(The original video is in french but it has an autodubbed english track)

AISLE demonstrated in the last few weeks that small (weak per the author) models can find the openBSD bug (when pointed at the code). And apparently did several runs with the same results. Was gpt oss hallucinating on all those runs?

And what separates a strong model from a weak one? Is qwen3.5 27b weak?

Don't trust who says that weak models can find the OpenBSD SACK bug. I tried it myself. What happens is that weak models hallucinate (sometimes causally hitting a real problem) that there is a lack of validation of the start of the window (which is in theory harmless because of the start < end validation) and the integer overflow problem without understanding why they, if put together, create an issue. It's just pattern matching of bug classes on code that looks may have a problem, totally lacking the true ability to understand the issue and write an exploit. Test it yourself, GPT 120B OSS is cheap and available.

BTW, this is why with this bug, the stronger the model you pick (but not enough to discover the true bug), the less likely it is it will claim there is a bug. Stronger models hallucinate less, so they can't see the problem in any side of the spectrum: the hallucination side of small models, and the real understanding side of Mythos

Laudato si : https://www.vatican.va/content/francesco/en/encyclicals/docu...

I don't believe this is specific to the US. The agent at the border always has the last decision on whether you can enter the country even if you have a valid visa and travel documents.

Comments URL: https://news.ycombinator.com/item?id=36851058

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=36768301

Points: 3

# Comments: 0

Something like this :

    magnet:?xt=urn:btih:BSXYFTH5VCJLB32DYS2FPTJUB2IVNKUS&dn=Fedora-Astronomy_KDE-Live-x86_64-37

Microsoft did something similar before (without a vm) called Static Typescript : https://www.microsoft.com/en-us/research/publication/static-...

I always read it as being about empathy. Explaining that sometimes a person's action probably have subjectively valid reasons that we should try to understand, or at least try to accept.

I read the gp comment's quote the same way that's why I shared this one.

The so-called ‘psychotically depressed’ person who tries to kill herself doesn’t do so out of quote ‘hopelessness’ or any abstract conviction that life’s assets and debits do not square. And surely not because death seems suddenly appealing. The person in whom Its invisible agony reaches a certain unendurable level will kill herself the same way a trapped person will eventually jump from the window of a burning high-rise. Make no mistake about people who leap from burning windows. Their terror of falling from a great height is still just as great as it would be for you or me standing speculatively at the same window just checking out the view; i.e. the fear of falling remains a constant. The variable here is the other terror, the fire’s flames: when the flames get close enough, falling to death becomes the slightly less terrible of two terrors. It’s not desiring the fall; it’s terror of the flames. And yet nobody down on the sidewalk, looking up and yelling ‘Don’t!’ and ‘Hang on!’, can understand the jump. Not really. You’d have to have personally been trapped and felt flames to really understand a terror way beyond falling.

I think they're planning to move it next to the like button to make it more visible.

Do you have the names of the authors of the first one?

A lazy google search didn't mention the commission of two reports

Comments URL: https://news.ycombinator.com/item?id=34044664

Points: 4

# Comments: 1

More info here : https://www.codegram.com/case-studies/github-skyline/

Comments URL: https://news.ycombinator.com/item?id=33168846

Points: 1

# Comments: 0