mikepollard_dev
Joined 2 years ago
Karma
41
Submissions
9
Member since
May 30
I have been helping startups go from 0 to 1 since 2019. I currently work at inference.net
View on Hacker NewsRecent submissions
Comment · 4 months ago
It's more-so recursive decomposition rather than clustering failures or stream summarizing. You can look at this repo if you want to learn more about how RLM's work: https://github.com/alexzhang13/rlm
Comment · 4 months ago
Yeah, fair question. For a small number of traces just dumping them into Claude Code can work well.
However, once you're at production scale the problem changes. You can't always fit 10,000+ traces in Claude Code and still have it be effective especially when the relevant pattern of agent failures may only become apparent when you pass that many in. That's where the RLM based methodology helps. HALO recursively decomposes the trace data into smaller investigations, analyzes those sub-pieces, and then synthesizes those up to determine the recurring harness-level failure modes better than Claude Code or Codex ever could at a large scale.
Comment · 2 years ago
Security platforms should be open source by default. It provides assurance that nothing weird is occurring behind the covers and also shows confidence in the implementation and the cryptography behind it all.
I will also never forgive Authy for removing desktop support with near immediate deprecation and no way to export off their platform.
I will never use another Twilio product again after that.