banner
LightNews
mergesort.me
Joe Fabisevich
@mergesort.me
3.9K followers 71 following 4.4K posts
“Apps genius” - Colleen. I used to work on making Twitter a bit healthier, then that all went to hell. Now I make puns and indie apps @plinky.app. Born and raised New Yorker, trying to do a little good and be the friend you made along the way. 🍕🐱⚾️
Posts Media Videos Starter Packs
Pinned
mergesort.me
Joe Fabisevich @mergesort.me · Nov 9
Hi, I’m Joe! I used to work @ Twitter on all the hard things like misinformation, disinformation, harassment, and civic integrity. I also spent a ton of effort on little improvements to make people’s lives better. These days I’m an indie developer making it easy to save links for later, with Plinky.
Plinky
Plinky helps you easily save links from any device, so you can enjoy them later. Save on your iPhone, iPad, Chrome, Safari, Firefox, Zapier, and so much more.
plinky.app
5 12 110
mergesort.me
Joe Fabisevich @mergesort.me · 11h
Heck, I was able to port this OpenAI library to work on Linux without writing one line of code. It took real effort and I used my development experience to make it work, but I never would have done this without AI because the task would have been too arduous.
Release SwiftOpenAI v4.3.0 · jamesrochabrun/SwiftOpenAI
What's Changed Adds xAI information to README.md by @AlekseyPleshkov in #149 Implementing cross-platform support by supporting Linux-friendly HTTP clients by @mergesort in #143 New Contributors ...
github.com
1
mergesort.me
Joe Fabisevich @mergesort.me · 11h
I use it a ton in my own open source projects. Whether that’s solving subtle bugs that manifest in rare circumstances (github.com/mergesort/Bo...) or building features from scratch (github.com/mergesort/Re...), it’s just the way I code now. Still my judgement and oversight, but I manage the code.
1 1
mergesort.me
Joe Fabisevich @mergesort.me · 12h
Ok Mr. Arms.
1 2
mergesort.me
Joe Fabisevich @mergesort.me · 1d
Sounds like vibe prototyping or vibe exploration to me.
1
mergesort.me
Joe Fabisevich @mergesort.me · 1d
Sorry to beg sir, but my family needs ChatGPT Pro
The blind beggar meme
3
mergesort.me
Joe Fabisevich @mergesort.me · 1d
This is the last thing you see before your cat murders you.
A black cat peering with one eye from behind a computer monitor
3 30
mergesort.me
Joe Fabisevich @mergesort.me · 1d
Can’t stop me, this post is already in my PDS.
1
mergesort.me
Joe Fabisevich @mergesort.me · 1d
You're telling me someone jerked this chicken?
1 4
mergesort.me
Joe Fabisevich @mergesort.me · 1d
I would do almost anything to never have to record a TikTok video, but here we are.
1 1
Reposted by Joe Fabisevich
plinky.app
Plinky 🔗 @plinky.app · 1d
Based on my internal metrics 1.5 billion of them are links, which is still not enough links.
bsky.app
Bluesky @bsky.app · 8d
we hit 2 billion posts today! 🥳
1 6
mergesort.me
Joe Fabisevich @mergesort.me · 2d
You got my vote. 🌟
2
mergesort.me
Joe Fabisevich @mergesort.me · 2d
Nm what’s hypha witchu?
1 2
mergesort.me
Joe Fabisevich @mergesort.me · 2d
No true HATEOScotsman
1
mergesort.me
Joe Fabisevich @mergesort.me · 2d
Isn’t the answer cryptocurrencies?
mergesort.me
Joe Fabisevich @mergesort.me · 2d
Fuck yeah.
2
mergesort.me
Joe Fabisevich @mergesort.me · 2d
Now that we have a name 50% of the work is done. I’m a little mad that I have absolutely no time right now, otherwise I’d quickly whip something up with Codex.
6
mergesort.me
Joe Fabisevich @mergesort.me · 2d
Lorem atsum
1 13
mergesort.me
Joe Fabisevich @mergesort.me · 3d
I'm kinda done debating because you're making it clear you didn't even read the research you cite. (I actually have read the papers and you can't extrapolate from 16 developers in a randomized trial, 8 of whom had never used Cursor — a few of didn't even know the features Cursor offers.)
Ruben Bloom (Ruby) on X: "I was one of the developers in the @METR_Evals study. Thoughts: 1. This is much less true of my participation in the study where I was more conceintious, but I feel like historically a lot of my AI speed-up gains were eaten by the fact that while a prompt was running, I'd look" / X
I was one of the developers in the @METR_Evals study. Thoughts: 1. This is much less true of my participation in the study where I was more conceintious, but I feel like historically a lot of my AI speed-up gains were eaten by the fact that while a prompt was running, I'd look
x.com
mergesort.me
Joe Fabisevich @mergesort.me · 3d
I’m well aware of this subject matter but what you’re describing is a different problem. For example workslop is a matter of laziness and incentives, mediocre results from people who don’t use AI in a novel way but instead regurgitate whatever it says verbatim. That’s not who I’m talking about.
mergesort.me
Joe Fabisevich @mergesort.me · 3d
Current models simply do not hallucinate 30% of the time. If you believe that than odds are you haven’t tried any model that was released in the last six months, because the amount of progress they’ve made on the hallucination front is wildly good, especially for software development subjects.
2 1
mergesort.me
Joe Fabisevich @mergesort.me · 3d
Nothing was stopping them, but people learn differently. Have you ever met a developer who learns better from video than reading? Or by doing than sitting in a lecture? There are a lot of people who will learn better from AI (and many worse or far worse), but you can’t disqualify them if they learn.
1
mergesort.me
Joe Fabisevich @mergesort.me · 3d
A lot of people see X posts about vibecoding from $0-100K and underestimate how many thousands of people there are out there who are using AI as an on-ramp to learning more about the technical subjects you say they will discover and cry about. Far from everyone of course, but I keep an open mind.
2
mergesort.me
Joe Fabisevich @mergesort.me · 3d
See this is the perfect example of what I don’t think is universally true, but is viewed derisively as if it is. I work with people who over the last six months have gone from Uber drivers or teachers to building real software — only — because they’re curious and interested in these exact things.
1
mergesort.me
Joe Fabisevich @mergesort.me · 3d
I don’t think it’s my default assumption based on what I’ve seen working with people who have no technical experience because AI does a good job of defaulting to best practices *but* I definitely think it’s plausible or likely that we’ll be annoyed when non-technical people contribute to codebases.
1 1
mergesort.me
Joe Fabisevich @mergesort.me · 3d
Wouldn’t a similar argument apply I front end developers today vs. 15 years ago when many people chided them as “fancy designers”? Or constructing a scenario, is there a future where someone who has product instincts can deliver “meaningful” code/results in a team despite less technical training?
1