn't really improve much, just changed stuff around and making different tradeoffs.

I disagree, it improved enormously especially at staying consistent for long-tasks, I have a task running for 32 days (400M+ tokens) via Codex and that's only since gpt-5.4
Post reply on HN