ทวีตที่ปักหมุด
Introducing my new side project: nextUX
Fill out any form with your voice.
Do you know anyone this would be useful to?
Link to live demo in next tweet!
English
Jonny Langefeld
972 posts
Jonny Langefeld
@jonnylangefeld
@kenzielangefeld 💍 Software Engineer 👨🏼💻 @xAI 🧠 interested in all things digital
San Francisco, CA เข้าร่วม Mart 2012
1.3K กำลังติดตาม1.2K ผู้ติดตาม
English
Update on the below: 9 months later we're expecting our third child any day now.
I decided to focus on my family for a while. Leading Supercomputing at @xai will remain the honor of my life. Thank you @elonmusk for the opportunity. We will win.
heiner@HeinrichKuttler
me trying for kid no. 3:
English
I was also really happy to see you here! You actually showed up on my main timeline and I was like “no way” 😄 Already loved reading through your recent posts and excited to follow for more!
Probably as for a coding task itself, the complexity of the merge conflict matters. I’ve seen make LLMs make good decisions on some merge conflicts. They compared the intent of each contribution and tried to make them both work. But I agree it might not work as well if there are conflicting intents and it has to decide for either or.
English
Hey @jonnylangefeld ! Good to see you again :)
I think I posted something in a comment thread earlier about the fact that I'm not convinced that solving merge conflicts is something that can be done (well) without a human in the loop. An agent can definitely remove conflict markers and ensure that the code compiles, but it can't really determine what union of features is best aligned with the overall project goals.
I also leverage agents to help resolve conflicts (so that I don't have to read the git docs for the billionth time to remind me of all of the flags I forgot, and what "--mine" means in a given context), but I still generally have to make some decisions along the way.
English
Half-formed shower thought: we need a better version control paradigm for AI assisted coding.
The agent speedup feels great on greenfield/solo projects, but when you start collaborating with other devs, things can fall apart. Either you all exchange huge PRs (abandoning code review, and dealing with gnarly merge conflicts), or stick to a traditional flow with reasonably sized changes, in which case you spend a lot of time waiting for changes to land.
Old style version control systems had the notion of files being "checked out" by a user. This was painful, but was a pretty good signal that someone was making changes to a set of files that might affect what you wanted to do. Obviously that had huge downsides, but I wonder if that "signal" doesn't still have value. In theory you could get something like this from git, with automatic / frequent push and pulls. You'd have to deal with the messy commit history, but...maybe the existing "functional chunk commits" strategy is an anachronism
English
@jonallie LLMs put the joy of writing code into the leisure activity category. Just like we wouldn’t use a carriage to compete in a race, it’s still fun to ride on one.
English
These days, 99% of my "work" coding is agent assisted, but outside of work, I still do a lot of programming by hand.
For this, I follow nearly the opposite of my agentic coding advice: I pick languages and problems I'm not familiar with, and type everything into vim. (Most recently, implementing 9P in Zig)
Partly, I do this because I enjoy the process of programming, just like I enjoy tabletop games, but partly I do it for the same reason that I lift weights...doing hard things builds strength that I can apply to other areas.
As I hinted in my post about getting started with agents, just because the agent is typing, doesn't mean that I'm not deeply involved. Instead, I find that I get the most return with agents when I can apply the knowledge I've acquired over years of "regular" coding and systems design.
Being able to leverage agents if I want to "get things done", and reserving my personal programming time to learn is, in many ways, incredibly freeing
English
@veggie_eric Up one notch: pipe to fx for interactive json viewer and navigate the json with vim commands (fold, unfold etc)
English
I'll go first:
pipe to `jq` to pretty print JSON
curl ... | jq
English
🧵starting a thread for goated terminal commands and one-liners. I need to up my game, please share your favs below
English
@HSVSphere "not actually required" is a somewhat brief summary of a 1000+ page law that is not well tested in European courts. One might want to ponder why said law created this behavior if it didn't "require" it. One can also keep writing complex laws during the decline.
English
This banner isn't actually required btw
Andy Orsow@andyorsow
lol never been to posthog's website before
English
In 90% of cases where people say you need first-principles reasoning to fix a mistake, you probably don’t. Common sense is enough. We make far more basic mistakes than we like to admit.
