Claude Code @anthropicai. prev YC W20, @spc, @medialab

SF via Toronto
Joined August 2011
Pinned Tweet
I put a lot of heart into my technical writing, I hope it's useful to you all. 📌 Here's a pinned thread of everything I've written. (much of this will be posted on the Claude blog soon as well)
270
889
122
8,716
2,105,940
Thariq retweeted
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent. It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
1,984
3,712
4,181
48,665
7,096,301
I think most people multi-tasking with agents could benefit from slowing down most of the stuff you're doing wont really matter- what's your P0? what would it look like if you gave it your full attention?
560
378
178
6,888
447,616
I've realized I often would prefer to vibe code little parts of games than actually play games these days. Especially cerebral ones that require some thinking like League. I'm not quite sure what this really means for games but I think it's important?
286
32
39
2,096
158,534
I'm coming back to my game side project, and now that I feel confident in the theme, I want to revisit what the actual gameplay and hook is. Is it a 1v1 or 3v3 or single player? What if you could vibe code your own characters? xitter.cf/trq212/status/21053334…
As a personal side project, I've been prototyping a video game. As a former games founder, the process of making a game is deeply satisfying and creative, don't outsource that to AI. Use AI to work with you to bring your vision to life. Here's how I'm trying it:
100
21
7
943
75,880
One hook I kept coming back to was that I was having as much fun making the game + characters as I was playing it. What if that was the main hook? I'd distribute the game as open source, you could vibe code your own characters & it would balance it.
5
29
10,530
What do the mechanics look like here? Do your characters play themselves, like Salty Bet? Or maybe there are cool cinematic options for you in combat, like Persona or Heavy Rain. I'm not sure! But I'll share more as I figure it out.
8
16
9,512
What do the mechanics look like here? Do your characters play themselves, like Salty Bet? Or maybe there are cool cinematic options for you in combat, like Persona or Heavy Rain. I'm not sure! But I'll share more as I figure it out.
1
6,487
thanks for the feedback on the Claude Code Desktop launch this week. we'll continue to iterate based on feedback (yes, group by folder is coming back). our small team is grateful to be building for so many of you!
141
11
4
877
73,790
"Today's Weather: Partly Agentic"
we've been working on simplifying the ui and making it easier to manage multiple sessions. there are a lot of things in this update, hope you enjoy it!
36
11
1
239
41,605
Replying to @fnthawar
@fnthawar and I talked about how the skill of coding agents is "being in the details" like running a company, you can't know everything but caring obsessively about the right details is what makes something great it could be code, architecture, design, UX- whatevers needed
excited to be back home
44
4
252
36,482
I used to tell people it's good to "be technical" but I think this is not accurate enough. If you're technical you need to be in the details more with the right parts of the code. If you're non-technical, being in the details means knowing how things work at the right level.
3
1
1
16
7,643
Claude Code Desktop is now so much aware of its own capabilities and how it can work with you, like spinning off subsessions. I think of this almost like a v2, so many small details went into make it great.
We've been working hard on making the Claude Code desktop app great for running lots of sessions side by side. It's now much quicker to start sessions, easier to split work across a few, and you can always see what each of them is doing. Here’s what's new:
436
135
34
6,019
369,909
s/o to @alicelovescake1 @amorriscode the CCD goats
6
1
56
18,608
excited to be back home
50
4
1
1,044
83,212
evergreen
Replying to @tszzl
say it with me now. experts are fake, smart generalists rule the world, everything is designed by people no smarter than you, and courage is in shorter supply than genius
36
75
4
2,209
140,063
I think Terrence Tao is directionally correct, we shouldn’t settle for a super intelligence that is opaque. A key signal of intelligence is communication. We should strive to make products and models that build understanding with humans instead of disintermediating them.
This is a slide from Terence Tao's 'Math 2.0' public lecture yesterday evening at Caltech. I am highly confident that, if the cure actually worked, almost any Stage 4 cancer patient would tell you that human comprehension of its mechanism is completely irrelevant to them.
241
73
43
1,455
122,184
honestly pretty cool to have this on my new tab page just merged in some PRs by others too!
you now get Claude API credits with your MAX plans ($100, or 200 matching your plan) every month, use this to build more personal AI for yourself! I made an AI homepage that's generated everyday based on sites I read and replaces my 'new tab' page in Chrome
86
16
5
663
79,963
before I joined Anthropic, I spent about 2 weeks hacking on this as a side project with Opus 4. It used the Agent SDK so it needed a constantly running process & didnt work that well but one prompt to Opus 5.5 ported it to Claude Managed Agents & made it way more reliable
you now get Claude API credits with your MAX plans ($100, or 200 matching your plan) every month, use this to build more personal AI for yourself! I made an AI homepage that's generated everyday based on sites I read and replaces my 'new tab' page in Chrome
104
46
5
1,595
164,232