Hacker News: hagen8

New comment by hagen8 in "Herdr: Agent multiplexer that lives in your terminal"

hagen8 — Mon, 29 Jun 2026 09:12:22 +0000

This is way to complex... Why don't just use some harness which manages all that and give u a good UI?

New comment by hagen8 in "1M context is now generally available for Opus 4.6 and Sonnet 4.6"

hagen8 — Sat, 14 Mar 2026 01:07:55 +0000

Well, the question is what is contributing to the usage. Because as the context grows, the amount of input tokens are increasing. A model call with 800K token as input is 8 times more expensive than a model call with 100K tokens as input. Especially if we resume a conversation and caching does not hit, it would be very expensive with API pricing.

New comment by hagen8 in "1M context is now generally available for Opus 4.6 and Sonnet 4.6"

hagen8 — Sat, 14 Mar 2026 00:57:57 +0000

Did u use the API or subscription?

New comment by hagen8 in "Redox OS has adopted a Certificate of Origin policy and a strict no-LLM policy"

hagen8 — Tue, 10 Mar 2026 10:03:26 +0000

They will sooner or later change that policy or get very slow in keeping up.

New comment by hagen8 in "GPT-5.4"

hagen8 — Fri, 06 Mar 2026 06:42:34 +0000

But does it use the same agent harness? Because the harness determines the behavior a lot.