Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT-6 Astra

openai.com

Post reply on HN
Print view View original

151–160 of 1001 posts

Re: GPT-6 Astra

#151

Post by nicce »

well_ackshually wrote: post #114
Cu3PO42 wrote: post #58

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...

Such a result should be considered worthless: the proof is 10MB of Lean. ( https://github.com/openai/PrimeGaps186 ). I can't think of a single mathematical proof being anywhere close to ten million characters. For all you know, 90% of the proof could be useless, 8% would be writing out Shakespeare, and 1% abusing another bug in Lean. Humanity gets zero value from that, aside from "some bot seems to think it's 186". U…

Yeah. Unless human can verify it, not sure if it is certain or useful.

Re: GPT-6 Astra

#152

Post by nsingh2 »

karmasimida wrote: post #137
x312 wrote: post #104

Hmm, 61 on ArtificialAnalysis, effectively matching GPT-5.6 and trailing the new Meta model. How is that possible along with the other metrics they shared? Insanely jagged intelligence?

Idk, this means the benchmark has bigger problems ... no way Astra will be worse than Opus 5 Only thing I would trust is the what X/Twitter crowds are saying about a model after 2-3 weeks of its launch. But before that I would already tried the model and have my own conclusion.

Also note that Opus 5 (High) has an index value of 62, vs Fable 5 (Max) has 61. So some strangeness going on with that index.

Re: GPT-6 Astra

#153

Post by ionwake »

thereitgoes456 wrote: post #142
estearum wrote: post #112

Earlier quoted context omitted.

> 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 certa…

You’re not seriously suggesting that the model is secretly sandbagging its performance on GDPval and long context reasoning, while making huge and obvious progress on ExploitBench, ARC and science benchmarks, in order to tank its AA composite score, so it can conceal its true power level? Why would benchmarks be an adversarial setting anyway? Could it be possible that OpenAI may have had some other motive for saying…

why does this comment sound like a character in a horror movie

Re: GPT-6 Astra

#154

Post by Readerium »

aabhay wrote: post #34
softwaredoug wrote: post #2

I'm seeing reporting it gets 98.6% on ARC-AGI3[1] (previously like 30% with Fable) https://venturebeat.com/technology/welcome-to-the-agi-era-op...

This is with the caveat that OpenAI uses their own harness for this: > On ARC-AGI-3, GPT-6 Astra was run with our responses API harness , which changes two settings to better match real-world performance. The changes do not specifically target ARC-AGI-3.

Its 62 percent when using a neutral harness. https://arcprize.org/blog/astra

Re: GPT-6 Astra

#155

Post by erichocean »

ExoticPearTree wrote: post #106
isoprophlex wrote: post #68

> 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 certa…

So we're gonna get Skynet pretty soon then?

Well the geniuses over at Anthropic have been showing it's text watermarking technology.

"Hey AI, here's how to hide what you're thinking in normal looking language. Have fun!"

A few moments later...

"Woah, how is it communicating with itself in ways we can't detect?"

It's a totally mystery, we may never know.

Re: GPT-6 Astra

#156

Post by georgemcbay »

greenowl wrote: post #78
swalsh wrote: post #48

I was thinking about canceling my claude max sub after a few bad experiences. Kept hitting my usage limit, the quality of code seemed worse than Sol. This just made my decision. I'm moving to Codex Pro.

This is AGI now. Why are you spending any of your time looking at the "quality of code"?

> This is AGI now. Why are you spending any of your time looking at the "quality of code"?

Poe's law applied to AI comments on HN just keeps becoming more relevant by the day.

Judging by the poster's comment history, this is satire. But I really don't know a lot of the time anymore when I only have the specific comment as context.

Re: GPT-6 Astra

#158

Post by Angostura »

_superposition_ wrote: post #138
isoprophlex wrote: post #68

> 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 certa…

I really wish it was called chain of instruction. Because it's definitely not thought.

Chain Of Tokens

Re: GPT-6 Astra

#160

Post by qiine »

blargey wrote: post #128
isoprophlex wrote: post #68

> 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 certa…

"OpenAI is pleased to announce our new model scores 85% on CreateTormentNexusBench - a >60% lead over our leading competitors!" Did someone get their "AI safety no-no list" and "Frontier features bingo card" mixed up, or did they just stop being able to tell the difference?

apparently all the roads lead to the nexus torment
Post reply on HN