Joined June 2026
- Tweets400
- Following740
- Followers25
- Likes3.7K
Ren retweeted
Evidently Figma does not understand the point of open protocols. xitter.cf/GayaniFigma/status/210…
Hey David, Gayani here from Figma. You're right that our remote MCP server only accepts clients on our supported list, and Pi isn't on it yet. You can see the current list in our MCP catalog at figma.com/mcp-catalog. If you'd like Pi considered for a future addition, please fill out this form: forms.gle/qSvUawwznWyoj8Go7.
Ren retweeted
This is how I work now. Actually it's how almost everyone at @every works. Every workstream has an ongoing thread in Codex. I never make one off chats and I never worry about compaction.
There's SO MANY THINGS OpenAI can do to make this better. A few ideas:
1. Folders. Let me group chats together
2. Emoji selector. It's a design bummer but it's visually so much more appealing and easier to find pinned threads
3. Remove the chat bubble icon ya'll just launched. Nothing in the UI should be repetitive like that IMO.
4. Enable me to fork convos much more easily. Those should be worktrees that live inside of each chat like a folder would work.
5. SHARED CHATS with easily forked convos that all have the same context. Killer feature and makes Codex multiplayer.
6. Make HQ a feature. It's my ongoing to-do list but it's just not built for chat. I need a kanban board or something that i can kickoff codex sessions from.
Ren retweeted
people of @pidotdev I have made your new favorite extension: lgtm
it allows pi to opens a super performant web view to annotate and review a git diff (or markdown plan).
pi will wait for you and will receive all your comments in JSON when you are done.
github.com/rendotdev/lgtm
Ren retweeted
lgtm now supports ssh into remote boxes and also "groups" of files which you agent can fill to help you review its work. Also fixed some bugs with the pi extension.
github.com/rendotdev/lgtm
Ren retweeted
How about a CLI called that your agents can call to request feedback, which opens in a browser. You hover -> auto-focus on the input -> write a comment. Rinse and repeat. When you're done, it has already saved all your comments in a JSON file with all the context for your agent.
Ren retweeted
Updates for Codex and ChatGPT Work users. No nerfing, only good stuff!
- We have landed inference optimizations and are passing down savings to all the subscriptions for GPT-5.6 Sol. That should result in around 10% more usage on its own.
- We noticed that by changing the context size limit in the product to 372k for GPT-5.6 Sol, up from 272k for GPT-5.5, it resulted in more usage being charged than intended. We have reverted to 272k and will work to roll back out to 372k in the days to come. You should notice that usage drains significantly less after this change.
- To understand where the extra usage was coming from, we ran some experiments where reasoning efforts were changed (referred to as juice values under the hood) and have reverted this.
- There is slightly more usage of multi-agent than intended in high and xhigh reasoning effort, we are fixing this going forward. Also fixing a small other thing we noticed with auto-review where we can be more efficient.
And we continue to have the 5h limit temporarily not apply. Enjoy the rest of the weekend!
OpenAI has reduced GPT-5.6 Sol's thinking budgets in an effort to make the model more efficient
They essentially bumped everyone's reasoning down by 1... so if you were running Sol Extra High, you now have to set it to Max to get the same effort
So we basically don't have Max reasoning anymore, how do you feel about these changes? 🤔
Ren retweeted
If you like this I think you’ll like rig as well
Similar idea but with 100% type safety for agents as well a prebaked tools for content collections, SQLite, kv store, cache with stale while revalidate, crons and minimalist foot print.
github.com/rendotdev/rig
Ren retweeted
1 Year of Research coming to an end. 8 Months seeing no results, Almost quitting twice. November/December of last year finally seeing a very narrow path to a universal 2x perf improvement on every modern JS parser which would take me another 4 months to build.
This will land in oxc_parser fairly soon speeding up OXLint, OXFmt, Vite, Rolldown, Deno (oxc consumer) almost immediately.
In the long term it's likely that it will land in V8/SpiderMonkey/Bun/JavascriptCore/Typescript/+ Every other JS parser implementation
The wins come from a few key elements, obviously 1 novel "SIMD For Context Sensitive Languages" the other key elements take it from a 20% win e2e to a 80-200% win (99% of files will see a 80-100% perf improvement).
These key elements translate to any AST design and thus will speed up not only all JS tooling but every major browser when complete.
Ren retweeted
Sharing a lil' wider. I made an extension for Pi that lets you communicate with a running instance of pi via discord, telegram, email and web hooks
pi.dev/packages/pi-chaos-rel…
It does proxy all messages through my relay server, but the server is oss so you can host your own
Ren retweeted
herdr isn't an app. that's by design.
it's a runtime for your coding agents. it owns your terminals, your agents, their state, and lets you drive them from anywhere.
that was the idea from day one. but people started running with it faster than we could give them a real way to.
even without any official support, they're already building on top of it. web, ios, dashboards. their own idea of what a client even is.
so here's a sneak peek 👇
it's native api support in the runtime, the thing we've been building so you can.
the tui will always be the first citizen. but soon you'll be able to build your own client on top of herdr, on the same protocol we do.
