» Tag
ai
1033 postsAgent Skill Forces LLMs to Write Docs in ASD-STE100 Simplified English
An MIT-licensed Agent Skill forces LLM output into ASD-STE100 Simplified Technical English, cutting rule violations 72.9% across six Claude models.
Distilling DeepSeek into GPT-OSS Doesn't Transfer Its Censorship
Research shows distilling DeepSeek into GPT-OSS-120B boosts financial reasoning without inheriting the teacher model's political censorship.
Preventing Context Loss in AI Agents with Two-Document Pattern
Two-document pattern for AI agents: append-only log and editable index. Prevents context loss, corrects errors.
CommitBrief — AI code reviews, right in your terminal
A provider-agnostic, local-first CLI that reviews your staged changes, a historic range, or a whole GitHub pull request. Zero telemetry, no server. Free and open source.
commitbrief.comWho's Liable When AI and Doctors Share Medical Decisions?
A proposed seven-level framework classifies medical AI by autonomy, automation and scope to close liability gaps in clinical care.
Why Multi-Model AI Pipelines Lose the Truth at Handoffs
Model handoffs in multi-agent AI systems can silently erase caveats and evidence, turning careful findings into false certainty without errors.
Visa Turns Claude Mythos on Its Payment Network, Then Open-Sources the Harness
Visa used Anthropic's Claude Mythos to stress-test its payment network, then open-sourced the harness and its new Mean Time to Adapt metric.
When Anthropic's Fable Model Vanished, Gene Kim's AI Agents Nearly Broke
A US export order abruptly cut off Anthropic's Fable model mid-session, nearly breaking Gene Kim's personal AI agent system. Here's how he recovered.
Back-End Engineering in 2026: APIs Give Way to Agent Orchestration
Back-end engineering in 2026 shifts from stateless APIs to agentic systems: orchestration, async tasks, tool governance, and reasoning traces.
Stop Fine-Tuning Everything: A Framework for Model Adaptation
A decision framework for choosing between prompt engineering, RAG, fine-tuning, and domain pre-training when adapting foundation models.
SkyPilot and Hugging Face bring zero-egress storage to multi-cloud AI
SkyPilot and Hugging Face add a zero-egress storage backend, letting AI teams run GPU workloads on any cloud while data stays on the Hub.