GPT-6 Astra • Hacker News Board

Re: GPT-6 Astra

#531

Post by nater5000 » Thu, Sep 03, 2026, 10:27 PM UTC

thomasahle wrote: post #476

abixb wrote: post #230

I want to take a step back: So, this is GPT-6 -- the natural number version release comparable to GPT-4 and GPT-5 from the past few years. The ARC-AGI-3 score is obviously impressive at 99.9% (we'll need to wait for more details on how they used the response API harness on GPT-6 Astra, wrt reasoning retention and compaction), but every other benchmarks seems to be a relatively modest improvement, comparable with any…

• 98.6% on ARC-AGI-3 • 97.6% on frontier math • 95.9% on CAD • 100% on ExploitBench Nothing modest about it

Except the release announcement. You know, the thing the OP you're responding to is specifically pointing out?

Re: GPT-6 Astra

#532

Post by doctoboggan » Thu, Sep 03, 2026, 10:28 PM UTC

pera wrote: post #396

intenex wrote: post #251

The ARC-AGI-3 scorecard is extremely misleading given that it clearly states itself that "with [the responses API] harness, we estimate Sol would score in the ballpark of ~30%." but it shows a score of 7.8% for GPT-5.6 Sol presumably since if they updated the percentage for GPT-5.6 Sol to the score it would receive with the responses API harness they used for GPT-6 Astra they'd have to do the same for the percentage…

To each their own. Personally I will start feeling the AGI as soon as we move from chatting about benchmark results to learn that some lab just announced the discovery of tens of novel treatments for rare diseases. Maybe I'm too boring but it seems quite pointless to have this same prediction game every time a new model is released.

Wouldn’t that be ASI? I.e. surpassing humans by outputting novel treatments at a far greater rate than normal humans?

Re: GPT-6 Astra

#533

Post by maxall4 » Thu, Sep 03, 2026, 10:29 PM UTC

The official ARC-AGI 3 score—-without OpenAI’s custom harness—-can be found here: https://arcprize.org/leaderboard. Astra scores 62.7% at max reasoning for the low-low price of 26,000 dollars.

Re: GPT-6 Astra

#534

Post by tripleee » Thu, Sep 03, 2026, 10:30 PM UTC

trixn86 wrote: post #209

Secret tip to win the mario cart clone: Just hold w, no steering needed.

you can also fly by pressing space repeatedly

Re: GPT-6 Astra

#535

Post by madhatter999 » Thu, Sep 03, 2026, 10:30 PM UTC

gavinray wrote: post #359

XCSme wrote: post #339

It's fun, but every new model release makes me even less interested to create cool stuff. Like, what's the point, if the next AI can do it in 5 seconds?

> Like, what's the point, if the next AI can do it in 5 seconds? Live a life doing whatever makes you happy. Post-work society is an inevitability if we don't destroy our planet.

I think you're assuming work's only function is getting things done. Work also is a crowd control tool.

Re: GPT-6 Astra

#536

Post by visarga » Thu, Sep 03, 2026, 10:30 PM UTC

intenex wrote: post #251

The ARC-AGI-3 scorecard is extremely misleading given that it clearly states itself that "with [the responses API] harness, we estimate Sol would score in the ballpark of ~30%." but it shows a score of 7.8% for GPT-5.6 Sol presumably since if they updated the percentage for GPT-5.6 Sol to the score it would receive with the responses API harness they used for GPT-6 Astra they'd have to do the same for the percentage…

Their definition of AGI is "when we can't invent any more tests where it fails"

Re: GPT-6 Astra

#537

Post by steve-atx-7600 » Thu, Sep 03, 2026, 10:31 PM UTC

wiseowise wrote: post #425

Hey Astra, can you fix openai website so that static website doesn't lag on M3 Pro when I scroll?

looks like it worked :)

Re: GPT-6 Astra

#538

Post by SneakyZero » Thu, Sep 03, 2026, 10:31 PM UTC

danieltk76 wrote: post #213

great, but nobody can use it for another 100 days right?

"GPT‐6 Astra is rolling out today to a limited set of organizations and over the coming days will become available to all ChatGPT Plus, Pro, Business"

Re: GPT-6 Astra

#539

Post by arkensaw » Thu, Sep 03, 2026, 10:33 PM UTC

alpineman wrote: post #387

“allowing non-technical people to create and play custom games that go beyond rudimentary elements” Proceeds to generate the most generic, rudimentary, and unoriginal clone of Mario Kart

It's worse than that, someone else generated it using and then put it on a static page. We just have to take their word for it that GPT6 can do this. It probably can. It's not really an impressive test anymore. Claude Fable can do it. Opus can do it. I've been making one-shotted games with models for a while now, to test out their capabilities, and they all pretty much come out like this - generic bland and basic, using three.js with rudimentary controls and zero gameplay other than collecting points.

Here's a one-shotted submarine game I made with Fable a few weeks back - https://roryok.com/games/deepdive3d.html. One prompt, and I think it's deeper than this (if you'll pardon the pun)

Re: GPT-6 Astra

#540

Post by keeganpoppen » Thu, Sep 03, 2026, 10:33 PM UTC

kroaton wrote: post #300

dalemhurley wrote: post #288

OpenAI is killing it now that they are more focused. Killing projects like Sora et al have seen it go from irrelevant to level footing with Anthropic. Sol is so much better than Fable 5. Then we get Astra (yet to use it) few days after Fable 5.1 (which is very impressive). Codex is slightly better than Claude Code. Good on Sam Altman getting back to basics and turning OpenAI around.

I think it mostly shows that there is no moat and the only advantage the U.S companies have over the Chinese is more compute. Qwen Max, Kimi K3, GLM 5.3 are really close to Opus/Sol/Fable/Astra and they are open weights.

[flagged]