EGOIST
@localhost_5173
CTO of http://chatwise.app
ChatWise affiliate program is now open. You earn 15% of each sale by referring your friends Powered by @useAffonso 😄 docs.chatwise.app/affiliate-link…
As a casual vibe coder, this is my monthly CC usage under the $20 plan, only rate limited once so far.
claude code makes using termux on android so much easier now 😄
true
complexity first, simplicity second people say “keep it simple,” but most approach it backwards. they start from simple, then add on complexity without seeing the whole. that’s how you end up with frankenstein products: clean-looking components awkwardly stitched together, held…
UM870/SER8 got pretty popular lately because of @dhh, so I also got one (UM870) 😄 The time it took to build ChatWise on UM870: front-end 40s / tauri backend 1m40s While on M4 Mac: front-end 25s / backend 45s
I tried building ChatWise (Tauri) on this CPU, the Rust part took 15 seconds, while on Mac Mini M4 it’s 4 seconds.
M4 Mac Mini is a great Mac, but it's not a particularly good deal as a dev machine. A @Beelinkofficial SER8 is the same money, but comes with 32GB RAM + 1TB, and is almost twice as fast for multi-core workloads like our HEY test suite!
I still have my bet on DeepSeek instead of other Chinese LLMs, cuz DeepSeek would probably never release a half baked project like this 😂
You can already try it for free with OpenRouter on ChatWise openrouter.ai/qwen/qwen3-235…
Bye Qwen3-235B-A22B, hello Qwen3-235B-A22B-2507! After talking with the community and thinking it through, we decided to stop using hybrid thinking mode. Instead, we’ll train Instruct and Thinking models separately so we can get the best quality possible. Today, we’re releasing…
A lot more people would use @zeddotdev if they provide better integration with Claude Code
You never knew you had anger issues until you interacted with an LLM code assistant
Claude Code is so much better than Gemini CLI / Code Assist 😅