AI finds thousands of zero-day exploits... including in FreeBSD.

[cracauer@]

Running a "bug-find" on each file of a large project has little chance of finding useful issues.

It turned out useful for me.

But this touches on the biggest problem I see with this style of code review: context size in the LLM in use. I find that even moderately-low-mid size files overrun the context window with too many input tokens. A whole-codebase review is out of question, let's leave this aside. But even grouping related files that could produce bugs only detectable when looking at the group will be challenging.

Keep in mind Anthropic charges you double when you use their models with larger context windows, which is 1 million tokens. And that is generally out of reach for local LLMs.

 

[msplsh]

This would drown devs.

That's not what they're doing with the tools tho, so it's not a problem.

 

[blackbird9]

The hype is big with this one...

Trump summons banks over terrifying new threat to financial system

The Trump administration summoned bank leaders this week to an urgent meeting on a new threat to the global financial system.

www.dailymail.co.uk