2026年9月3日に開催されたイベント「Bet AI Day 2026」における登壇資料です。
■ 概要
世はまさに大AIエージェント時代!!!私たちは、プロダクトを通したAIエージェントの社会実装と、社内利用を通した私たち自身への実装を両面で進めています。この発表では、主に社内利用のためのプラ…
Changes to SourceHut's terms of service regarding LLMs
sourcehut is a network of useful open source tools for software project maintainers and collaborators, including git repos, bug tracking, continuous integration, and mailing lists.
builderz-labs/mission-control: Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes.
Self-hosted control plane for AI agents: dispatch tasks, review runs, track spend, and operate OpenClaw, Claude Code, Codex, and other runtimes. - builderz-labs/mission-control
Project HydraFusion: Frontier quality via multi-model orchestration
In controlled offline evaluations, HydraFusion’s selective coding workflows matched or exceeded the evaluated Opus 5 baseline while reducing estimated cost.
esperanza-volkov/confdiff: Semantic, format-aware diff for config & structured-data files (JSON, YAML, TOML, INI, .env, .properties, CSV, XML). See what actually changed — keys and values, not text noise.
Semantic, format-aware diff for config & structured-data files (JSON, YAML, TOML, INI, .env, .properties, CSV, XML). See what actually changed — keys and values, not text noise. - esperanza-vol...
How to Deploy a TanStack Start app to Vercel | Vercel Knowledge Base
Deploy a TanStack Start app to Vercel with the Nitro Vite plugin. Covers Git and CLI deployment, Fluid compute defaults, and framework detection fixes.
A shared, self-pruning build cache for Rust. Keep using Cargo, reuse compilations across worktrees, and run builds together without overwhelming your machine.
ArchSpec: Executable Architecture Specs for Ruby and Rails
ArchSpec turns your architecture into an executable spec: declare components and boundaries in one Ruby file, and every change gets checked, whether a person or an agent wrote it.
Frontier LLMs are much better and dramatically faster than I am at finding and fixing bugs. If you are not asking them to debug your code and review your bugs, you are doing it wrong.
A thread of Claude wins.
(No longer at Google, btw.)
[contains quote post or other embedded content]