Hacker News: joshheitzman

New comment by joshheitzman in "Claude Seems Down"

joshheitzman — Mon, 17 Aug 2026 00:48:04 +0000

Personally I don't care about common benchmarks as I don't find actual coding agent performance correlates strongly with them. One reason to use open-weight models is that they don't hide the reasoning, so you can do very aggressive context management in your harness to use significantly less tokens. Smaller prompts are faster since KV is N^2 plus it can be dramatically cheaper (if you balance your aggressive context management with maintaining the prefix cache as much as possible). Even paying for API prices directly and using agents as much as I want I spend less per month than the $200 I spent on a Claude MAX sub when I had it.

New comment by joshheitzman in "Claude Seems Down"

joshheitzman — Sun, 16 Aug 2026 22:18:21 +0000

Dozens of providers of open-weight models. I have one session going with synthetic.new and another going with novita.ai right now.

New comment by joshheitzman in "Models Are Getting Dumber on Purpose"

joshheitzman — Sun, 16 Aug 2026 21:15:21 +0000

As RAM prices are so nuts, I picked up a used gaming laptop early this year with an RTX 3070 (i.e. 8GB) to match the specs for my gaming tower that's run everything I'm interested in just fine. That includes recent Unreal 5.x games (Satisfactory, Fortnite, etc.) with high graphics settings on a 4k TV (60hz). There aren't a ton of games that require more than 8GB of GPU ram.