Archive
Claude Worktree Guide: Parallel Agents in Claude Code, Codex and Cursor
Octomind — Claude worktree setup for real projects: run Claude Code, Codex and Cursor agents in parallel git worktrees without colliding .env files, ports or databases.
Welcome to the era of embodied AI: Introducing AA-Robotics v0.1
artificialanalysis.ai — We are launching AA-Robotics v0.1, our research preview that measures frontier language model performance on understanding, planning, and acting in the physical world. In v0.1, each model is given control of a 6-axis robot arm (5 joints and a gripper) and a simple objective. We’re releasing results for our first eight tasks today.
Today, we’re introducing the Responses API in public preview, made for building agents on Mistral.
Engineers are shipping faster, so we made our CI self-driving to keep up
posthog.com — PostHog ships code at a rapid pace, and that pace has only accelerated in recent months due to LLM adoption. We went from merging 1,354 PRs in October…
The New Security Agenda
a16z.news — What CISOs told us about AI, budgets, and the priorities shaping 2027.
Kodiak AI and DTL to Deploy 75 Unsupervised Autonomous Trucks
kodiak.ai — Kodiak AI and DTL Transport sign a binding agreement to deploy 75 driverless trucks on Sun Belt interstate routes under Kodiak’s Driver-As-A-Service model.
No quarantine for Bedrock Mantle
Plerion — AWS's compromised key quarantine policy denies five bedrock actions, but Project Mantle's bedrock-mantle:CreateInference is not one of them. A look at the LLMjacking gap and how to detect it.
First impressions of Gemini 4 Carbon’s preview by @GoogleDeepmind are in.
How OpenRouter rebuilt provider routing for better, faster inference
OpenRouter Blog — OpenRouter's new default provider routing scores each provider on effective price, throughput, reliability, availability, and output quality for every request instead of ranking mostly by prompt token price. Measured with a switchback experiment against the old router.
MAI-Image keeps climbing!
NVIDIA Nemotron 3.5 Transcribe and Granary v2: Intelligent Multilingual Transcription You Can Prompt and Adapt
huggingface.co — A Blog post by NVIDIA on Hugging Face
Build specialized multimodal models with LFM3
huggingface.co — A Blog post by Liquid AI on Hugging Face
Code mode vs tool calling: a 5,276-run benchmark
pydantic.dev — Code mode vs tool calling across 5,276 graded Pydantic AI runs on eight models: on long tasks it was 58% cheaper, 51% faster and 16 points more often right.
Claude Code is the best Linux tech support I've ever had
XDA — This would have taken me hours to figure out
Decisions for a penny: introducing joey-1, our fastest decision model
Baseten — A week ago we shipped mammoth-1 (27B) and elephant-1 (9B), the #1-ranked decision models. Today we’re adding joey-1, our fastest, cheapest 2B decision model.
Granola crunches up a dictation feature to compete with Wispr
TechCrunch — Uno reverse! After Wispr added meeting notes to its dictation app, Granola is adding dictation to its meeting notetaker. The voice AI wars are getting interesting.
OneQode leases 14MW from AdaniConneX in India
datacenterdynamics.com — AI cloud company's first deployment in India, more planned
Ex-Palantir execs launch Dream with $17M from a16z to build AI world models for construction
TechCrunch — rained on 100 million square feet of building permits, dream wants to disrupt Autodesk with AI.
/teardown by @jakubkrehel now available as a skill in Perplexity Computer.
Dismiss email signup
Subscribe to 
The top AI news in your email delivered each morning. Choose categories