Viewing profile — sachamorard
sachamorard
HN member- Joined
- Fri, Jan 20, 2023, 9:00 AM UTC
- HN karma
- 5
- Public activity
- 37 items
- HN profile
- View on Hacker News ↗
About sachamorard
Recent public activity
- story
- story
-
comment
Comment #48842593
What does that have to do with the topic? Someone is sharing something serious on this thread, I don't see how your message helps.
-
comment
Comment #48784170
It's far from being a foolish idea, and it seems to me that the project correctly documents its own limitations. It's rare to see a README list so precisely where the tool falls sh…
-
comment
Comment #47706645
More info in the GitHub repo, in the reports folder (sorry, I'm not sure I can add the link here without being flagged). "Codex + Edgee consumes roughly half the fresh tokens of th…
-
comment
Comment #47704727
[dead]
- story
- story
- story
- story
-
comment
Comment #47599317
The compaction problem described here is worse than it looks because of the asymmetry between the compactor and the reader. The model doing the compaction has full access to everyt…
-
comment
Comment #47592210
[dead]
- story
-
comment
Comment #47443746
[dead]
- story
- story
- story
-
comment
Comment #47423846
Cool idea. I have had rather a bad experience with semantic caching. Do you have benchmarks that demonstrate the effectiveness?
-
comment
Comment #47423820
Really cool concept! The spatial sorting into llms.txt is a clever touch. ;)
-
comment
Comment #47075064
That's exactly the trade-off we're pointing at. One nuance we've been seeing in practice is that the "utility" of a token isn't purely semantic: some tokens carry behavioral constr…
- story
- story
- story
- story
- story