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 jumploops »

isoprophlex wrote: post #66

> 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…

The CoT change is due to a new technique called recurrent depth, which essentially moves some reasoning to hidden states, allowing the "output" (or traditional CoT) to be more controlled by the model.

Some are calling it "neuralese" as reported by The Information[0][1], but I'm not seeing any sources from OpenAI beyond this tweet[2] attempting to quell the fear-mongering.

[0]https://www.theinformation.com/articles/secret-technique-beh...

[1]https://x.com/MTSlive/status/2095227056040919202

[2]https://x.com/merettm/status/2095023204993490967

Re: GPT-6 Astra

#152

Post by _superposition_ »

karmasimida wrote: post #124
x312 wrote: post #98

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.

I must be on the wrong X/Twitter then.

Re: GPT-6 Astra

#153

Post by rektomatic »

petilon wrote: post #135

This is wild: OpenAI is basically declaring that AGI is here. https://www.theverge.com/ai-artificial-intelligence/989601/o... “If we fast-forward a couple of years, and we look back and say, ‘When was it, really, that AGI was created?’ I think it’s going to be about this time, and I think it might be about this model,” OpenAI president Greg Brockman said during a Thursday press briefing. Later in the call, he added,…

Remember when the term "AGI" meant something? Pepperidge farm remembers

Re: GPT-6 Astra

#154

Post by pluc »

petilon wrote: post #135

This is wild: OpenAI is basically declaring that AGI is here. https://www.theverge.com/ai-artificial-intelligence/989601/o... “If we fast-forward a couple of years, and we look back and say, ‘When was it, really, that AGI was created?’ I think it’s going to be about this time, and I think it might be about this model,” OpenAI president Greg Brockman said during a Thursday press briefing. Later in the call, he added,…

Find me someone who isn't paid by OpenAI who is saying the same

Re: GPT-6 Astra

#156

Post by arm32 »

_superposition_ wrote: post #125
isoprophlex wrote: post #66

> 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.

They’re intermediate tokens, so I wish we called it what it is… ITG. The anthropomorphizing is out of control.

Re: GPT-6 Astra

#157

Post by ActionHank »

opus5_hater wrote: post #33
tristanj wrote: post #13

GPT 6 Astra benchmarks https://cdn.thenewstack.io/media/2026/09/358eb84a-screenshot... Performance is significantly higher than Fable 5.1 Source: https://thenewstack.io/openai-gpt6-astra-benchmarks/

any benchmark where opus 5 achieves higher scores than fable 5 in any way is not a benchmark worth trusting.

username checks out
Post reply on HN