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

321–330 of 1001 posts

Re: GPT-5.5

#321

Post by irthomasthomas »

deflator wrote: post #232
simonw wrote: post #195

This doesn't have API access yet, but OpenAI seem to approve of the Codex API backdoor used by OpenClaw these days... https://twitter.com/steipete/status/2046775849769148838 and https://twitter.com/romainhuet/status/2038699202834841962 And that backdoor API has GPT-5.5. So here's a pelican: https://simonwillison.net/2026/Apr/23/gpt-5-5/#and-some-peli... I used this new plugin for LLM: https://github.com/simonw/llm-op…

Hmm. Any idea why it's so much worse than the other ones you have posted lately? Even the open weight local models were much better, like the Qwen one you posted yesterday.

It beats opus-4.7 but looks like open models actually have the lead here.

Re: GPT-5.5

#322

Post by dist-epoch »

losvedir wrote: post #77

> It excels at ... researching online How does this work exactly? Is there like a "search online" tool that the harness is expected to provide? Or does the OpenAI infra do that as part of serving the response? I've been working on building my own agent, just for fun, and I conceptually get using a command line, listing files, reading them, etc, but am sort of stumped how I'm supposed to do the web search piece of it.…

It's a property of the model in the sense that it has great Google Fu.

The harness provides the search tool, but the model provides the keywords to search for, etc.

Re: GPT-5.5

#323

Post by irthomasthomas »

simonw wrote: post #300
andriy_koval wrote: post #226

Earlier quoted context omitted.

what is your setup for drawing pelican? Do you ask model to check generated image, find issues and iterate over it which would demonstrate models real abilities?

It's generally one-shot-only - whatever comes out the first time is what I go with. I've been contemplating a more fair version where each model gets 3-5 attempts and then can select which rendered image is "best".

Try llm-consortium with --judging-method rank

Re: GPT-5.5

#324

Post by camdenreslink »

sosodev wrote: post #101
an0malous wrote: post #86

Earlier quoted context omitted.

The premise of the trillion dollars in AI investments is not that it’ll be as good as it currently is but cheaper. It’s AGI or bust at this point.

Yeah, but don’t you agree that less tokens to accomplish the same goal is a sign of increasing intelligence?

It could be. Or just smarter caching (which wouldn't necessarily have to do with model intelligence). Or just overfitting on the 95% most common prompts (which could save tokens but make the models less intelligent/flexible).

Re: GPT-5.5

#325

Post by simonw »

SkyBelow wrote: post #313
simonw wrote: post #195

This doesn't have API access yet, but OpenAI seem to approve of the Codex API backdoor used by OpenClaw these days... https://twitter.com/steipete/status/2046775849769148838 and https://twitter.com/romainhuet/status/2038699202834841962 And that backdoor API has GPT-5.5. So here's a pelican: https://simonwillison.net/2026/Apr/23/gpt-5-5/#and-some-peli... I used this new plugin for LLM: https://github.com/simonw/llm-op…

Wait, I thought we were onto racoons on e-scooters to avoid (some of) the issues with Goodhart's Law coming into play.

I fall back to possums on e-scooters if the pelican looks too good to be true. These aren't good enough for me to suspect any fowl play.

Re: GPT-5.5

#326

Post by computerdork »

wholinator2 wrote: post #312
lambdas wrote: post #277

Earlier quoted context omitted.

Nothing a little digital lisdexamfetamine won’t solve

Hmmm, that's an area of study id've never considered before. Digital Psychopharmacology, Artificial Behavioral Systems Engineering. If we accept these things as minds, why not study temporary perturbations of state. We'd need to be saving a much much more complicated state than we are now though right? I wish i had time to read more papers

neat idea!

Re: GPT-5.5

#327

Post by ModernMech »

moralestapia wrote: post #99
vlovich123 wrote: post #93

Earlier quoted context omitted.

Conceivably you could have a public-facing dashboard of the rollout status to reduce confusion or even make it visible directly in the UI that the model is there but not yet available to you. The fanciest would be to include an ETA but that's presumably difficult since it's hard to guess in case the rollout has issues.

Why would you be confused? The UI tells you which model you're using at any given time.

I don't see what model I'm using on the Codex web interface, where is that listed?

Re: GPT-5.5

#328

Post by dakolli »

simonw wrote: post #195

This doesn't have API access yet, but OpenAI seem to approve of the Codex API backdoor used by OpenClaw these days... https://twitter.com/steipete/status/2046775849769148838 and https://twitter.com/romainhuet/status/2038699202834841962 And that backdoor API has GPT-5.5. So here's a pelican: https://simonwillison.net/2026/Apr/23/gpt-5-5/#and-some-peli... I used this new plugin for LLM: https://github.com/simonw/llm-op…

You know they are 1000% training these models to draw pelicans, this hasn't been a valid benchmark for 6 months +

Re: GPT-5.5

#329

Post by simianwords »

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.

Re: GPT-5.5

#330

Post by _alternator_ »

> One engineer at NVIDIA who had early access to the model went as far as to say: "Losing access to GPT‑5.5 feels like I've had a limb amputated.”

This quote is more sinister than I think was intended; it likely applies to all frontier coding models. As they get better, we quickly come to rely on them for coding. It's like playing a game on God Mode. Engineers become dependent; it's truly addictive.

This matches my own experience and unease with these tools. I don't really have the patience to write code anymore because I can one shot it with frontier models 10x faster. My role has shifted, and while it's awesome to get so much working so quickly, the fact is, when the tokens run out, I'm basically done working.

It's literally higher leverage for me to go for a walk if Claude goes down than to write code because if I come back refreshed and Claude is working an hour later then I'll make more progress than mentally wearing myself out reading a bunch of LLM generated code trying to figure out how to solve the problem manually.

Anyway, it continues to make me uneasy, is all I'm saying.

Post reply on HN