» Tag
llm
535 postsInside the New Agent Swarm: Coordination at 1,000 Commits/Sec
A deep dive into how a new AI agent swarm architecture uses planner-worker hierarchies and a custom VCS to coordinate work at 1,000 commits per second.
Study Finds AI Text Watermarks Fail Legal Evidence Standards
Study finds AI watermarking schemes KGW, Unigram, and SynthID fail Daubert legal criteria after simple paraphrase attacks strip out marks.
MoE Expert Streaming Runs a 120B-Parameter LLM on an Android Phone
An open-source Android app streams MoE experts from flash storage to run a 120B-parameter LLM on phone CPUs, with 30B models at usable speeds.
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.comSDABench: A New Benchmark Testing LLMs on Scientific Discovery
SDABench evaluates LLMs on six scientific capabilities beyond code execution, exposing major gaps in assumption selection and mechanistic reasoning.
AI Circuit Tutor That Can't Draw a Wrong Circuit
How digiwleea's AI circuit tutor uses netlist verification and simulation feedback to guarantee every generated circuit is provably correct.
A Multi-Agent AI Game Cost $1,847 in One Weekend — Here's Why
A two-agent AI game cost $1,847 in one weekend. Breakdown of why multi-agent LLM costs multiply, plus the fixes that cut expensive calls.
Why PDF Ingestion, Not the LLM, Broke a Banking RAG Chatbot
How PDF extraction, broken tables, OCR, and chunking issues nearly derailed a production banking RAG chatbot pipeline.
Open AI-Agent Incident Database Lists 32 Failures, Admits Its Gaps
ARE Incident Database catalogs 32 real AI agent failures mapped to OWASP ASI Top 10, with runnable repros and honestly flagged coverage gaps.
Local Model Showdown Round 9: Qwen 3.6, Nemotron, Qwythos Coding Test
Five LLMs face off on a real coding task via llama.cpp on an RTX 5090 in Round 9 of the Local Model Showdown series.
Does the Harness Come Before Pretraining? A Data Flywheel View
An analysis of how AI agent harness design and pretraining are interdependent, shaping data flywheels and model biases in coding agents.