English
@TobyPhln The second best car in the world (right behind model S) and the best color 👌🏼😄
Have fun!
English
Picked up my first Tesla on Monday. Impressions: very quick, thoroughly inspected the glovebox and button (no complaints), price was very on-brand. Can't wait to do 0-20mph in 0.6s in London.
English
@Guodzh @pranjalssh Thank you for everything you’ve done!
English
Last day at xAI.
Wild journey past three years but excited about next chapter.
Thanks all for the love and support yesterday. So many friends made along the way and I will miss you all!
English
English
I left xAI earlier this week. It was a difficult decision. The past two years have been an intense, fun, and deeply rewarding journey, and I accomplished things I could not have imagined two years ago.
Thank you @elonmusk for the opportunity and for everything I learned at xAI. Thank you @Guodzh for the trust you placed in me and for all the days and late nights we worked through together.
And thank you to the entire Omni / Imagine team: thank you for your trust, and for growing together with me. It has been an honor, and I am incredibly proud of what we achieved together. I feel fortunate to have had the chance to work with all of you.
At xAI, everything feels possible. I had the chance to work with and learn from some of the most exceptional people I have ever met. I was able to explore across domains: from pretraining to post-training, from language models to multimodal, from perception to generation. Joining xAI was one of the best decisions I have ever made.
@grok imagine is special to me. Building video generation models, where I started with almost zero prior knowledge, from 0 to No.1, as an IC and as a lead, alongside an extraordinary team, and shipping it as a great product used by millions, all within 6 months, at age 28: I feel proud.
But now it’s time for me to move on. I’m burnt out, and I know my happiness is no longer maximized in my current state. It is sad to say goodbye, but it is just the right time for a change.
Best wishes to the Imagine team, you are absolutely the best, and you deserve the best. I will cherish all our memories for the rest of my life.
For now, I’m taking a break and giving myself time to figure out what comes next.
Posted from Hawaii.
English
Three years, thousands of PRs, and a million jokes. Today was my last day @xai. To the team: you rock, no one burns the midnight oil better. To @elonmusk, thanks for taking me on board. I've learnt more about execution, speed, and product perfectionism than I could ever have imagined. Thanks for everything.
My next priorities: sleep for more than 8h, write down all the things I've learnt (I have a list), and then think about what I want to do next.
@gork wdyt?
English
Jonny Langefeld รีทวีตแล้ว
Jonny Langefeld รีทวีตแล้ว
Top again!
Arena.ai@arena
BREAKING: @xAI’s Grok-Imagine-Video now #1 in Video Arena! For the first time, Grok-Imagine-Video-720p takes the top spot on the Image-to-Video leaderboard, overtaking Google’s Veo 3.1 while being 5x cheaper. Its 480p version released a few days ago ranks #4. Huge congrats to @xAI team and @elonmusk on this incredible milestone!
English
🚀
@levelsio@levelsio
✨ Grok Imagine Video is now live on Photo AI It's hard to explain how impressive this is because of the speed that @xAI got itself from literally nothing to the top of the leaderboards Six months ago Grok's video model was a joke, it wasn't even close to any of the video models out there, it looked cartoony and wasn't there and nobody took it seriously Now it's here and it's instantly the #1 video model out there now, it shot above Kling (which I used before on Photo AI and usually my favorite) and above Runway Gen 4.5 which was just launched 6 days ago! Mmore importantly it's now above xAI's biggest competitors' models: Google's Veo 3 and OpenAI's Sora 2 Being the best video model doesn't mean it's flawless: video is incredibly hard and actually because it looks so realistic now when it does make a mistakes it's even funnier One thing I noticed is that it still has a hard time with is voice, it does it well for a majority of the video but then slips up and produces unintelligible blabbering (which is really funny to hear) in both English (video 1: "it's where I find my naim", what's a "naim"?), and tested it in Portuguese too (video 3 at the end is unintelligible Portuguese I believe) In many ways Grok Imagine Video also reminds me of Sora, it has that weird but funny Sora conversation style But guys it's REALLY really really really close to getting perfect, we're so close to having full video productions being to be able done in AI, actually you already can if you just cut out the bad parts already Very exciting and I'm grateful I can experience this
ART
