Viewing profile — andy12_

The automated AI pipeline also had an automatic grading model to try to reduce false positives. But anyway, my point was that in that case the prompt involved was indeed pretty muc…

> but it is worth noting that this wasn't a matter of "ChatGPT, solve this unsolved problem. Make no mistakes." It wasn't the case for this, but when OpenAI disproved the Unit Dist…

When Google Maps routes me using a smaller secondary road instead of the main road that I would otherwise have used , I've always wondered whether that significantly changes the am…

> Even interns can understand ambiguous asks with a bit of help This is not a case of an ambiguous task. This is literally trying to judge a model based on information it cannot po…

It's pretty much confirmed by OpenAI here [1]. > We generally treat GPT-5.5’s safety results as strong proxies for GPT-5.5 Pro, which is the same underlying model using a setting t…

No, GPTCyber is specifically trained for cybersecurity, and GPT-5.5-pro is just an ensemble of many subagents, not an actual model. Mythos is simply a much bigger model in terms of…

I think what's unexpected is that it seems that some cases of model errors are truly caused by the model being misaligned? In the "Catching a model fabricating data" example I woul…

I think it makes more sense to make it so that major versions are different pretraining runs, and minor versions are simply the same pretraining run that was finetuned to different…

I mean it as in, train a model across different clusters instead of a centralized cluster. It's been shown that it's possible to train 10B models this way. If more research effort …

To be fair. There is a security concern angle: even open-source models could be trained as sleeper agents that act adversarially (for example, adding backdoors) when used in specif…

I'm from Spain and I also hate these projects with passion. Creating models that speak multiple languages is a solved problem. Having each European Nation train its own useless "so…

This is making me extremely depressed. If this was coming from Anthrohpic I would just need to wait for OpenAI to drop a similar model. But if this comes from the US government, th…

I don't know if you are aware, but some people reported in Twitter that Fable 5 may flag the message regardless of content if it knows (from either pretraining knowledge or memorie…

> Performance on benchmarks has practically leveled off Ehm, no? DeepSWE[1] for example shows that new models like gpt-5.5 continue to show big improvements compared to older model…

Claude can indeed decide to terminate conversations on its own using a special tool[1] if it feels "uncomfortable" with how the conversation is going. Also, very famously, in the m…

You don't get it. A human set up a software system allowing spicy autocomplete to solve open math problems if the appropriate keyword appears in its output.

I skimmed through the paper completely expecting polite prompts to do better, and when I saw table 2 I lost it hahahahaha. The rude prompts are specially funny. I mean: > You poor …

Someone blatantly copied their tutorials but ChatGPT is to blame, somehow? The accusation here isn't even that ChatGPT learned from their tutorials and then generated them verbatim…

> Was the question asked by a mathematician? As per the report, the prompt used to solve the problem is AI-written and the solution was initially graded by an AI grading pipeline. …

I disagree. Even frontier models still achieve way worse results than the human baseline in VendingBench. As long as models can't manage optimally something as simple as a vending …

To make performant code sometimes requires implementing or using "unsafe" functions (it's not obligatory, and a lot of projects don't use them; but it was probably needed to map Bu…

For now it appears that it talks only to the Codex App. Some users in this thread are saying that apparently the Codex CLI will support it on the next official release.

Not if you use Linux; app not available yet.