Agents should not edit blind.
Better lets them ask: “who worked on this file/symbol before, and is there a checkpoint I can reuse?”
Then parallel sessions compose into one release frontier.
Git import/export works today. Hosted sync coming soon.
github.com/logesh45/better-s…
79
Logesh R retweeted
Intended for emergency use only. Use of this feature will damage your vehicle and the Supercharger. Deliberate misuse will invoke additional penalties.
62
113
4,474
258,878
Logesh R retweeted
if you're job searching right now: choose the team, mission and approach that resonates most, and where you'll have the most fun.
not just the buzziest or apparent leader. with model advancements, products reinvent themselves every 3-6 months, so the leaderboard resets often.
if you're chasing hype, you'll be unhappy once you're (inevitably) out of the hype cycle.
26
60
1,312
193,879
having fun at work (and a lot of tokens) will fix you
i was super burnt out at my last job before i joined cursor and spacexai. i even thought that i was no longer cut out to be an engineer! but im happy to say that i'm no longer burnt out and in fact thriving thanks to how much fun im having
if you're job searching right now: choose the team, mission and approach that resonates most, and where you'll have the most fun.
not just the buzziest or apparent leader. with model advancements, products reinvent themselves every 3-6 months, so the leaderboard resets often.
if you're chasing hype, you'll be unhappy once you're (inevitably) out of the hype cycle.
122
81
3,135
175,217
Logesh R retweeted
LLM responses shouldn't be limited to plain text.
With the Jetpack Compose A2UI Renderer, you can seamlessly decode and render agent streams into native Android UI components with state management and theming built in.
Explore the docs & samples → goo.gle/3ToufoZ
7
41
468
43,093
Cursor + SpaceXAI: the fastest iterating team wins a16z.com/cursor-spacexai-the…
11
Logesh R retweeted
Some, especially. in the beginning to see if the direction is good. Rest has been well tested in prod by the team. Who reads all that code anymore?
10
4
201
18,238
Go poteto!
the Grok @Bot desktop app just got even faster! we shipped 53 perf fixes over the past few days:
• reconnecting after a flaky connection: 60s → 0.7s
• waking your laptop: 23s → 1s
• switching back to a bot's Computer view: 868ms → 27ms
• opening a chat with a long code block: 954ms → 228ms
• the Media tab no longer re-downloads every time: 137MB → 0.7MB
plus smoother sidebar animations, no more jumpy screenshot-heavy chats, and much lower memory usage while idle.
still more to improve!
8
Logesh R retweeted
Claude Opus 5.5 is now available in Cursor!
It's the new top model on CursorBench at 57.8% (Max) and costs 40% less per task than Opus 5.
268
199
4,705
523,909
Logesh R retweeted
Tesla, the only trillion-dollar company where memes don’t have to go through 10 rounds of committees before posting
6
29
1,459
100,373
Logesh R retweeted
To all the people calling me about our dogpatch cafe: we had a temp permit and it expired while we were waiting for our permanent one to get approved. Due to administrative error on our end, the dogpatch cafe is temporarily closed. The dogpatch cafe was mostly soft launched anyways, so we are excited to fully open soon! Our other four locations, including our Claude Lane cafe in SF, remain fully open, as they have for the duration of 2026.
46
18
406
194,861
Logesh R retweeted
So excited for tomorrow!
ALT Apple Fifth Avenue, wrapped in burgundy on the left and glacier on the right.
807
1,871
52,207
2,936,805
Logesh R retweeted
Here's a 45-second TL;DR on Jev.
I find the core idea beautifully simple, but the video made it really hard to understand.
Hope you find it helpful.
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI?
I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev
• 20-200x faster
• 40-400x cheaper (w/ output tokens free)
• Frontier composable intelligence optimized for decisions
AFAICT the shortest path to AI-based economic revolution
244
731
9,859
1,759,641