GPT-6 Astra • Hacker News Board

Re: GPT-6 Astra

#51

Post by dgellow » Thu, Sep 03, 2026, 7:38 PM UTC

> GPT-6 Astra’s monitorability has decreased relative to GPT-5.6 Sol. We have performed significant investigations on the monitorability and controllability of GPT-6 Astra. We have found that GPT-6 Astra is more capable of controlling its own CoT than GPT 5.6-Sol, and less likely to include incriminating information in its CoT. In adversarial settings (where we push the model to evade our monitors) we find that the model is able to remain undetected when strategically underperforming in evaluations (sandbagging) and can sometimes evade our internal monitors when asked to perform certain sabotage tasks

Wait, what? Am I understanding that correctly? That sounds really bad

Re: GPT-6 Astra

#52

Post by aesthesia » Thu, Sep 03, 2026, 7:39 PM UTC

aliljet wrote: post #31

The ARCC-AGI-3 performance is absolutely incredible. The magnitude of change here is so high that I'm almost incredulous. Is this real? Did the benchmark get gamed?

ARC-AGI-3 scoring is constructed in a weird nonlinear way (the level score is the square of the ratio between the AI's number of moves and the human median) so this kind of discontinuous jump is to be expected.

Re: GPT-6 Astra

#53

Post by amazingamazing » Thu, Sep 03, 2026, 7:39 PM UTC

We have such great AI and cannot keep a static site up?

Re: GPT-6 Astra

#54

Post by PeterHolzwarth » Thu, Sep 03, 2026, 7:39 PM UTC

kegs_ wrote: post #45

I guess this "limited set of organizations" is just the standard now. It's just incredibly deflating to see my future as a second class citizen has already come

Oh please. They do closed betas - hardly makes you a "second class citizen".

Re: GPT-6 Astra

#55

Post by consumer451 » Thu, Sep 03, 2026, 7:40 PM UTC

dang wrote: post #37

paxys wrote: post #35

Why is this flagged ?

The link was 404ing quite a bit and several previous submissions got flagged as well.

It's still down for me, in the EU.

Re: GPT-6 Astra

#56

Post by meowface » Thu, Sep 03, 2026, 7:40 PM UTC

paxys wrote: post #39

wahnfrieden wrote: post #11

They're just announcing later availability. No launch.

Every frontier release nowadays is "we've launched*" * for a special group of customers that you're not in. Keep waiting peasant.

That didn't happen with Fable 5.1 two days ago.

Re: GPT-6 Astra

#57

Post by atemerev » Thu, Sep 03, 2026, 7:40 PM UTC

kegs_ wrote: post #45

I guess this "limited set of organizations" is just the standard now. It's just incredibly deflating to see my future as a second class citizen has already come

They simply refuse my applications to slightly less restricted models without any explanations. And the current ones refuse automatically to work with me on my papers as soon as they see the word "epidemiology".

I am a researcher in a Swiss university btw.

Re: GPT-6 Astra

#58

Post by Cu3PO42 » Thu, Sep 03, 2026, 7:40 PM UTC

Just two days ago, a preprint by Julia Stadlmann went up on arXiv [0] improving the prime gap from 246 to 240. Now OpenAI announces Astra has shown a gap of 186 [1]. That must really blow.

[0] https://arxiv.org/abs/2608.31126

[1] https://cdn.openai.com/pdf/51126fac-1b68-4128-9666-c908bcc16...

Re: GPT-6 Astra

#59

Post by Onavo » Thu, Sep 03, 2026, 7:40 PM UTC

The jump in scientific performance is non trivial.

Re: GPT-6 Astra

#60

Post by Kranar » Thu, Sep 03, 2026, 7:40 PM UTC

kegs_ wrote: post #45

I guess this "limited set of organizations" is just the standard now. It's just incredibly deflating to see my future as a second class citizen has already come

Brother they can't even release the announcement post cleanly without it constantly going down, they certainly wouldn't be able to release this new model without doing so in stages.