Claude code is designed for anthropic models. Try it with opencode!

I will, right now.

EDIT: opencode was a bit slow with qwen3.5:35b using Ollama. Faster/nicer to use with Liquid lfm2:latest

Try llama.cpp - it usually excels with these MoE models imho.

Or Pi

Or Oh My Pi

>We have tried in good faith to reach an agreement with the Department of War

LMFAO

It's a rather humorous riddle for 2026 LLMs, it seems!

ChatGPT and Claude's eco friendly guardrails are trumping their reasoning ... but Kimi prevails!

If you believe that rushing capabilities ASAP is the right call, that is.

Starts in 1 hour! Free livestream! Who's watching?

I'm smiling already. Excellent read. This writer has SKILLS!

I think we'll be fine. AIs definitely generate a lot of garbage, but then they have us monkeys sifting through it, looking for gems, and occasionally they do drop some.

My point is, AI generated code still has a human directing it the majority of the time (I would hope!). It's not all bad.

But yea, if you're 12 and just type "yolo 3d game now" into Claude Code, I'd say I'd be worried about that but then immediately realized no... that'd be awesome.

So yea, I think we'll be fine.

Amazing. I want one. Keep up the great work!

A couple of facts on the Florida case: it was a jury verdict, not a judge. The jury found Tesla 33% at fault for a 2019 Key Largo crash. Damages were $129M compensatory (Tesla responsible for 33% of that) plus $200M punitive, for $243M total.

The driver admitted he looked down after dropping his phone and blew a stop sign; Tesla argues his foot was on the accelerator, but the jury still assigned partial fault because Autopilot was allowed to operate off limited-access highways and the company didn’t do enough to prevent foreseeable misuse. The driver had already settled separately.