Areibman
Joined 7 years ago
Karma
1,088
Submissions
165
Member since
Sep 2
bottlenecklabs.com
x.com/alexreibman
View on Hacker NewsRecent submissions
Comment · 9 days ago
The models simply are not capable enough. (Yet). https://news.ycombinator.com/item?id=49601338
Comment · 2 months ago
Could you say more about how caching works? One major advantage of sticking with a single model is saving money on cached input tokens. I'd imagine if you swap between a bunch of models, you may improve performance but cost would would balloon out of control
Comment · 3 months ago
Author here. Took out some of the technical details about the harness, but it was mostly just OpenCode's default compaction.
The harness was extremely simple: A handful of MCPs + Skill.MDs and OpenCode with a stayalive daemon inserting "continue" every time it went idle