LinearUncle (@LinearUncle)

This is now fixed along with the latest release of Codex! Make sure to upgrade your codex installation to the latest version via npm or bash installer Thanks again to all of you for raising this issue and to the goated (jif) codex team

alright it seems people are losing their shit about zai glm being good. it’s been a not to open secret that the best hyper token burning engineers for last six months have been doing statsarb in this window of opportunity whilst western companies have been locking in with either openai or anthropic. the glm models are really fantastic but they are like an autistic german. black and white thinking and high precision. whereas opus/fable are great for painting colours/figuring out with gaps of meaning when under specification of prompts. here’s how you should be using it. use another model (ie gemini) which excels at painting to create the prompts used for generation the prompt which is then put into glm. for those similar with Amp’s oracle pattern. it’s that. register another model in as a tool within GLM itself for quality of living benefits.

🤗 MOSS-TTS-Local Transformer v1.5 is now open source. Built with a pure autoregressive Audio Tokenizer + LLM paradigm: >MOSS-Audio-Tokenizer-v2, 2B params >Qwen3-4B backbone >Native 48 kHz stereo audio >Streaming output with theoretical sub-100 ms TTFT >Zero-shot voice cloning >Inline [pause] control >🇺🇸 🇯🇵 🇰🇷 31 language synthesis >SGLang-Omni Day0 support 🎉 @sgl_project @lmsysorg Designed for voice agents, digital humans, game NPCs, audiobooks, and real-time speech generation. 👇

Alrighty, everything is ready 😎 here’s an unofficial “2x Codex limits” promo from my side for you all. meet DevSpace — an MCP connector app that turns ChatGPT into Codex. npm install -g @waishnav/devspace After installing, tunnel the MCP server over the internet and enjoy 2x limits. You can use GPT-5.5 Pro, xHigh, or High for planning, then hand off the task to your local Codex/pi/opencode/cursor/claude code instance. Or you can just use it for reviewing code written by other local coding agents Go ahead, experiment with different workflows, and keep the feedback coming on GitHub Issues or in my DMs And let’s thank OpenAI for being so generous by giving us separate ChatGPT and Codex limits and by being so chill around this MCP :) Please use it sparingly, only when you run out of limits. Don’t overuse it — in the end, they do have a button to stop it 🙂

introducing pi-dynamic-workflows This is probably going to be a bigger token burner than pi-goal, BUT, dynamic workflows is the first implementation of subagents that i don't hate, mainly because it's "code mode" for subagents. agent writes a js-based workflow DSL into a dedicated tool, engine parses the workflow code and runs it. the dsl implements some primitives for the agent (agent(), parallel(), pipeline(), phase() and log()) to keep it as simple as possible. now available in @badlogicgames pi! pi install npm:pi-dynamic-workflows