@simonw

–

24 March 2026 19h48

Would you trust the current administration not to find a reason to claw back a grant?

Code Validation Tools Essential for AI Coding Agents

By

–

24 March 2026 19h38

As always though the trick is to arm them with a good coding agent harness and the right collection of tools – compilers and debuggers and linters and fuzzers and suchlike I don't trust any code produced by a model directly until I've seen the model run it

LLMs Show Strong Capability for Complex C Code Reasoning

By

–

24 March 2026 19h37

I would not have trusted LLMs with C code a year ago but today's models appear to be very good at reasoning through memory management and other tricky aspects That said I'm not enough of a C expert myself to credible evaluate what they're doing!

Security Visibility Trade-offs in Cyberattacks

By

–

24 March 2026 16h00

I don't understand how that benefits the attackers though, surely it just makes the issue MORE visible?

GitHub LiteLLM Exploit Comments Mystery Explained

By

–

24 March 2026 15h51

Anyone got any theories as to why there are hundreds of comments like this on the GitHub issue reporting the exploit? https://
github.com/BerriAI/litell
m/issues/24512
…

LiteLLM Package Quarantined on PyPI After Security Compromise

By

–

24 March 2026 15h35

Thankfully the LiteLLM package has now been marked as "quarantined" on PyPI so attempting to install the compromised update via pip et al shouldn't work

Fast AI Performance on Latest Mac Hardware

By

–

24 March 2026 5h56

It appears to work fast enough to be interesting on the latest Mac hardware

Protecting Journalist Sources From Government Subpoena Powers

By

–

24 March 2026 5h56

Think about journalists who sometimes need to protect their anonymous sources from governments with subpoena powers

Qwen3.5-397B Runs on iPhone with Streaming MoE Weights

By