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

281–290 of 1001 posts

Re: GPT-5.5

#281

Post by threecheese »

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.

Anecdotally, I get the same wall time with my Max x5 (100$) and my ChatGPT Teams (30$) subscriptions.

Re: GPT-5.5

#282

Post by jswny »

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…

Codex is fully open source…

Re: GPT-5.5

#283

Post by Gander5739 »

seanw444 wrote: post #272
postalcoder wrote: post #234

Earlier quoted context omitted.

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.

Can someone explain how we arrived at the pelican test? Was there some actual theory behind why it's difficult to produce? Or did someone just think it up, discover it was consistently difficult, and now we just all know it's a good test?

https://simonwillison.net/2025/Jun/6/six-months-in-llms/

Re: GPT-5.5

#284

Post by mitjam »

kingstnap wrote: post #172
puppystench wrote: post #145

Earlier quoted context omitted.

For API usage, GPT-5.5 is 2x the price of GPT-5.4, ~4x the price of GPT-5.1, and ~10x the price of Kimi-2.6. Unfortunately I think the lesson they took from Anthropic is that devs get really reliant and even addicted on coding agents, and they'll happily pay any amount for even small benefits.

I feel like devs generally spend someone else's money on tokens. Either their employers or OpenAIs when they use a codex subscription. If I put on my schizo hat. Something they might be doing is increasing the losses on their monthly codex subscriptions, to show that the API has a higher margin than before (the codex account massively in the negative, but the API account now having huge margins). I've never seen an O…

The difference between sub and api price makes it hard to create competitive solutions on the app level.

Re: GPT-5.5

#285

Post by rane »

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.

This might be the opposite of staying nimble as my workflows are quite tied to Claude Code specifically, however I've been experimenting with using OpenAI models in CC and it works surprisingly well.

Re: GPT-5.5

#286

Post by coffeemug »

robwwilliams wrote: post #167
jorl17 wrote: post #23

Earlier quoted context omitted.

GPT 5.4 is already better than Opus 4.7 to me. But, then again, Opus 4.7 is a massive disappointment. I hope they don't discontinue 4.6.

Depends in goals. For long free-firm discussions I find Opus 4.7 Adaptive better/deeper than Opus 4.6 Extended. But usual caveats apply: first week of use and token budget seems generous now on Max 5X.

I had the opposite experience. Opus 4.6 extended feels like the first genuinely intelligent model to converse with, Opus 4.7 adaptive feels like slightly smarter LinkedIn slop.

Re: GPT-5.5

#287

Post by dataviz1000 »

astlouis44 wrote: post #9

A playable 3D dungeon arena prototype built with Codex and GPT models. Codex handled the game architecture, TypeScript/Three.js implementation, combat systems, enemy encounters, HUD feedback, and GPT‑generated environment textures. Character models, character textures, and animations were created with third-party asset-generation tools The game that this prompt generated looks pretty decent visually. A big part of th…

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 currently.

I should release my Rubiks Cube MCP server with the challenge to see if someone can write a prompt to solve a Rubik's Cube.

Re: GPT-5.5

#288

Post by redox99 »

seanw444 wrote: post #272
postalcoder wrote: post #234

Earlier quoted context omitted.

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.

Can someone explain how we arrived at the pelican test? Was there some actual theory behind why it's difficult to produce? Or did someone just think it up, discover it was consistently difficult, and now we just all know it's a good test?

It all began with a Microsoft researcher showing a unicorn drawn in tikz using GPT4. It was an example of something so outrageous that there was no way it existed in the training data. And that's back when models were not multimodal.

Nowadays I think it's pretty silly, because there's surely SVG drawing training data and some effort from the researchers put onto this task. It's not a showcase of emergent properties.

Re: GPT-5.5

#289

Post by narcindin »

mikepurvis wrote: post #275
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…

Reminds me a lot of the Lena short story, about uploaded brains being used for "virtual image workloading": > MMAcevedo's demeanour and attitude contrast starkly with those of nearly all other uploads taken of modern adult humans, most of which boot into a state of disorientation which is quickly replaced by terror and extreme panic. Standard procedures for securing the upload's cooperation such as red-washing, blue-…

Crazy, I could have sworn this story was from a passage in 3 Body Problem (book 2).

Memory is quite the mysterious thing.

Re: GPT-5.5

#290

Post by winrid »

dandaka wrote: post #192
vthallam wrote: post #142

This model is great at long horizon tasks, and Codex now has heartbeats, so it can keep checking on things. Give it your hardest problem that would take hours with verifiable constraints, you will see how good this is:) *I work at OAI.

Could be a great feature, can't wait to test! Tired of other models (looking at you Opus) constantly stuck mid-task lately.

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.

Post reply on HN