» Tag
llm
471 postsGigatoken: ~1000x faster tokenization than HuggingFace tokenizers
Gigatoken delivers ~1000x faster tokenization than HuggingFace tokenizers, offering GB/s throughput as a Rust-based drop-in replacement.
Stagehand: AI-Resolved Instructions Meet Deterministic Browser Automation
Stagehand pairs AI-resolved natural-language instructions with deterministic browser actions, surviving redesigns that break hardcoded selectors.
Review-Loop Engineering: Designing Real Human Oversight for Agent Loops
Why 'human in the loop' isn't real oversight for AI coding agents, and how review-loop engineering designs packets that expose gaps, not just green checks.
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.comAgentic AI ROI: Track Cost Per Accepted Outcome, Not Tokens
A five-step framework for measuring agentic AI ROI through cost per accepted outcome instead of raw token or infrastructure spend.
New Verification Gate Catches AI Models' Silent Omissions
A layered verification gate now catches AI models that silently skip claims they should surface, splitting omission into checkable failure states.
Thinking Machines Lab Ships Inkling: 975B-Param Open MoE, Tunable Reasoning
Thinking Machines Lab's 975B-param, 41B-active Inkling model offers encoder-free multimodality and a tunable reasoning-effort control.
We gated CI on six LLM eval frameworks — only two survived
An eight-month CI test of six LLM eval frameworks found only Promptfoo and DeepEval reliable as merge-queue gates, thanks to deterministic checks.
How do you actually test if an AI understands your codebase
A hands-on benchmark for testing whether an AI agent truly understands codebase structure, tested across thirteen real Ruby projects.
Colibri lets 744B-parameter GLM-5.2 run on just 25GB of RAM
Colibri is a single-file C engine that runs GLM-5.2's 744B MoE model on 25GB RAM with no GPU, streaming experts from NVMe on demand.
AI Agent Runtime Policy: Stop Dangerous Tool Calls Before They Execute
A runtime policy layer stops AI agents from calling dangerous tools in production: risk tiers, delegation scopes, and argument validation explained.