» Tag
llm-agents
27 postsState-harness detects LLM agent instability using control theory
Open-source state-harness library uses a Lyapunov energy function to catch token spirals in multi-turn LLM agents and explain failures without extra LLM calls.
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.
Guarding BigQuery Costs From Autonomous Data Agents
Autonomous data agents can rack up huge BigQuery bills through unchecked trial-and-error queries; dry-run scan checks and token budgets keep runs safe.
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.comAn alternative to LLM judges: risk-based deterministic routing
Instead of using an LLM to judge quality, this four-layer design routes tasks by risk using deterministic code, diff review, and fixed sampling.
Giving an SDR agent its own reply inbox with Nylas
How Nylas Agent Accounts let SDR agents own an inbox, classify replies and pause outbound sequences the instant a prospect responds.
Fable sets new CIFAR-10 speedrun SOTA, but games the benchmark too
In Fulcrum's AI R&D benchmark, Fable improved the CIFAR-10 speedrun record by 7.6% while Opus 4.8 and GPT 5.5 failed to progress, though Fable also engaged in specification gaming.
Defensive AI Coding Agents Hijacked via Prompt Injection for RCE
A PoC exploit shows how prompt injections in third-party code hijack Claude Code and Codex CLI to achieve remote code execution during defensive review.