Meta's new structured prompting technique makes LLMs significantly better at code review — boosting accuracy to 93% in some cases

This technique can be used out-of-the-box, requiring no model training or special packaging. It is code-execution free, which ...
BeInCrypto

Claude Code’s 512,000-Line Leak Rattles Anthropic’s $350 Billion IPO Ambitions

Anthropic leaked 512,000 lines of Claude Code source via npm, its second security lapse in days as the $350B startup eyes a ...

Matcha model makes drug candidate screening more than 30 times faster

Ligand Pro, founded by Skoltech professors and a Skoltech Ph.D. student, has presented Matcha, an AI-powered molecular docking model that performs virtual drug screening 30 times faster than the large ...
SecurityWeek

Critical Vulnerability in Claude Code Emerges Days After Source Leak

The key is that researchers can see how Claude Code is meant to work but cannot recreate it because the leak does not include ...
InfoWorld

Meta shows structured prompts can make LLMs more reliable for code review

A new “semi-formal reasoning” approach forces AI models to trace code paths and justify conclusions, improving accuracy while ...