
Founder @trytalentos - Multiplayer AI for teams, Prev @frontiertower @buildmyanmar
San Francisco, CA
Joined August 2019
- Tweets5.5K
- Following3.7K
- Followers953
- Likes26.4K
Pinned Tweet
What a way to wrap up SF Tech Week! 🔥
Honored to share the stage with these legends:
Court Lorenzini, DocuSign co-founder & founding CEO
Lindsey Simon , VP of Engineering at Vercel
Leo Kayali, founder & CEO of INVO Station, building flying cars!
Huge thanks to everyone who made it happen.
More next year! 🙌
🤖 Made with AI
I wouldnt worry
they would be back within a heartbeat lol
this stunt caused them to lost half their users to @theo (t3code) and @mitchellh (rex) already 😭
24
Your Chatgpt can now coordinate with your Claude without ever leaving it !
All your skills, memory, routines, and files in one place, accessible to every agent.
Finally, a portable company harness.
TalentOS is now headless
You don’t have to open TalentOS to use it. Your team’s Rooms, skills and memory now come to the AI you already work in:
• Claude Code, Codex, Cursor, Gemini CLI and Antigravity: one setup line, npx talentos@1 init
• ChatGPT, Claude and Grok: add mcp.talentos.so/mcp as a custom connector and sign in
Use TalentOS from any AI agent: talentos.so
34
If a startup built a 1:1 copy of Conductor, they'd be wildly successful.
Surprised no one's done it yet.
3 more days till Conductor kicks us out their cloud
whittle it down to 4
1. ❌ Amp
2. ❌ Boxes
3. 🔎 Capy
4. ❌ Cursor native agents
5. ❌ Delta
6. ❌ Emdash
7. ❌ Factory
8. ❌ Hoplite
9. ❌ Nuphos
10. ❌ Open Session
11. ❌ Orca
12. ❌ Orchestrator
13. 🔎 Paradev
14. ❌ Paseo
15. ❌ Reason Machines
16. 🔎 Replicas
17. ❌ Tembo
18. ❌ Traycer
19. 🔎 Vespin
20. ❌ Vorflux
21. ❌ unreleased app
Super bullish on ambient orchestraction
In 2014, I sold my first company Loom to Dropbox.
Today, I’m proud to announce Roma 2.0 (YC F26): the first to-do list for AI agents.
Everyone uses a different agent: Claude, Grok Bot, Muse…
Until now, none of them could work together.
Roma automatically creates tasks and hands them to the right agent.
Allowing you and your agents to work together, with shared context.
Try it here: roma.app
2
50
The best thing @conductor_build got right isn't the UI. It's cross-session management.
Threads that talk to each other means one manager agent can orchestrate hundreds of sub-agents.
Eventually you talk to one agent and it coordinates every AI and every human on your team.
1
49
Long $NVDA
NVIDIA CEO Jensen Huang in Hedi Slimane Saint Laurent Jacket after admitting to an affair with Chinese spy
1
101
bad strategy to offer alcohol to sf millennials lol
Should be offering pilates classes or $100 voucher for tartine instead!
85
James Win retweeted
When two founders call themselves co-CEOs, it doesn’t mean they’ve found a better structure. It means they haven’t decided which one of them is CEO.
A daily reminder - There are only three ways a smart person can go broke: liquor, ladies, and leverage.
젠슨 황 지금 ㅈ되기 일보직전임
중국 스파이랑 불륜했다고
지금 완전 난리난거 알고있지 ? ㅋㅋ
근데 1985년 로리 황이랑 결혼할 당시에
만약 이혼하게 되면 재산 분할 어떻게 할지
결정하는 혼전계약서도 안썼다고함 ㅜㅜ
근데 캘리포니아는 재산분할 원칙이
반띵이라서.. 전재산 반갈죽 나게 생김
그럼 현재 아내는 110조 정도를 분할받음 !!
최태'원이'의 1조는 그냥 귀여운 수준임😱
4
376
Exactly how I do it
I've changed how I work over the last few weeks.
I now have one lead agent for each area of focus, running all the time, and a chief of staff agent that oversees them. Each lead manages its own sub-agents that write code, test it, chase reviews, and coordinate with team members.
Everything I need to decide or review comes into one prioritized queue, a simple local web app. Each product review includes screenshots and a video demo of the feature. I clear the queue in batches, mostly by voice and keyboard shortcuts. The leads also bring back ideas I hadn't considered.
Working from one queue, instead of switching between dozens of chats, has cut a lot of mental overhead. The system keeps learning my preferences and distilling my judgment into a "Brian brain," so its recommendations and first drafts get better before they reach me. The goal is fewer corrections per change.
Every change still goes through the same human review and security checks. It is eliminating tasks, not human judgment.
What an exciting time to push the frontier of productivity, especially as we build the economy for agents (agentic finance). We should all keep pushing in this direction.
43






























