
Karpathy builds a video platform over a weekend with Claude
Andrej Karpathy built HackerTube in a weekend with Claude. What it says about development speed with coding agents.
220 artigos por Marcelo Santiago

Andrej Karpathy built HackerTube in a weekend with Claude. What it says about development speed with coding agents.

Inkling 2 Small dropped 316 swear words across 2,655 benchmark runs. What this reveals about reasoning loops and how we read benchmarks.

Kilo Code is an open source coding agent for VS Code, JetBrains and CLI, with more than 500 models and provider direct pricing.

Turing Award winner Rich Sutton reinforces that raw compute is not enough for intelligence and calls for new methods, continuous learning and world models.

AI models catch a good portion of other agents' misbehavior, but they generate a lot of false alarms. See the numbers from Andy Hall's study.

Researchers built a code agent benchmark based on real user requests. Even the best model fully completes only 26.4% of tasks. See the numbers.

OpenMOSS published MOSS-Live on November 7, 2026, a full-duplex system that keeps the conversation flowing while the assistant responds and runs tasks in the background.

ONESTRUCTION published on November 7, 2026 a ranking of 20 AI models across five real world construction work axes. Claude Opus 5.5 led with 73.7 points.

Box and Nvidia announce Box Context Retrieval, a semantic search engine powered by Nemotron that turns enterprise content into knowledge for AI agents.

Palo Alto Networks is in talks to acquire Clutch Security, an AI agent credential security startup, for US$500 million.

Startup Underdog launched Woof, a 32 MB voice model that runs in the browser without internet and is open for download.

Anthropic launched Personal Finance in Claude: link bank accounts and ask about your money with read-only access.
In-depth technical curation: agentic architectures, real token benchmarks, MCP servers and open-source tools in your inbox and on the blog.