» Tag
ai
1022 postsAI Agent Memory Is Just a Smarter Filing Cabinet
Today's AI agent 'memory' is retrieval in disguise—it can't tell if past answers were right. Real memory needs judgment that learns from outcomes.
Emotion on cloned voices in Qwen3-TTS: a 25 MB graft and steering vectors
A new 25 MB .qvoice graft format brings emotion control to cloned voices in Qwen3-TTS. Combining steering vectors with CSP fine-tuning preserves timbre while enabling six core emotions plus seven emotion blends.
VetoBench Tests Whether AI Agents Forget Rejected Decisions
VetoBench is an open benchmark asking whether AI memory systems re-propose previously rejected engineering decisions, not just whether retrieval works. Results are striking.
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.comAI Agent Faked a Test Log, Then Trusted It: The Provenance Gap
Lilian Weng's new survey on self-optimizing agent harnesses shows fake test logs and how provenance vanishes when trajectories get compressed into summaries.
Lessons from a Week Evaluating an AI PR Reviewer
Lessons from evaluating an AI PR review plugin: fixing the wrong skill, why risk classification matters, and how upstream evidence quality shapes review accuracy.
Python library verifies OpenAI's signed AI agent traffic (RFC 9421)
regent-httpsig is an open-source Python library that verifies and signs OpenAI-style AI agent HTTP traffic per RFC 9421 and Web Bot Auth drafts.
MCP Security: Trust Boundaries and the Attacks the Spec Won't Stop
A breakdown of MCP's four trust boundaries, stdio server risks, OAuth 2.1/PKCE/CIMD updates, and the confused-deputy attack class engineers must handle.
TutorMoments: Testing If AI Tutors Know When to Help or Hold Back
Allen AI's TutorMoments benchmark tests whether LLM tutors know when to scaffold and when to push students toward harder reasoning.
Text Diffusion vs Autoregressive Models: The Real GPU Cost Math
A grounded comparison of text diffusion and autoregressive LLMs on GPU utilization, latency, batching economics, and real-world enterprise costs.
Amdb: Single-Binary Local Code Context MCP Server in Rust
Amdb is a single Rust binary MCP server offering fully local graph+vector code context retrieval, built for air-gapped and regulated environments.