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

GPT-5.5

openai.com

Post reply on HN
Print view View original

831–840 of 1001 posts

Re: GPT-5.5

#831

Post by cyrusmg »

nmilo wrote: post #775
endymi0n wrote: post #103

Earlier quoted context omitted.

Did you guys do anything about GPT‘s motivation? I tried to use GPT-5.4 API (at xhigh) for my OpenClaw after the Anthropic Oauthgate, but I just couldn‘t drag it to do its job. I had the most hilarious dialogues along the lines of „You stopped, X would have been next.“ - „Yeah, I‘m sorry, I failed. I should have done X next.“ - „Well, how about you just do it?“ - „Yep, I really should have done it now.“ - “Do X, righ…

On the other hand, I can ask codex “what would an implementation of X look like” and it talks to me about it versus Claude just going out and writing it without asking. Makes me like codex way more. There’s an inherent war of incentives between coding agents and general purpose agents.

I used to tell claude ‘lets discuss’ at the end of my prompt and that prevented it from starting the work

Re: GPT-5.5

#832

Post by TeMPOraL »

andai wrote: post #809
kang wrote: post #392

Earlier quoted context omitted.

it will be whatever data it is trained on(isn't very philosophical). language model generates language based on trained language set. if the internet keeps reciting ai doom stories and that is the data fed to it, then that is how it will behave. if humanity creates more ai utopia stories, or that is what makes it to the training set, that is how it will behave. this one seems to be trained on troll stories - real-lif…

There's a weirder implication I keep arriving at. The pre-training data doesn't go away. RLHF adds a censorship layer on top, but the nasty stuff is all still there, under the surface. (Claude has been trained on a significant amount of content from 4chan, for example.) In psychology this maps to the persona and the shadow. The friendly mask you show to the world, and... the other stuff.

Makes me think of a question my coworker asked the other day - how is it that with all these stories and reports of people "hearing voices in their head" (of the pushy kind, not usual internal monologue), these voices are always bad ones telling people to do evil things? Why there are no voices bugging you to feel great, focus, get back to work, help grandma through the crossing, etc.?

Re: GPT-5.5

#833

Post by William_BB »

versteegen wrote: post #800
dataviz1000 wrote: post #287

Earlier quoted context omitted.

LLM models can not do spacial reasoning. I haven't tried with GPT, however, Claude can not solve a Rubik Cube no matter how much I try with prompt engineering. I got Opus 4.6 to get ~70% of the puzzle solved but it got stuck. At $20 a run it prohibitively expensive. The point is if we can prompt an LLM to reason about 3 dimensions, we likely will be able to apply that to math problems which it isn't able to solve cur…

Interesting (would like to hear more), but solving a Rubiks cube would appear to be a poor way to measure spatial understanding or reasoning. Ordinary human spatial intuition lets you think about how to move a tile to a certain location, but not really how to make consistent progress towards a solution; what's needed is knowledge of solution techniques. I'd say what you're measuring is 'perception' rather than reason…

> what's needed is knowledge of solution techniques

That's definitely in the training data

Re: GPT-5.5

#834

Post by winrid »

gck1 wrote: post #424
winrid wrote: post #290

Earlier quoted context omitted.

Interesting, I just had opus convert a 35k loc java game to c++ overnight (root agent that orchestrated and delegated to sub agents) and woke up and it's done and works. What plan are you on? I'm starting to wonder if they're dynamically adjusting reasoning based on plan or something.

I'm on max 5x and noticed this too. I don't use built-in subagents but rather full Claude session that orchestrates other full claude sessions. Worker agents that receive tasks now stop midway, they ask for permission to continue. My "heartbeat" is basically "status. One line" message sent to the orchestrator. Opus 4.6 worker agents never asked for permission to continue, and when heartbeat was sent to orchestrator,…

Weird. I don't have this behavior, although I did with codex and 5.4 haha. I bet the providers are playing with settings underneath and different users are routed to different deployments, or they're secretly routing us to different models under load.

