Chinese AI lab Moonshot AI announced Kimi K3 this morning, describing it as their "most capable model to date, with 2.8 trillion parameters". It's currently available via their website and API, but an open weight rele... Context & related coverage →
OpenWiki 0.2 generates codebase wikis in the OKF format, helping developers organize repo docs with metadata, changelogs, and agent-friendly retrieval. Context & related coverage →
Lattice quantum chromodynamics (LQCD) provides a first-principles framework for computing hadronic observables, but its practical use remains limited by the substantial expertise required to turn research motivation i... Context & related coverage →
The formation of political coalitions is a complex negotiation driven by both concrete policy objectives and deep-seated ideological convictions. While Large Language Models (LLMs) open new avenues for computational p... Context & related coverage →
We've been using a now-discontinued version of pi-mom from the pi monorepo for a few months now. Digby is a slackbot which you can also assign Linear issues to. It has a private (Sign In with Slack, locked to your tea... Context & related coverage →
Large language models are increasingly evolving from text generators into general agents capable of understanding user requests, invoking external tools, and completing complex tasks through interaction. However, exis... Context & related coverage →
/fork now copies your conversation into a new background session (its own row in claude agents ) while you keep working; the in-session subagent it used to l... · Added claude auto-mode reset to restore the default au... Context & related coverage →
Firefox in WebAssembly This is absurdly cool: Puter compiled Firefox to WebAssembly such that the whole browser runs in another browser. Here's my blog, running in Firefox, running in WebAssembly, running in Chrome: T... Context & related coverage →
Build custom AI agents in Fleet without code, then deploy them to Slack in one click. Give agents custom identities, use them in channels and threads, and keep work moving where your team already collaborates. Context & related coverage →
Predictive world models enable robots to plan by imagining the outcomes of their actions, but their value for control hinges on generating many rollouts quickly. This creates a bottleneck for diffusion-based world mod... Context & related coverage →