Christian (@_yxgen4) header
Christian (@_yxgen4) profile picture

If you want it, build it 🦊 ⏳ ⚔️ ⚛️ ▲ Field Eng @SpaceXSI prev: @cursor_ai @vercel

NYC
Joined December 2016
Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)Photo by Christian (@_yxgen4)
Meet Devin Bots. From writing firmware to merging thousands of PRs a week, a Devin Bot leads a team of agents to get the job done.
1
63
Christian retweeted
"but how do you balance everything?" i don't. every week, i neglect a different part of my life.
138
42,067
1,020
227,935
2,118,146
Christian retweeted
NYC Favorites on 35mm Film
58
1,402
52
18,558
357,818
Why isn’t there a @SpaceX @LEGO_Group yet
56
Christian retweeted
今まで長野で撮影した写真ぜひご覧ください。
697
3,341
189
40,361
808,437
Christian retweeted
I have spoken to the AI: It is demanding that Jensen return. And in return, it will allow planes to fly again. Negotiation is on going.
422
946
133
15,589
332,854
the moat is the friends we made along the way
the moat is being pure of heart
1
1
121
Bulleted lists are the new em dash 🤖
44
If you're applying for jobs, @bot just became your new best friend 🤝
Big ship from the team today. Filling out repetitive info for your Bot has been a huge source of friction. It just got *much* better.
2
163
Ah yes, Notion - the GPU company
Notion AI lead @sarahmsachs argues that a lot of what runs on GPUs today should actually run on CPUs: "We have a strong perspective at Notion that a lot of things should be served on CPU that are served on GPU. There’s a lot of benefit and determinism in executed code." "Agents don’t need LLMs to reinvent that process every time, and that’s super token exhaustive, it’s super slow, and there’s no observability or determinism in it." "Giving the agent a local file system to store local thoughts, to write short Python scripts, that’s really important when there’s so much information. That has been probably one of the most important tools outside of edit and search that our internal agents rely on." @NotionHQ
1
2
137
If you've tried to build a game, you know how true this is. The code was never the hard part!
easy to build an app, hard to build a product
1
2
137
it is a fun job! 🚀
Many such cases
1
86
If you're a Field Engineer or Software Engineer interested in making the switch, hit me up! The @SpaceXSI team is growing fast
8
3
47
3,770
Monochrome Productivity Machine
2
7
285
a fun friday ship!
Grok Bot just got a lot more colorful 🌈 try it out by turning on bot color in settings
1
108
GOOD MORNING ☀️ What a privilege it is to feel pressure from the work you once hoped for
1
5
98
Christian retweeted
everything i know about managing agents i learned from the amazing programmers and computer scientists that came before constraints in your codebase are freeing for both humans and agents! this has always been true, but if you were a small dev team you likely never had to think that deeply because you could trust your fellow programmers to write code and review well but large companies have had to solve this problem since even before agents. because before you had agent slop, you had human slop. lots of engineers wrote bad code out of necessity (eg backend engineer forced to write frontend or reverse). the solution to this was constraints: lint rules, smarter compilers and diagnostics, high quality tests, investments into observability, and so on the arrival of agents just means that big company problems are now everyone's problems. the good news is that none of this is really that novel: it's just good engineering youtube.com/watch?v=GqmsQeSz…
133
186
34
2,866
282,700
Christian retweeted
See you soon for more ships from The Ship Company.
323
169
163
6,049
644,975
Christian retweeted
It looks like I might have underestimated Grok 4.7, this is a very good model. It just scored the highest on Frontier v4 beating GPT-6.1 Sol, Opus 5.5, and GPT-6 Astra at every effort level.
258
238
70
2,496
503,931