Dima Ch
191 posts
@Fried_rice opuslop is opuslop, whatever anthropic heads say - bullshit.
English
Claude code source code has been leaked via a map file in their npm registry!
Code: …a8527898604c1bbb12468b1581d95e.r2.dev/src.zip
English
How to finally become the 10x engineer:
Add WarCraft 3 sounds to Claude hooks to get alerts when it finishes a task or needs permission.
English
AgentCraft v1 is live ⚔️
Control your agents like it's an RTS game!
It's early. It's rough. It's fun.
npx @idosal/agentcraft
English
Speaking of skills
I thought Figma MCP is shit (at least for mobile development) up until the moment I tried OpenAI's figma-implement-design skill. This thing just makes it work
Tweaked it a bit to focus on reusing components: github.com/za4em/skills-c…
English
@maestro__dev I'll consider moving these rules to skills as they aren't project specific
English
@maestro__dev I used it only in codex, gpt-5.3-codex on high figured it out kinda quickly. If any other model or agent struggles - these instructions may help: github.com/za4em/maestro-…
English
Using @maestro__dev MCP with AI agent is great for the result validation and e2e tests
It gives your agent eyes and a phone, so it can validate its own work. Removing manual testing from the workflow (or replacing a part of it) simplifies things a lot
English
i've been using it for all my work for the past 24 hours and i don't see much of a difference from opus
maybe opus is a bit smarter but this guy is so fast and so cheap
and we're probably going to drop our prices even further
OpenCode@opencode
kimi 2.5 is free for a limited time in OpenCode if you ran into bugs before, upgrade OpenCode - we've fixed up a few things and we're having a great time with it now huge thanks to fireworks for getting this model running so well so quickly
English
@RayFernando1337 It's pretty good at coding as well. I use it for nearly everything except planning!
The only downside is that this model is tailored for claude code and doesn't perform as well in other agents. So, a little bit of setup is required.
English
@d_chem_ Good for code reviews? What else do you throw at it?
English
GPT-5.2 Low just beat Opus 4.5 on a real code review. The cheapest reasoning setting caught issues the expensive model missed.
English
@catgirlprostate I have more hours clocked in de_dust2 than you have hours on this planet
English
Guy who has never played a video game before but has read the headline that it's the most profitable entertainment industry:
Guillermo Rauch@rauchg
There's definitely a non-zero chance we get "generate your own GTA6 in a few minutes" before GTA6
English
You can now use Claude Code with OpenRouter 🎊
Code with over 320 LLMs, including 39 free ones!
English