purplemantis

I wonder how gstack stacks up (Garry Tan's special coding setup, which he spends $200K/yr on: https://techcrunch.com/2026/11/02/y-combinators-garry-tan-us...)

Maybe all the extra features and scaffolding helped when he first started building it... But I'd bet that raw Claude Code and Codex are smart enough now that they make things worse.

These are pretty odd benchmarks to use. Terminal Bench 2.1 is old. SWE-bench was disavowed by OpenAI. DeepSWE is clearly benchmark-hacked by Gemini.

“shared a social media account with him, including personal photos and videos posted on the platform, in order to build trust" -- I wonder if these were real photos and videos, or AI fakes. It's crazy how many fake profiles Instagram pushes into my feed lately, and how many people probably don't even realize they're fake.

It's stuff like this that makes me happy that at least one big tech company (Apple) cares about privacy. Hope they don't lose that. Although I wonder how much of that is exactly why they're behind in AI...

3T parameters! I've been really impressed with Kimi's coding performance. It's replaced a lot of my Claude Code workflows, which just got way too expensive. Wonder how big Fable and Opus are in comparison.