ElevenLabs' Eleven v4 won three of five head-to-head text-to-speech tests against Google's Gemini 3.8 Flash TTS, but Gemini won the voice-cloning test by preserving the tester's South African accent w…
Boris Cherny, creator of Claude Code, says he no longer prompts Claude directly, instead using loops that prompt the agent and figure out what to do. Anthropic's research supports this shift, where ag…
A technical writing company tested Anthropic's Opus 4.8 model as an agentic editor for code-heavy articles, finding that while the AI could flag structural and logical issues, its output still exhibit…
Z.ai released GLM-5.2, an open-weights AI model under an MIT license, positioning it between Claude Opus 4.7 and 4.8 in performance while costing less than a fifth of Opus on output tokens. The model …
Developers built Otto, a local voice assistant that routes meeting audio through existing devices without joining the call, using Deepgram's streaming transcription and text-to-speech APIs. The assist…
A developer built a personal AI agent called Al after finding existing options like OpenClaw too expensive and unpredictable. The agent runs on a remote server using Pi, OpenCode Go, Telegram, and oth…
FLUX.2 and Gemini 3.1 Flash produced the strongest character consistency across three tests comparing OpenAI, Gemini, Black Forest Labs, and Runway image generators. gpt-image-2 placed third and Runwa…
XAI's text-to-speech models outperformed OpenAI's in a blind comparison of six real-world scenarios, winning 20 out of 30 audio pairs and tying in six. In a separate realtime voice agent test for a ho…
A coding agent harness comparison published in May 2026 analyzed nine terminal coding tools — Claude Code, Codex, Amp, OpenCode, Gemini CLI, Pi, Command Code, Factory, and Aider — across open source s…