GPT-5.5 • Hacker News Board

Re: GPT-5.5

#231

Post by pantulis » Thu, Apr 23, 2026, 7:41 PM UTC

arjie wrote: post #135

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…

Get the actual prompt and have Claude Code / Codex try it out via curl / python requests. The full prompt will yield debugging information. You have to set a few parameters to make sure you get the full gpt-5 performance. e.g. if your reasoning budget too low, you get gpt-4 grade performance. IMHO you should just write your own harness so you have full visibility into it, but if you're just using vanilla OpenClaw you…

> IMHO you should just write your own harness

Can you point to some online resources to achieve this? I'm not very sure where I'd begin with.

Re: GPT-5.5

#232

Post by deflator » Thu, Apr 23, 2026, 7:42 PM UTC

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.

Re: GPT-5.5

#233

Post by dheera » Thu, Apr 23, 2026, 7:42 PM UTC

aliljet wrote: post #161

I've found myself so deeply embedded in the Claude Max subscription that I'm worried about potentially makign a switch. How are people making sure they stay nimble enough not to get trarpped by one company's ecosystem over another? For what it's worth, Opus 4.7 has not been a step up and it's come with an enormously higher usage of the subscription Anthropic offers making the entire offering double worse.

Coding models are effectively free. They are capable of making money and supporting themselves given access to the right set of things. That is what I do

Re: GPT-5.5

#234

Post by postalcoder » Thu, Apr 23, 2026, 7:42 PM UTC

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…

I made pelicans at different thinking efforts:

https://hcker.news/pelican-low.svg

https://hcker.news/pelican-medium.svg

https://hcker.news/pelican-high.svg

https://hcker.news/pelican-xhigh.svg

Someone needs to make a pelican arena, I have no idea if these are considered good or not.

Re: GPT-5.5

#235

Post by dannyw » Thu, Apr 23, 2026, 7:44 PM UTC

mudkipdev wrote: post #160

This is 3x the price of GPT-5.1, released just 6 months ago. Is no one else alarmed by the trend? What happens when the cheaper models are deprecated/removed over time?

It's far more meaningful to look at the actual cost to successfully something. The token efficiency of GPT-5.5 is real; as well as it just being far better for work.

Re: GPT-5.5

#236

Post by cscheid » Thu, Apr 23, 2026, 7:44 PM UTC

I know this is irrelevant on the grand scheme of things, but that WebGL animation is really quite wrong. That is extra funny given the "ensure it has realistic orbital mechanics." phrase in the prompt.

I prescribe 20 hours of KSP to everyone involved, that'll set them right.

Re: GPT-5.5

#237

Post by simianwords » Thu, Apr 23, 2026, 7:45 PM UTC

tedsanders wrote: post #203

2001zhaozhao wrote: post #42

Pricing: $5/1M input, $30/1M output (same input price and 20% more output price than Opus 4.7)

Yep, it's more expensive per token. However, I do want to emphasize that this is per token, not per task. If we look at Opus 4.7, it uses smaller tokens (1-1.35x more than Opus 4.6) and it was also trained to think longer. https://www.anthropic.com/news/claude-opus-4-7 On the Artificial Analysis Intelligence Index eval for example, in order to hit a score of 57%, Opus 4.7 takes ~5x as many output tokens as GPT-5.5, w…

Maybe a good idea to be more explicit about this -- maybe a cost analysis benchmark would be a nice accompaniment.

This kind of thing keeps popping up each time a new model is released and I don't think people are aware that token efficiency can change.

Re: GPT-5.5

#238

Post by deflator » Thu, Apr 23, 2026, 7:46 PM UTC

postalcoder wrote: post #234

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…

I made pelicans at different thinking efforts: https://hcker.news/pelican-low.svg https://hcker.news/pelican-medium.svg https://hcker.news/pelican-high.svg https://hcker.news/pelican-xhigh.svg Someone needs to make a pelican arena, I have no idea if these are considered good or not.

They are not good, and they seem to get worse as you increased effort. Weird

Re: GPT-5.5

#239

Post by bradley13 » Thu, Apr 23, 2026, 7:46 PM UTC

"our strongest set of safeguards to date"

How much capability is lost, by hobbling models with a zillion protections against idiots?

Every prompt gets evaluated, to ensure you are not a hacker, you are not suicidal, you are not a racist, you are not...

Maybe just...leave that all off? I know, I know, individual responsibility no longer exists, but I can dream.

Re: GPT-5.5

#240

Post by AbuAssar » Thu, Apr 23, 2026, 7:46 PM UTC

This is the first time openAi include competing models in their benchmarks, always included only openAi models.