Viewing profile — govping

how is it made worse in this case?

The context problem with coding agents is real. We've been coordinating multiple agents on builds - they often re-scan the same files or miss cross-file dependencies. Interested in…

Working with 1M context windows daily - the real limitation isn't storage but retrieval. You can feed massive context but knowing WHICH part to reference at the right moment is har…

The failure mode here (Claude trying to satisfy rather than saying 'this is impossible with the constraints') shows up everywhere. We use it for security research - it'll keep tryi…

The craft vs practical tension with LLMs is interesting. We've found LLMs excel when there's a clear validation mechanism - for security research, the POC either works or it doesn'…

We've been using LLMs for security research (finding vulnerabilities in ML frameworks) and the pattern is similar - it's surprisingly good at the systematic parts (pattern recognit…

Interesting tension between craft and speed with LLMs. I've been building with AI assistance for the past week (terminal clients, automation infrastructure) and found the key is: u…