LLM deployment
3 posts
Article
Parameter count is the wrong number to watch
Bonsai 2 27B's 9x smaller footprint is real, but near-lossless is an average - how to gate compressed LLMs on your own eval set before production.
Article
The same AI you're shipping wrote the malware
10,000 trojan GitHub repos weren't a malware breakthrough - they prove LLM safety lives in the model while abuse happens in the unguarded pipeline.
Article
Forge guardrails took an 8B model from 53% to 99%
A Show HN post says Forge guardrails took an 8B model from 53% to 99% on agentic tasks. Here's what that means for security and reliability.