⚡️Jag Valaiyapathy⚡️

283 posts

⚡️Jag Valaiyapathy⚡️ banner
⚡️Jag Valaiyapathy⚡️

⚡️Jag Valaiyapathy⚡️

@jaghub

Senior Forward Deployed Engineer (FDE), Salesforce CTA

Richmond, VA Beigetreten Mart 2011
7.5K Folgt775 Follower
Can.
Can.@lumendriada·
@jaghub @andrewqu kitty protocol supported under experimental settings! #kitty-graphics" target="_blank" rel="nofollow noopener">herdr.dev/docs/configura…
English
1
0
1
75
Andrew Qu
Andrew Qu@andrewqu·
first week in years I haven't reached for tmux completely switched to herdr by @lumendriada — the ergonomics, the information architecture, the hackability all just click my biggest gripe with every coding agent orchestrator I've tried (and I've tried 10+): if you're building a pretty UI - they're sluggish, you need to "import projects", not as snappy as tui tools, and the setup isn't portable to remote machines if you're building a multi terminal manager - agent runs get buried (i finish a task, walk away, come back, and now i'm scrolling through panes trying to find where it happened), and they still somehow make the UI around the terminal feel sluggish herdr is the best mix of: - native tui launched from terminal, no separate desktop app - dedicated spaces + agents view - finished session? one jump. no need to scan - super easy to extend new features (I forked the main project to build full screen panes, ctrl+k quick switcher, navigation mode) - works with ssh for remote coding agents - i can get pi to spin up multiple new herdr panes and visually see the new agent runs haven't felt this level of flow state in a tool since early cursor (not sponsored, but wish I was)
Andrew Qu tweet media
English
11
2
101
9.3K
⚡️Jag Valaiyapathy⚡️
@lumendriada @andrewqu I love herdr. The only thing preventing me is support for first class kitty protocol for image rendering. My agent workflows post screenshots of browser pages as part of verification and I would love not to context switch to a browser to verify
English
1
0
1
66
Can.
Can.@lumendriada·
@andrewqu thank you, and great to see the exact reasons i built herdr resonate with you as well! also context switcher will be included into herdr with the next release (though will steal some parts of the design from yours you hehe)
English
1
0
5
499
⚡️Jag Valaiyapathy⚡️
Feedback for @xai Grok CLI Unable to render images in terminal. I am using Ghostty and it supports kitty protocol.
⚡️Jag Valaiyapathy⚡️ tweet media
English
0
0
1
47
skcd
skcd@skcd42·
Grok-code-fast-1 is now out and available for everyone to use 🚀🏎️💨 When I joined the coding team, the team was just 3 people and we very quickly built a model which was SOTA on SWEBench. But as things go, in the real world benchmarks matter less. Over the last few months we approached the modelling + data + infra perspective from a different lens, putting developers and users first over everything else. This required us to tune the data recipe, get the infra in place to do a lot of rollouts and create a set of grounded evals which was powered by both human judgement and an in-house auto-evaluation framework that captured real world usability. This is the first model of many in the grok coding family, we are going to make quick iterations and improve the model performance over time. We thrive on your feedback, please share your unfiltered and honest thoughts so we can keep pushing new boundaries for agentic coding
xAI@xai

Introducing Grok Code Fast 1, a speedy and economical reasoning model that excels at agentic coding. Now available for free on GitHub Copilot, Cursor, Cline, Kilo Code, Roo Code, opencode, and Windsurf. x.ai/news/grok-code…

English
238
130
1.7K
6.6M
Mario Zechner
Mario Zechner@badlogicgames·
OSS is just such a nice past time. You meet so many smart and nice people. Recommended!
Mario Zechner tweet media
English
8
0
68
4.9K
Eric Jiang
Eric Jiang@veggie_eric·
When training Grok 4.3, we spoke directly with devs and businesses to understand what they actually needed: a model that’s fast, affordable, and great at tool calling. The result is a daily driver that doesn't just look good on random benchmarks, but is actually useful in the real world. 💰 $1.25 in / $2.50 out ⚡️ 100 tokens / second 📖 1 million context window Try it through Hermes Agent or direct through the xAI API!
Eric Jiang tweet media
English
359
905
3.4K
657.5K
⚡️Jag Valaiyapathy⚡️
Just got 200$ subscription from @OpenAI and downgraded @AnthropicAI subscription from 200$ to 20$. Why? I am not allowed to take my subscription plan to Pi harness. It’s a shame, Opus 4.6 is a good model @bcherny
English
0
0
1
197
⚡️Jag Valaiyapathy⚡️
@badlogicgames I have love hate relationship with tmux because it does not support kitty protocol to render beautiful images as part of agent workflow
English
0
0
0
398
Mario Zechner
Mario Zechner@badlogicgames·
tmux is love, tmux is life.
Mario Zechner tweet media
English
10
3
200
25.6K
Nico Bailon
Nico Bailon@nicopreme·
Major shout to @thdxr and the team at @opencode for sponsoring my OSS work! Absolutely blown away and grateful beyond words. Pi + opencode 🤝
Nico Bailon tweet media
English
17
5
314
33.3K