Product. Tech. Open Source. Life.
🇮🇳
Joined February 2008
- Tweets4.2K
- Following510
- Followers371
- Likes3.8K
One frustrating limitation of Claude Code Remote Control on mobile: you can’t create new sessions from a coordinator session. You have to go back to your computer to start them.
It defeats part of the purpose of remote control. If I’m coordinating agents from my phone, I should be able to spin up new sessions too.
Uninstalled Orca today and moved fully to the new Herdr desktop app.
Orca served me well and the team ships fast, so no complaints there. What tipped it for me was how each tool tracks agents.
Orca puts hooks into every agent's config. When I cleaned up, I found 13 in Claude Code, 9 in Codex, 8 in Devin and a plugin in Hermes, all running on every prompt and tool call.
Herdr reads agent status from the terminal itself. My Claude and Codex configs are clean again: no hooks, nothing running between me and the agent.
What I like most:
• Agents can drive the workspace through a small CLI. Claude opens a pane next to itself and leaves a command at my prompt (sudo installs, prod releases) without running it. I just press Enter.
• Spaces, tabs and panes per project, with Claude and Codex side by side
• Less setup and fewer moving parts
I still use the Claude and Codex desktop apps too, but for terminal agent work Herdr is home now.
This was much needed on Linux. Codex and Claude lack computer use on Linux.
Deependra Solanky retweeted
1/ Excited to announce our new company Particle
This is our first step in a series of models focused on developers.
With particle-1, we focused on token efficiency and managed to keep parity in performance while using ~45% fewer tokens.
Live now: particle.ai
Testing GPT-6.1 Terra on the Plus plan.
Not sure about token usage compared to Sol yet, but overall it's very fast and browser use feels super snappy. Haven't tested it on coding since I already have Claude Max for that.
Deependra Solanky retweeted
GPT-6.1 Terra: delivering fast and capable computer use at a lower price.
GPT-6.1 Terra understands what’s on screen, takes action across apps, writes naturally, and is a more capable model for your whole workday with the efficiency to take on more of it.
🤖 Made with AI
Stopped using Claude Code Projects and moved back to a Chief of Staff workflow on my local machine.
Claude Projects asks for too many permissions, interrupts often, and switching back and forth between threads is cumbersome.
Hope these get fixed once it's out of beta.
Now I have to decide whether to keep Codex by downgrading to the $20 Plus plan or continue with Devin at $20.
Devin is good, but I haven't even used the free SWE-2 in days. Its real appeal for me is Cloud, where $20 isn't enough. For CLI/Desktop, Claude already covers my needs.
Codex seems more useful as a backup, especially for reviewing Claude's work.
Just got access to Claude Code Projects. Watching a coordinator thread orchestrate parallel threads in real time is a massive workflow upgrade. A few rough edges here and there, but overall a seriously useful addition.
I still have a week left on my Codex subscription, with 3 banked resets, and Devin SWE-2 is free too.
But since switching to Claude, I haven’t felt the need to use either. Claude’s usage limits have been more than enough for my work so far.
After a lot of thought, I finally subscribed to Claude Max 20× and decided not to renew my Codex Pro 20× plan.
Codex is still a great product, and the recent usage resets and improvements are welcome. But I just couldn't resist moving to Opus 5.5.
Let's see how this change works out over the next few weeks.
After a lot of thought, I finally subscribed to Claude Max 20× and decided not to renew my Codex Pro 20× plan.
Codex is still a great product, and the recent usage resets and improvements are welcome. But I just couldn't resist moving to Opus 5.5.
Let's see how this change works out over the next few weeks.
SWE-2 is now free in Devin for October month. But for Desktop/CLI only. I wish it would have been for Cloud as well.
Yesterday I posted that Sol 6.1 is super slow but today it is working fine. Speed has improved definitely, can't say temporary or permanent?
Day 11/
We've landed a series of changes and more compute to very significantly decrease the occurrence of the disruptive "Selected model is at capacity. Please try a different model". When it does happen, it should also eventually just continue by itself and not just block on it.
Let us know if you still see it out there in the wild and we'll take a look.
Unified my Cursor and X accounts on the Plus plan today, only to find Auto-Review disabled in settings.
Turns out it relies on third-party models (Gemini 3.5 Flash Lite / Claude 4.5 Haiku) that aren't included in Plus. Without Auto-Review, Cursor is honestly barely usable.
From last 2 hours Sol 6.1 is working on minor bug fixes and not a single PR created. Super slow… Seriously thinking to switch to Claude now…
Codex Desktop on Linux doesn't yet have built-in computer use, so I decided to experiment with Cua @trycua .
Using Cua Driver, I got Codex to detect application windows, capture screenshots, click through settings, and interact with the UI.
Getting it working on Ubuntu took some effort. GNOME/Wayland permissions, accessibility access, and window targeting needed attention, but the results have been encouraging.
It's still experimental, with a few reliability issues to resolve. But getting Codex to operate native Linux apps without disabling security protections is a good step forward.
Hopefully, native computer use will eventually come to Codex Desktop on Linux too.
github.com/trycua/cua