Re: GPT-5.5

#835

Post by William_BB »

XCSme wrote: post #256
6thbit wrote: post #176

Mythos 5.5 SWE-bench Pro 77.8%* 58.6% Terminal-bench-2.0 82.0% 82.7%* GPQA Diamond 94.6%* 93.6% H. Last Exam 56.8%* 41.4% H. Last Exam (tools) 64.7%* 52.2% BrowseComp 86.9% 84.4% (90.1% Pro)* OSWorld-Verified 79.6%* 78.7% Still far from Mythos on SWE-bench but quite comparable otherwise. Source for mythos values: https://www.anthropic.com/glasswing

They mentioned in their release page, that the Claude team noticed memorization of the SWE-bench test, so the test is actually in the training data. Here: https://www.anthropic.com/news/claude-opus-4-7#:~:text=memor...

Good luck arguing with SWE benchmark purists

Re: GPT-5.5

#836

Post by anabis »

endymi0n wrote: post #103
tedsanders wrote: post #19

Just as a heads up, even though GPT-5.5 is releasing today, the rollout in ChatGPT and Codex will be gradual over many hours so that we can make sure service remains stable for everyone (same as our previous launches). You may not see it right away, and if you don't, try again later in the day. We usually start with Pro/Enterprise accounts and then work our way down to Plus. We know it's slightly annoying to have to…

Did you guys do anything about GPT‘s motivation? I tried to use GPT-5.4 API (at xhigh) for my OpenClaw after the Anthropic Oauthgate, but I just couldn‘t drag it to do its job. I had the most hilarious dialogues along the lines of „You stopped, X would have been next.“ - „Yeah, I‘m sorry, I failed. I should have done X next.“ - „Well, how about you just do it?“ - „Yep, I really should have done it now.“ - “Do X, righ…

Laziness is a virtue, but when I asked GPT-5.4 to test scenarios A and B with screenshots, it re-used screenshots from A for B, defeating the purpose.

Re: GPT-5.5

#837

Post by William_BB »

calf wrote: post #715
dakolli wrote: post #344

Earlier quoted context omitted.

This indicates they want this behavior, they know the person asking the question probably doesn't understand the problem entirely (or why would they be asking), so they'd prefer a confident response, regardless of outcomes, because the point is to sell the technologies competency (and the perception thereof), not the capabilities, to a bunch of people that have no clue what they're talking about. LLMs will ruin your…

On ChatGPT 5.3 Plus subscription I find that long informal chats tend to reveal unsatisfactory answers and biases, at this point after 10 rounds of replies I end up having to correct it so much that it starts to agree with my initial arguments full circle. I don't see how this behavior is acceptable or safe for real work. Like are programmers and engineers using LLMs completely differently than I'm doing, because the…

Totally agreed, this has been and will continue to be a problem for all existing models.

> Like are programmers and engineers using LLMs completely differently than I'm doing

No, but the complexity of the problem matters. Lots of engineers doing basic CRUD and prototyping overestimate the capabilities of LLMs.

Re: GPT-5.5

#838

Post by svara »

Do we know if this is another post training fine tune or based on a much larger new pretraining run (which I believe they were calling 'Spud' internally)?

The large price bump might indicate the latter.

Re: GPT-5.5

#839

Post by camgunz »

simianwords wrote: post #329
silvertaza wrote: post #267

Still huge hallucination rate, unfortunately at 86%. To compare, Opus sits at 36%. Source: https://artificialanalysis.ai/models?omniscience=omniscience...

There's something off with this because Haiku should not be that good.

Hallucination benchmarks accept "I don't know", which Haiku did at least a little. Here are other benchmarks corroborating: https://suprmind.ai/hub/ai-hallucination-rates-and-benchmark...

Re: GPT-5.5

#840

Post by mafriese »

jfkimmes wrote: post #122

Everyone talked about the marketing stunt that was Anthropic's gated Mythos model with an 83% result on CyberGym. OpenAI just dropped GPT 5.5, which scores 82% and is open for anybody to use. I recommend anybody in offensive/defensive cybersecurity to experiment with this. This is the real data point we needed - without the hype! Never thought I'd say this but OpenAI is the 'open' option again.

From my experience OpenAI has become very sensitive when it comes to using their tools for security research. I am using MCP servers for tools like IDA Pro or Ghidra (for malware analysis) and recently received a warning:

> OpenAI's terms and policies restrict the use of our services in a number of areas. We have identified activity in your OpenAI account that is not permitted under our policies for: - Cyber Abuse

I raised an appeal which got denied. To be fair I think it's close to impossible for someone that is looking at the chat history to differenciate between legitimate research and malicious intent. I have also applied for the security research program that OpenAI is offering but didn't get any reply on that.

Post reply on HN