We’re bringing Codex and ChatGPT together in one desktop app. The same powerful coding agent, now alongside ChatGPT Work, with new coding workflows, a new Chrome extension, revamped in-app browser, and faster Computer Use powered by GPT-5.6.

Day 9/ We've rolled out optimizations to how we store state on disk for the chatgpt & codex desktop app that should reduce the amount stored on disk by 60%. Small ship but we've heard enough feedback about power users running out of disk space.

sharing a recent improvement in my harness customization I built with @pidotdev this may not be common problem at first, but it appears when your Pi setup starts accumulating a lot of skills, extensions, tools, and instructions e.g. Ponytail is useful when I’m coding, but not when I’m doing research. subagents are useful (still experimenting), but unnecessary when I only want a summary this felt particularly wrong in Pi because its minimal core is one of its biggest strengths, while my configuration was slowly moving in the opposite direction I spent weeks experimenting with Hermes style (or Grok bots style atp) agent profiles. separate configuration directories, separate agents, separate session stores eventually I realized profiles were the wrong abstraction Pi already separates global resources from trusted project resources. but its SDK resource loader also lets integrations control resources and instructions for individual sessions this was useful to create a pool-and-preset architecture where: - I can keep a large global pool of skills, extensions, and packages to choose from - I can create presets with only selected items, so a “research preset” can leave behind the coding stuff - I start each session with a preset that selects the exact global skills and extensions it needs - each preset also defines its active tools and instructions - trusted project resources, settings, and AGENTS.md still load normally - credentials, models, trust, settings, and session history remain shared so i change and inspect them only in one place - each session stores a snapshot of its preset, so it can resume with the same setup even if the preset later changes or gets deleted - unused global capabilities stay in the pool instead of entering every session’s active surface the result has been quite significant for my workflow: some task-specific presets reduced the starting system prompt by more than 35% more importantly, I can keep expanding my Pi setup without making every session carry all of it Pi’s own examples already include a simpler preset extension for models, thinking levels, tools, and instructions. the SDK makes it possible to take the same idea deeper into resource loading this is only a thin layer over infrastructure Pi already exposes, which is exactly why it works so well with its minimal-core and extensible philosophy sharing here in case anyone with a growing Pi setup is starting to face the same problem and curious about your solution.

Let me know when Opus 5.5 can do this

-nerf the usage and add a new $500 sub -done -make GPT 6.1 Sol slow as fuck -done -now make 6.1 Sol Ultrafast available only on the $500 sub

Ultrafast is rolling out today for GPT-6.1 Sol in the API, Codex, and ChatGPT Work. Near-Astra intelligence at up to 8x faster speeds than Sol Standard, so you can build as fast as the ideas come.

probably the most beautiful agent builder desktop app till date for mac no it’s not codex

Day 2.2/ OK this one is smaller, but we removed some friction for when building on the API. Happy building.

We’re in the AI agent “honeymoon period” Many are experiencing this using Grok Bot, Instinct, Muse, or Dots for the first time It feels amazing at first - “holy sh*t it just did this thing for me!” Everyone races to tell their friends, it’s the talk of social gatherings - “dude my Instinct got me a refund and all I did was text it” You start doing more and more with it, handing it over more data so it can be even better at helping you But then something happens - it misses an important detail, it screws up something you have to fix, it just feels not as good anymore Anyone who’s been using agents since the early OpenClaw and Hermes days knows this feeling The only question is what do you do? Do you “break up” with your agent and try another one, or do you keep going with the faith that it will get better with time (it will), or do you stop using agents and submit to the permanent underclass?