Pinned Tweet
I was drowning in terminals.
Six tmux sessions. Three agents running. Zero clarity on what was happening where.
Context-switching to fix a bug meant wasting minutes just remembering the state.
This wasn’t sustainable.
So I built Uxnan Desktop instead:
→ Right-click any Git worktree and launch any agent (Claude, Codex, Gemini, Pi, Zero, Antigravity…)
→ Watch sub-agents spawn and work live in their cards
→ Run multiple agents in isolated workspaces. No collisions, no “wrong directory” mistakes
→ Your machine stays light — we orchestrate the official CLIs, no heavy local models draining your resources
This is for developers who want to run serious AI agents without turning their laptop into a space heater.
What does your current multi-agent setup look like? How many terminals are open right now? Be honest 👇
Luis Gamas retweeted
We keep improving performance across Claude, and you may have noticed it starts responding sooner!
Claude Code now gzips the conversation it sends on every turn, so it reaches the model faster. Cloud sessions also start up as soon as you start typing.
Wow, it looks like I've been blocked by someone higher up, what could this mean? 🤔
It's interesting to discover this kind of thing, since I don't remember ever interacting with @athasdev
Well, this shouldn't be a problem when it comes to testing his new creation🤝
In response to the ZCode product security issues reported by the community, we have completed the necessary remediation and sincerely apologize to all our users.
We have open-sourced ZCode at github.com/zai-org/ZCode, placing the code under community scrutiny and making ZCode more open and transparent.
We sincerely thank the community developers who previously identified issues in ZCode. Going forward, we will establish an ongoing product security vulnerability reporting and response process. We welcome developers to continue reviewing ZCode and reporting potential issues, and we will provide rewards based on the severity of the issues reported.
With respect to the code data referenced by the community, we confirm that no such data is retained and that it has never been used for model training.
Following the remediation, we invited the China Academy of Information and Communications Technology (CAICT) and NSFOCUS to conduct security assessments. The results are as follows:
Through its technical assessment, CAICT confirmed that the zcode-prod Alibaba Cloud OSS bucket is in a zero-data state. Security remediation has been completed in the ZCode v3.14.0 client. The Repo Wiki feature has been removed, and the workflow for generating and uploading local repository snapshots has been disabled.
NSFOCUS confirmed that all data objects in the zcode-prod Alibaba Cloud OSS bucket, as well as the bucket itself, have been deleted. Remediation has been completed in the ZCode v3.14.0 client. The Repo Wiki entry point and the associated generation workflow have been removed, and no functional path capable of triggering the generation of local repository snapshots or transmitting local files externally was identified.
Once again, we sincerely apologize and welcome continued scrutiny from the community. The full security assessment report will be released soon.
Luis Gamas retweeted
#MithaTelaInivlcial ✌️
- Walley
@RajjAryaa
- Elegant For Kwgt 🎁
@ersteuomo
- Phatom Black
@lkn9x
- PulshScreens Mockup
@AndroidTools3
- Launcher
@SmartLauncher
#Android #Wallpepers #widgets #Icons
❤️ 🔄 💬
Thanks Anthropic!
We started Codex for OSS six months ago.
Today, we’re renewing the program with $100 Pro plans and doubling the number of grants (from 5,000 to 10,000) to reach more maintainers.
(If you received a grant previously, we encourage you to re-apply!)
openai.com/form/codex-for-os…
This is my quick question or request to find out if @t3dotcodes has or will have a way to retrieve sessions that were started outside of T3Code.
@theo @jullerino @maria_rcks
Call me crazy, but I really haven't found a great desktop app for working with AI agents that also has a good mobile app.
Luis Gamas retweeted
A good thing about having aged is that I feel that it’s been 20 years since I’ve pressed the reset button. Intrigued to see if I can find it tomorrow and dust it up
Is this the clear result of how they use the available tools?
The available and “functional” tools can produce such great and brilliant results, and at the same time yield unpleasant and messed-up results—but come on! Shouldn’t the people in charge at least be aware of what’s possible so they can get something… better?
Almost Immediate Availability
More good news: GLM-5.3’s weights will be released tomorrow.
huggingface.co/zai-org/GLM-5…
Luis Gamas retweeted
新版本的 pi 桌面端已经发布,本次主要优化了系统还有 UI 界面
- AI 思考球的优化
- 系统架构依赖的更新
欢迎大家来体验,并且报告 issue 👇
github.com/Chasen-Liao/pi-ag…
The growing wave of OpenAI—Codex—GPT is reaching its sustainable peak; the growth target they had hoped for has been met and far exceeded.
Soon, the millions of users who joined because of Tibo’s generous giveaways will no longer receive them, and a downward trend will begin.
The 5-hour limits will return for Plus accounts because the weekly allowance runs out too quickly on small accounts; it makes sense.
Tomorrow we will bring back the 5h limit for Plus accounts across ChatGPT Work and Codex. I had mentioned this a while ago, but then postponed it.
This is necessary as (a) the 5h limit allows us to smoothen the load on our compute, allowing to keep the plan generous in terms of weekly usage and (b) users on the Plus plan are relatively casual and new users, but then also just accidentally eat through their whole weeks usage and then are confused, making it not a great experience.
We are for the upcoming months keeping the 5h limit not enabled for Pro $100 and Pro $200 subscriptions.
I think these guys deserve an extra reset for announcing stuff like that 😯😅 After the reset and "the correction," Codex's overall consumption is still the same or even worse 👀
How could I spend 20% with Luna? That's not normal.

























