Sharpening My Vibe Coding Skills: Adding Personal Skills to Coder
I'd typed some version of the same paragraph into Coder Agents chat a dozen times before it occurred to me that I was the bug. Long agent sessions h…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
- игры
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
database
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
testing
tutorial
typescript
webdev
Thursday Thoughts: Why Anthropic Is the Next AWS, but Potentially Worse
A few weeks ago I wrote about how AI-native mirrors cloud-native — lift-and-shift now, real architectural rethink later. The same pattern enterprise…
The Real Cost of AI Agents Is Not the Model Bill
The language model call is predictable. You know the token count. You can estimate the cost. The surprise comes from everything the agent calls afte…
Friday Fixes: The Fix That Wasn't
Three bugs this month. All three looked fixed before they broke. The date was quoted in 51 out of 52 posts. The model was pinned to a specific versi…
The Sandbox Prodigies: Roblox, Event-Driven Logic, and the Future of Engineering
A few days ago, my 11-year-old relative showed me a snippet of code he was hacking together for a custom game in Roblox. It wasn't clean, syntactica…
Friday Fixes: Housekeeping the Homelab and Hub
Some weeks you ship a big feature. Other weeks you sweep the floor so the big features keep working. This was a floor-sweeping week — two completely…
Hermes Agent: First Contact
Someone recommended I look at Hermes Agent as an alternative to OpenClaw. I've been running OpenClaw on the homelab since early May — it drives a Di…
You Can't Prompt Your Way Out of a Hard Constraint
Thursday morning I removed five nodes from my content pipeline. By lunch I understood something about building with language models that eleven fail…
Seven PRs Before Lunch: Parallel Claude Code Tabs Plus Audit-Before-Bump
Two weeks ago I rebuilt my Claude Code context architecture . Cut CLAUDE.md from 14K tokens to 2.4K. Moved 12 stable rule sets into skills that load…