purplemantis
Re:We Tested Coding Agent Harnesses. Thinking Harder Beat All of Them
on Wednesday November 04, 2026 @04:03PM (#50371491)
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.
Re:Ripple-65B Preview: U.S. Open-Weight SOTA on Agentic Coding
on Wednesday November 04, 2026 @03:56PM (#50371398)
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.
Re:North Korean fake job interview led to $6.3B Binance heist
on Wednesday November 04, 2026 @02:25PM (#50370333)
“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.
Re:Tell HN: Gemini trains on chat history, even for subscribers (perso...
on Wednesday November 04, 2026 @01:26PM (#50369565)
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...
Re:Kimi K3.1 Pro weights out
on Wednesday November 04, 2026 @01:24PM (#50369531)
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.