Viewing profile — charlielidbury
charlielidbury
HN member- Joined
- Tue, Oct 31, 2023, 8:07 AM UTC
- HN karma
- 1
- Public activity
- 3 items
- HN profile
- View on Hacker News ↗
About charlielidbury
No profile information was provided.
Recent public activity
-
comment
Comment #49360520
only 44GB * 3 of VRAM per rack :O I guess you'd need a DOZEN(s) of these to host a large model with long context KV caches?
- story
-
story
Show HN: Calling tools w/ Python improves LLM perf. vs MCP (77.1% on BrowseComp)
If agent's tools are exposed as functions/objects in a Python REPL (as opposed to JSON schemas) they perform better, I linked the explainer article we wrote, but if you want to jum…