GPT-5.4 Pro became the first model to solve a researcher-level open problem in FrontierMath, a benchmark managed by Epoch AI. Claude Opus 4.6 and Gemini 3.1 Pro later solved it as well.
Changes from v1 to v2 of Kana Chat, an AI agent built around official CLI wrappers. Covers dual-model router, Heartbeat memory, planner mode, image input, speech transcription, PWA push notifications, and the lessons learned from a month of daily use.
An AI system that automatically reviews Linux kernel patches. Detected 53.6% of known bugs that passed human review. Rust implementation supports both Gemini and Claude.
Design and implementation of Kana Chat, a personal AI agent system that wraps official CLIs. Covers the tmux bridge, context isolation, and tool approval gate that make it safe to run in your own environment.
Gemini auto-generates images when you only ask about one or request a text prompt. The Saved info rule that stops it, a conversation-level fix, and where Google's fixes currently stand.
The Web Speech API + Gemini + VOICEVOX setup is complete — an AI character you can actually have a voice conversation with. Key implementation notes and impressions.
Testing the image generation features of Flow, now available in Google AI Pro. Findings on the He/She pronoun issue, the effectiveness of natural English prompts, and how to use Flow vs Gem.
