OpenAI's GPT-6 Astra Hits 99.9% on AGI Benchmarks and Runs Your Computer
OpenAI's new flagship saturates ARC-AGI-3 and FrontierMath Tier 4, drives a browser at 1.9x speed, and crosses the Critical cybersecurity threshold.
// Intelligence
Today in AI
A focused feed of models, agents, research and open-source releases for people building with AI.
Updated
Anthropic Wants Claude Code to Run TypeScript Middleware Like Express
Anthropic is proposing TypeScript Function Hooks for Claude Code, letting plugins deeply customize behavior with Express-style middleware and admin-controlled side effects.
Tencent Boosts Qwen3.6 Shell AI Scores 18 Points With Evolving Training Tasks
Tencent Hunyuan's environment evolution builds off-policy lineages of increasingly hard terminal tasks, boosting Qwen3.6 agents by up to 18 points on Terminal-Bench.
Warp's WarpBench Slashes Coding Agent Costs by 63% Using Your Own Codebase
Warp launches Factory Benchmarks, letting teams replay real agent runs to pick the best model per task and cut cost-per-PR from $80 to $30.
Google Research Maps 166,000 Neurons in a Fruit Fly Brain
Google Research and HHMI Janelia released a wiring diagram of 166,000 neurons and 125 million synapses spanning the male fruit fly brain and nerve cord.
FlashAttention-4's Direct-P Finally Unlocks 2.13x FP4 Speedup on NVIDIA GB200
A new attention kernel unlocks Blackwell's FP4 tensor cores for inference, hitting 2.13x BF16 forward throughput on GB200 while training stays partly in FP8.
Coding Agent Cost: Why Sessions Get Expensive
Keep the project on disk, treat lunch as a bill, and score the first finished tasks rather than dollars per million tokens
Runway's GWM Worlds 2 Streams Interactive AI Worlds at 720p in Real Time
Runway's new general world model streams continuous 720p video and 48kHz audio in real time, taking text prompts and camera input as you play.
Browser Use Lets AI Agents Shop and Pay Without Touching Your Card
Browser Use agents can now check out on any website using disposable single-use cards issued by Stripe Link, without ever seeing your real card number.
Krea Agents Opens Beta to Replace Node-Wiring With Plain English Prompts
Krea opens the beta for a new agent platform that turns natural-language prompts into finished visual assets, sitting on top of its existing creative suite.
Google DeepMind's WeatherNext 3 Ditches Physics Simulations for 60% Sharper Forecasts
Google DeepMind's new weather AI trains on raw satellite feeds and station data, delivering hourly 5km forecasts with up to 50% better rain accuracy.
Microsoft's MAI-Transcribe-2 Beats ElevenLabs on Accuracy at 54% Lower Price
Microsoft AI's new speech recognition model hits 2.0% word error rate at 411x real time speed for $1.67 per 1,000 minutes.
STAIR Beats Every RAG Baseline by Reading Documents Like a Table of Contents
A new generative retriever leverages the table of contents to hit 82.6% Recall@1 on a fresh 18-book benchmark, with hallucinations under 0.05%.
Xiaohongshu's Self-GC Cuts Agent Token Costs by 20% Without Losing Critical Context
Xiaohongshu's Self-GC uses a planner LLM to fold, mask, or prune agent context, retaining critical details 84.85% of the time versus 54.55% for rule-based baselines.
Figure Bets $6B on NVIDIA Vera Rubin GPUs to Scale Humanoid Robots
Figure locks in a $3.5B compute commitment scaling past $6B, targeting up to 100,000 Vera Rubin GPUs to train its Helix humanoid AI.
Qwen's E-Commerce Bench Exposes How Badly AI Agents Fail at Running a Business
A new 365-day simulation drops LLM agents into a deterministic marketplace with ¥100,000, real supplier data, and fraudsters, and no model wins everything.
Researchers Crack Open GPT-OSS-20b to Find Hidden Symbol Systems Inside
An 8-year interpretability project shows that LLM representations can be closely approximated by symbolic role-filler structures, enabling precise behavioral edits.
Alibaba's zvec-grep Gives Coding Agents One Search Layer to Replace Endless Grep Loops
Alibaba's Zvec team open-sourced zg, a local-first CLI that fuses ripgrep, BM25, and vector search into one interface for humans and coding agents.
ComfyUI Extension Lets MiniMax H3 Chain Clips With 0.95 Audio Continuity
A ComfyUI custom node makes MiniMax H3 clips chain seamlessly by carrying motion and the exact audio waveform across cuts.
Cursor Lets Enterprise Teams Run AI Coding Agents on Their own Servers
Cursor now lets teams run cloud coding agents on their own infrastructure or partnered sandbox providers, with auto-scaling worker pools.
Artificial Analysis Rebuilds Its Image Editing Arena Across 17 Specialized Categories
Artificial Analysis rebuilt its Image Editing Arena with a two-axis taxonomy of editing actions and use cases, revealing which model wins each specific task.
Perplexity's Lily Beats MLX-LM by 1.35x Running Qwen3.6 on Apple Silicon
Perplexity open-sources Lily, a Metal-based inference engine tuned for Qwen3.6-35B-A3B that beats MLX-LM by 1.23x prefill and 1.35x decode on M5 Max.
Meta's Muse Spark 1.3 Cuts Tool Calls 20% and Stops Agents From Hallucinating
Meta's latest agentic model trims tool calls by 20 percent and tokens by 25 percent while learning when to ask for help.
Anthropic's Claude Blueprint Boosts Retailer Carts by 35% With Shopping Agents
Anthropic open-sources a full commerce agent blueprint with shopping and merchant reference implementations, plus architectural guidance from production deployments driving 35% larger carts.
No stories match these filters.