Live data from Hacker News

GPT-5.5

openai.com

71–80 of 1001 posts

Re: GPT-5.5

#71

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…

The meshes look interesting, but the gameplay is very basic. The tank one seems more sophisticated with the flying ships and whatnot.

What's strange is that this Pietro Schirano dude seems to write incredibly cargo cult prompts.

  Game created by Pietro Schirano, CEO of MagicPath

  Prompt: Create a 3D game using three.js. It should be a UFO shooter where I control a tank and shoot down UFOs flying overhead.
  - Think step by step, take a deep breath. Repeat the question back before answering.
  - Imagine you're writing an instruction message for a junior developer who's going to go build this. Can you write something extremely clear and specific for them, including which files they should look at for the change and which ones need to be fixed?
  -Then write all the code. Make the game low-poly but beautiful.
  - Remember, you are an agent: please keep going until the user's query is completely resolved before ending your turn and yielding back to the user. Decompose the user's query into all required sub-requests and confirm that each one is completed. Do not stop after completing only part of the request. Only terminate your turn when you are sure the problem is solved. You must be prepared to answer multiple queries and only finish the call once the user has confirmed they're done.
  - You must plan extensively in accordance with the workflow steps before making subsequent function calls, and reflect extensively on the outcomes of each function call, ensuring the user's query and related sub-requests are completely resolved.

Re: GPT-5.5

#72

What is the reason behind OpenAI being able to release new models very fast? Since Feb when we got Gemini 3.1, Opus 4.6, and GPT-5.3-Codex we have seen GPT-5.4 and GPT-5.5 but only Opus 4.7 and no new Gemini model. Both of these are pretty decent improvements.

Anthropic is really tiny, and Google is just being Google, their models are just to show that they're hip with what the kids are doing.

Re: GPT-5.5

#73
post #55

Earlier quoted context omitted.

For less than 10% bump across the benchmarks? Probably not, but if your employer is paying (which is probably what OAI is counting on) it's all good. It's kind of starting to make sense that they doubled the usage on Pro plans - if the usage drains twice as fast on 5.5 after that promo is over a lot of people on the $100 plan might have to upgrade.

You are paying per token, but what you care about is token efficiency. If token efficiency has improved by as much as they claim it did (i.e. you need less tokens to complete a task successfully) all seems well.

If it uses half the tokens to complete a task, then doubling the cost is perfectly fine. But is that actually true?

Re: GPT-5.5

#74
post #30

For a 56.7 score on the Artificial Intelligence Index, GPT 5.5 used 22m output tokens. For a score of 57, Opus 4.7 used 111m output tokens. The efficiency gap is enormous. Maybe it's the difference between GB200 NVL72 and an Amazon Tranium chip?

why would chip affect token quantity. this is all models.

Chip costs strongly impact the economics of model serving.

It is entirely plausible to me that Opus 4.7 is designed to consume more tokens in order to artificially reduce the API cost/token, thereby obscuring the true operating cost of the model.

I agree though, I chose poor phrasing originally. Better to say that GB200 vs Tranium could contribute to the efficiency differential.

Re: GPT-5.5

#76
post #55

Earlier quoted context omitted.

For less than 10% bump across the benchmarks? Probably not, but if your employer is paying (which is probably what OAI is counting on) it's all good. It's kind of starting to make sense that they doubled the usage on Pro plans - if the usage drains twice as fast on 5.5 after that promo is over a lot of people on the $100 plan might have to upgrade.

You are paying per token, but what you care about is token efficiency. If token efficiency has improved by as much as they claim it did (i.e. you need less tokens to complete a task successfully) all seems well.

Not for coding because it actually needs to read and write large files

Re: GPT-5.5

#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.

Given that they're calling out that this model is great at online research - to what extent is that a property of the model itself? I would have thought that was a harness concern.

Re: GPT-5.5

#80
Two hundred pages of shilling and it’s a 1% improvement in the benchmarks. They’re dead in the water.

Imagine spending 100m on some of these AI “geniuses” and this is the best they can do.

Post reply on HN