Viewing profile — martianvoid

martianvoid

HN member

No profile information was provided.

comment
Comment #49045169
It's actually crazy to see the difference between opus 5 and the next best model on ARC AGI 3 when you actually look at the ARC AGI problems

Sat, Jul 25, 2026, 6:59 AM UTC
story
NeurIPS Mech Interp Workshop is getting more AI slop
Wed, Jul 15, 2026, 9:55 AM UTC
comment
Comment #48814931
I am very much skeptical on the joint optimization of the harness and the model weights, I mean we can argue that claude code itself was a joint optimization of the claude, they re…

Tue, Jul 07, 2026, 8:09 AM UTC
story
You can never replace your understanding
Fri, Jun 26, 2026, 4:19 AM UTC
story
The Art of War
Fri, Jun 26, 2026, 4:09 AM UTC
story
Show HN: Multi Agent Protocol for AI Scientist by Hexo Labs
Thu, Jun 25, 2026, 11:35 AM UTC
story
The Process Was the Point
Mon, Jun 08, 2026, 4:47 PM UTC
story
AI Agent that at inference time updates it's harness and model weights
Sun, May 31, 2026, 11:13 AM UTC
comment
Comment #48342534
Sun, May 31, 2026, 2:29 AM UTC
story
Tsplat – Run Gaussian splatting in your terminal
Thu, May 28, 2026, 12:15 PM UTC
story
Gaussian Splatting for Dummies
Tue, May 19, 2026, 5:28 PM UTC
story
Gaussian Splatting for Dummies
Sun, May 17, 2026, 6:48 AM UTC
comment
Comment #48054973
This is just git with extra steps...

Thu, May 07, 2026, 9:03 PM UTC
comment
Comment #48046055
Is there any codebase associated with this that we can check and tinker with? or is this just a promo thing?

Thu, May 07, 2026, 6:18 AM UTC