Joe Hoot 리트윗함
THE GUY WHO BUILT CLAUDE CODE USES A SINGLE CLAUDE. MD FILE WITH RULES, ERRORS, AND CONVENTIONS THAT THE MODEL READS EVERY SESSION.
English
Joe Hoot
273 posts
Joe Hoot 리트윗함
🚨 Anthropic just open-sourced the exact Skills library their own engineers use internally.
Stop building Claude workflows from scratch.
These are plug-and-play components that work across Claude Code, API, SDK, and VS Code copy once, deploy everywhere.
What's inside:
→ Excel + PowerPoint generation out of the box
→ File handling and document workflows
→ MCP-ready subagent building blocks
→ Pre-built patterns for multi-step automation
→ Production templates you'd normally spend weeks writing
The old way: re-explain your workflow every single chat.
The new way: build a Skill once, Claude never forgets how you work.
100% Open Source. Official Anthropic release.
Repo: github.com/anthropics/ski…
English
Joe Hoot 리트윗함
🚀 Introducing the Qwen 3.5 Medium Model Series
Qwen3.5-Flash · Qwen3.5-35B-A3B · Qwen3.5-122B-A10B · Qwen3.5-27B
✨ More intelligence, less compute.
• Qwen3.5-35B-A3B now surpasses Qwen3-235B-A22B-2507 and Qwen3-VL-235B-A22B — a reminder that better architecture, data quality, and RL can move intelligence forward, not just bigger parameter counts.
• Qwen3.5-122B-A10B and 27B continue narrowing the gap between medium-sized and frontier models — especially in more complex agent scenarios.
• Qwen3.5-Flash is the hosted production version aligned with 35B-A3B, featuring:
– 1M context length by default
– Official built-in tools
🔗 Hugging Face: huggingface.co/collections/Qw…
🔗 ModelScope: modelscope.cn/collections/Qw…
🔗 Qwen3.5-Flash API: modelstudio.console.alibabacloud.com/ap-southeast-1…
Try in Qwen Chat 👇
Flash: chat.qwen.ai/?models=qwen3.…
27B: chat.qwen.ai/?models=qwen3.…
35B-A3B: chat.qwen.ai/?models=qwen3.…
122B-A10B: chat.qwen.ai/?models=qwen3.…
Would love to hear what you build with it.
English
Joe Hoot 리트윗함
Code → Context. Enter the CDLC (Context Development Lifecycle). I wrote up my thoughts on where this is going and the parallels with what we learned from DevOps.
jedi.be/blog/2026/the-…
English
Joe Hoot 리트윗함
Wanna save some tokens? add this to your AGENTS.md
## Token Efficiency
- Never re-read files you just wrote or edited. You know the contents.
- Never re-run commands to "verify" unless the outcome was uncertain.
- Don't echo back large blocks of code or file contents unless asked.
- Batch related edits into single operations. Don't make 5 edits when 1 handles it.
- Skip confirmations like "I'll continue..." Lust do it.
- If a task needs 1 tool call, don't use 3. Plan before acting.
- Do not summarize what you just did unless the result is ambiguous or you need additional input.
English
2 different dashboard layouts
card based:
Joe Hoot@JoeHootDev
Being an experienced dev and having access to the frontier AI models allows you to iterate on your own custom software much faster than ever before. This is a custom dashboard "kit" on top of Mantine UI that is them-able. Sidebar layout and navigation is all config driven.
English
Being an experienced dev and having access to the frontier AI models allows you to iterate on your own custom software much faster than ever before.
This is a custom dashboard "kit" on top of Mantine UI that is them-able.
Sidebar layout and navigation is all config driven.
English
Joe Hoot 리트윗함
v1.2.0 of opencode includes our migration to sqlite - if anything goes wrong don't worry, your original data is not yet deleted
you can clear out `opencode.db*` files in %APPDATA% or ~/.local/share/opencode folder and it'll rerun
this paves the way to a lot of cool features!
English
I dont want to have to keep thinking about which models to use while im developing. It's poor user experience. I just want to use a coding model without having to worry about if Im using the right version of that model
OpenAI Developers@OpenAIDevs
Introducing GPT-5.3-Codex-Spark, our ultra-fast model purpose built for real-time coding. We’re rolling it out as a research preview for ChatGPT Pro users in the Codex app, Codex CLI, and IDE extension.
English
Joe Hoot 리트윗함
This is a HUGE win for developers.
Claude Code is excellent, but the $200/mo Max plan can be expensive for daily use.
GLM-5 works inside Claude Code, with (arguably) comparable performance at ~1/3 the cost.
Setup takes ~1 minute:
• Install Claude Code as usual
• Run `npx @z-ai/coding-helper` and follow the steps
One caveat: switching Claude Code back to Anthropic is a bit cumbersome today (would be nice if the helper tool supported this).
For now you'll need to switch back manually:
1. Open ~/.claude/settings.json
You’ll see something like:
"env": {
"ANTHROPIC_AUTH_TOKEN": "your_zai_api_key",
"ANTHROPIC_BASE_URL": "api.z.ai/api/anthropic",
"API_TIMEOUT_MS": "3000000"
}
2. Remove at least:
• ANTHROPIC_AUTH_TOKEN
• ANTHROPIC_BASE_URL
Either way, this is a big win—and price/performance in coding tools is indeed moving fast!
Z.ai@Zai_org
Introducing GLM-5: From Vibe Coding to Agentic Engineering GLM-5 is built for complex systems engineering and long-horizon agentic tasks. Compared to GLM-4.5, it scales from 355B params (32B active) to 744B (40B active), with pre-training data growing from 23T to 28.5T tokens. Try it now: chat.z.ai Weights: huggingface.co/zai-org/GLM-5 Tech Blog: z.ai/blog/glm-5 OpenRouter (Previously Pony Alpha): openrouter.ai/z-ai/glm-5 Rolling out from Coding Plan Max users: z.ai/subscribe
English
really getting tired of these providers, what are we switching to? Opencode + kimi/GLM?
Alexander Embiricos@embirico
Update: Between 15:35 and 18:45 PT today, we were overflagging for potentially suspicious activity. We estimate 9% of users were impacted. We fixed the issue at 18:45 PT and are working to prevent this overflagging going forward.
English