Holo3-35B-A3B
H Company's open-weight sparse MoE vision-language model purpose-built for desktop computer use, scoring 82.6% on OSWorld-Verified with only 3B active parameters.
Articles Tagged "AI Agents"
Best AI for Web Browsing and Computer Use - July 2026
Claude Fable 5 leads OSWorld-Verified at 85% after its 19-day US suspension ended July 1 - Holo3 open-source at 82.6% and Claude Sonnet 5 at $2/M tokens reshape the value calculus.
Gemini Spark Gains Mac File Access and MCP Support
Google's Gemini Spark agent is now in beta on macOS with local file system access, MCP server support, and real-time topic monitoring - but only for $99/month AI Ultra subscribers.
Agent Phase Collapse, Reasoning Exits, Preference Gaps
Three new arXiv papers map capability cliffs in agent world models, the narrow benefit of learned reasoning stops, and a 56% accuracy ceiling when agents help users build preferences.
Chatbot Arena Elo Rankings: Who Wins the Human Vote?
Updated July 2026 Chatbot Arena Elo rankings from Arena.ai: 7M+ votes across 368 models, Claude Opus 4.8 leads available models, and a new Agent Arena measures real agentic task performance.
AWS Bets $1B to Embed AI Engineers at Client Sites
Amazon's new Forward Deployed Engineering unit places AI specialists inside enterprise clients to build and ship agentic systems in weeks, following similar programs already launched by OpenAI and Anthropic.
Agent Languages, Sampling Ceilings, and Abstention
Three new papers on agents inventing symbolic languages to cut reasoning tokens by 3-6x, sampling ceilings that waste inference compute, and context-engineering to double agentic abstention rates.
Claude Sonnet 5 Is Anthropic's New Agentic Default
Anthropic's Claude Sonnet 5 becomes the default model across all plans, promising near-Opus agentic performance at a third less than Sonnet 4.6's standard price.
How to Use AI for Event Planning - A Beginner's Guide
A practical guide to using AI tools like ChatGPT and Claude for every stage of event planning, from concept to post-event follow-up.
Tandem Training, World Models, and Efficient Agents
Three new arXiv papers on making RL reasoning legible across models, fixing broken world model latent states, and training small agents to beat their teachers.
General Intuition Raises $320M to Train AI on Gameplay
General Intuition raised $320 million at a $2.3 billion valuation on the bet that billions of hours of video game footage - with action labels - can train AI agents that operate in the real world.
Quantization's Hidden Tax, Cliff Tokens, Smarter Memory
Three new arXiv papers reveal hidden costs in quantized reasoning models, single-token failure triggers, and a new framework that cuts agent memory errors by up to 79%.
