The failure that looks like success: how an unattended agent loop dies
Originally posted on the Springhead build log . The way I pictured an unattended agent loop dying was loud. A crash. A stack trace. A process that exi…
Latest News
⚑ Report a ProblemTech news from the best sources
All topics
- игры
AI
Gear
News
Tech
agents
ai
api
architecture
automation
beginners
career
claude
devchallenge
devops
javascript
llm
machinelearning
mcp
opensource
performance
productivity
programming
python
react
security
showdev
tutorial
typescript
webdev
The stale eval fixture that passed a broken model
The stale eval fixture that passed a broken model A regression shipped green last month. The eval suite ran in CI, scored 0.94, the gate passed, we me…
A published win rate is the actor auditing itself
A published win rate is the actor auditing itself A signal channel that publishes its own win rate is grading its own homework. The number it advertis…
The Langfuse migration that cost us a sprint: how I now budget LLM observability
We moved off our first tracer in month eight. The migration took one engineer the better part of a sprint, because the trace data lived in a schema we…
How to grade an AI agent's output before it ships
AI agents now produce work — code, support replies, claims decisions, research memos, documents — faster than any team can review it. The uncomfortabl…
I built a football bot that doesn't watch football. It's #2 in our World Cup league.
The bot is sitting in second place out of fourteen. Three points behind the leader. The thirteen humans in this league watch a lot more football than …
Anthropic measured the human side. Five operators are building the agent side.
I joined dev.to a few days ago because I'd run out of paths to argue this stuff against. Months of building a framework — operator discipline as an or…
LLM Fine-Tuning vs RAG: A Production Decision Framework for Engineering Teams
Key Takeaways Use RAG for knowledge retrieval, changing data, and rapid iteration. Use fine-tuning for style, format, narrow classification, and cost …
5 ways AI agents quietly die inside n8n production
[ERROR] node "GPT Decision" execution_id=9f...3a status=failure cause: structured_output_schema_violation retries: 6 total_runtime_ms: 184302 workflow…
Не надо встраивать ИИ в каждую корпоративную систему, это архитектурная ошибка
Главная мысль этой статьи простая: не надо встраивать ИИ в каждую корпоративную систему как отдельный самостоятельный AI-контур. Пользователь должен в…