Viewing profile — max-t-dev
max-t-dev
HN member- Joined
- Wed, Apr 29, 2026, 9:17 AM UTC
- HN karma
- 48
- Public activity
- 10 items
- HN profile
- View on Hacker News ↗
About max-t-dev
No profile information was provided.
Recent public activity
-
comment
Comment #47957145
I think there is some benefit to plugins, it's hard to say how much. I find the superpowers plugin is quite good, mostly in its structured approach to a conversation. Generally the…
-
comment
Comment #47957134
Hahaha
-
comment
Comment #47956868
As much as I wish it stacked like that I don't think it would make a difference haha
-
comment
Comment #47956677
Caveman doesn't compress the reasoning, only the output. The model still does its full reasoning before generating the response, caveman just affects how the final response is form…
-
comment
Comment #47956359
Yeah, makes sense. The appeal is is more to cut output tokens for cost, than downstream reading experience. But the benchmark suggests it doesn't offer as much benefit as "be brief…
-
comment
Comment #47956332
Yeah definitely a good point, Claude assisted with editing and tidying up the content with the caveat that it can flatten the voice. I agree the humanity behind writing is disappea…
-
comment
Comment #47956306
Yeah fair point. The benchmark is single-run per arm-prompt pair, so the variance finding on safety categories could be noise rather than signal. Findings doc flags this for the sc…
-
comment
Comment #47956221
Agree "be brief." being simpler with no setup is most of what people need in practice. To be fair to caveman though, it does more than compression; consistent output structure, int…
-
comment
Comment #47954746
Author here. Caveman is a popular Claude Code plugin that compresses Claude's responses via a custom skill with intensity modes. I wanted to know whether it actually beats the simp…
- story