Effy Zhang
@effyyzhang
Followers
3K
Following
9K
Media
113
Statuses
1K
Building something new. Previously, founder of @Baserunai(acq.), design lead @Cruise, @Square.
San Francisco, CA
Joined September 2011
RT @sdianahu: saw some impressive projects built in <8 hrs at the ai coding hackathon today hosted by @samedotdev @morphllm @benswerd from….
0
25
0
RT @morphllm: How to spend 85% less on Claude Code using @morphllm and @Kimi_Moonshot 's Kimi K2. (step-by-step thread 🧵) .
0
2
0
RT @yetone: I found that the combination of kimi-k2 and morph fastapply is incredibly effective. Since kimi-k2 is a bit slow, using morph f….
0
6
0
RT @yetone: Today, avante.nvim has two updates:. 1. Fast apply is supported, using to greatly improve the issue of….
morphllm.com
Let AI apply code updates to your files instantly and reliably with Morph. 4500+ tokens/second, trained on 1M+ code edits with speculative edits. Reduce errors by 4x + 3x faster.
0
11
0
I'm judging WeaveHacks this weekend! If you're free, come build agents with us! .Registration link in the comments.
1
1
5
Designing Claude Code would be fun! You can see a UI preview in terminal like this:
0
0
4
A day in Shenzhen: In one park, I saw three groups of engineers—one testing robot lawn mowers, another tuning the camera on a new phone, and a third training drones to avoid trees. #buildinpublic
1
0
10
Come to join us! 🙌.
Tonight is the night! I'm so excited to hear from @effyyzhang @adrianmg @JohnPhamous and @ryngonzalez about their angel investing journeys.
1
0
9
RT @garrytan: Bottom quartile investing at YC demo day is better than top quartile venture capital investing
0
121
0
RT @esther_confused: i got waitlisted for YC AI startup school. @garrytan shooting my shot, this is my application:. - one of the only 2 w….
0
11
0
Codex feels like one of those minimum lovable products — rough around the edges, clearly built fast with minimal design help. No file picker, no autocompletions, no hotkeys, confusing task list, clunky env config… but it just works. Shipped 20+ PRs in 12 hours, zero failures.
4
6
131
One thing I really like about @cursor_ai is that I can use different models to critique each other’s work. I often find small improvements I can tweak after making a big change.
0
0
10