I gave codex a markdown to keep track of progress and let it chirp away on a massive linter debt, and it worked all night and fixed around ~6000 linter/type issues. (it would stop but I queued a massive amount of continue's to keep it working) Part of my prompt was to google whenever it's stuck and always update the tracker file when it learn sth new. This seems to have worked... it's still working.

New: @cartesia_ai Sonic-3 TTS is now available on Layercode 🔥 The fastest and most expressive production-ready TTS model — with 90ms model latency and 190ms end-to-end. How is Sonic-3 different to other TTS models? 👇

wow, codex CLI worked on a problem with this feature uninterrupted for over 1.5hrs and actually solved it 🤯 pretty incredible @embirico @OpenAICodexCli @thsottiaux @markerdmann @fouadmatin

Inworld TTS 1 Max is the new leader on the Artificial Analysis Speech Arena Leaderboard, surpassing MiniMax’s Speech-02 series and OpenAI’s TTS-1 series The Artificial Analysis Speech Arena ranks leading Text to Speech models based on human preferences. In the arena, users compare two pieces of generated speech side by side and select their preferred output without knowing which models created them. The speech arena includes prompts across four real-world categories of prompts: Customer Service, Knowledge Sharing, Digital Assistants, and Entertainment. Inworld TTS 1 Max and Inworld TTS 1 both support 12 languages including English, Spanish, French, Korean, and Chinese, and voice cloning from 2-15 seconds of audio. Inworld TTS 1 processes ~153 characters per second of generation time on average, with the larger model, Inworld TTS 1 Max processing ~69 characters on average. Both models also support voice tags, allowing users to add emotion, delivery style, and non-verbal sounds, such as “whispering”, “cough”, and “surprised”. Both TTS-1 and TTS-1-Max are transformer-based, autoregressive models employing LLaMA-3.2-1B and LLaMA-3.1-8B respectively as their SpeechLM backbones. See the leading models in the Speech Arena, and listen to sample clips below 🎧

Codex has transformed how OpenAI builds over the last few months. Have some great upcoming models too. Amazing work by the team!

New: @DeepgramAI Flux is available on Layercode. Flux is the first STT model built specifically for voice agents. Even better: We run Flux at the network edge ⚡ Layercode voice agents process audio in sub-50ms and take full advantage of Flux's smart turn-taking to respond with human-like timing to users anywhere in the world.

Best stack I've used for vibe coding is not React with Tailwind. It's Hono with server-side rendered pages. I like to use server-side JSX templating. With plain or vanilla CSS, and when some client-side interactivity is required, either reach for HTMX or vanilla JavaScript. The reason this works so well: LLMs know vanilla JavaScript and CSS better than anything else. Frameworks like React or Tailwind CSS just add another layer of complexity that the LLM has to translate from to get to what you want. Layout issues and other problems I had with a more modern stack are gone now.