» Tag
llm
477 postsA Deterministic Guard Stops LLM Agents From SQL Overfetching
An open-source, LLM-free guard checks agent-generated SQL against user roles before execution, preventing text-to-SQL systems from overfetching sensitive data.
Why AI visibility dashboards are mostly useless
AI search visibility trackers have become a $100M industry, but research shows most of these measurements are statistically meaningless noise dressed as precision.
n8n Fixes Silent Cross-Item Data Leak in Batched AI Agent Calls
A silent bug in n8n's batched AI Agent node let tool-call histories leak between items; here's the root cause and the fix.
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.comCacheTracer Exposes Hidden Dependencies in LLM API Reseller Chains
CacheTracer uses prefix-cache side channels to reveal hidden dependencies among LLM API resellers, finding shared cache reach in 37% of tested pairs.
SIMURG: Real-Time Guard Stops LLM Decoding Corruption Mid-Stream
SIMURG is a numpy-only real-time monitor that detects and aborts LLM decoding corruption mid-stream, with zero training and conformal calibration.
Inside OpenAI's Agent Loop: How Harness, API, and Inference Cut Costs
OpenAI engineers detail how harness, API, and inference layer optimizations cut cost and latency in agentic systems like Codex and ChatGPT Work.
Agent 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.
Scaling Laws Explained: From Kaplan to Chinchilla to Overtraining
A breakdown of LLM scaling laws from Kaplan to Chinchilla, and why modern models are deliberately overtrained to cut inference costs.
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.