@tengyanAI Ehh, I think they were pretty clear about the change. This is anthropics first model with different reasoning efforts. When I was using high effort, it felt a bit like a slot machine on the quality of the output. More reasoning isn’t always better. IMO medium gives solid results.
Weekend vibe coding. Cost router for OpenClaw that classifies each LLM request by complexity and picks the cheapest model that can handle it. Runs locally & is easily configurable. https://t.co/SDryHBnLuv
If you started using Claude Code over the holidays, you might be curious about how AI actually works, the benefits and risks, and where it's headed.
Here are some of my favorite papers on alignment, interpretability, and societal impacts 🧵