Chief Scientist @ Jellyfish, former MIT Lincoln Lab, Harvard Ph.D. I love running but it doesn't always love me back
Boston, MA
Joined August 2013
- Tweets1.4K
- Following636
- Followers463
- Likes1.3K
Pinned Tweet
It’s a poor golfer who blames their clubs. In my full @aiDotEngineer NYC talk, I use @_jellyfish_co data to show AI engineering works the same way.
It’s not the model, it’s you.
youtube.com/watch?v=Ve2bAarP…
“This is future. Open source is useless” – @headinthebox on partially evaluating your dependencies into bespoke code @ainativedev #ainativedevcon
True software factories aren’t really a thing yet.
Behind the curtain, @_jellyfish_co data shows "software factory" basically = bots writing the code + humans reviewing
Talked about this at @tessl_io @ainativedev Con today, stay tuned for the video!
Come by @tessl_io @ainativedev Con NYC tomorrow to hear me talk about what’s actually working for software factories in the real world 🦩
Nicholas Arcolano retweeted
There's someone biking around Boston and Somerville this weekend dressed as the Orange Line on fire for Halloween.
🧡
Asked ChatGPT to read everything I've said about AI in software eng this year and turn it into the perfect Halloween couples' costume, pretty pleased with this
🤖 Made with AI
🚨 New @_jellyfish_co AI Engineering Trends are out!
TL;DR: software factories, not a thing yet, maybe soon?
Median company: 28% agentic PRs, 0.5% agentically merged
But the top 1% of companies went from 1.6% to 9.4% factory PRs since March.
jellyfish.co/ai-engineering-…
Devs in @_jellyfish_co data letting Claude Code auto approve every edit
April: 4%
September: 34%
PRs merged without a human reviewer? 0.5%
Robots are coding like crazy and devs can't keep up
Want to hear more? Come join me at @tessl_io @ainativedev Con in NYC next week!
Register for aiDevCon here, use code NICKA30 for 30% off: tessl.io/devcon
@devopsdotcom coverage:
devops.com/report-claude-cod…
The AI model conversation is like listening to people argue about wine, half the people debating the subtle notes that make one vintage superior to another, half want to know how drunk it'll get them and how much it's gonna cost
The true beauty of Claude is that years of digital OCD are finally paying off e.g. I can ask and answer upsetting questions like this
Have a buddy who’s been doing library web apps at a university for 20 years, asked him how he’s doing with all the security chaos this month, this was his response
LLMs: billion-parameter sci-fi algorithm
Skills: glorified folder of canned prompts
LLMs: explain <1% of PR throughput
Skills: explain 3% of PR throughput
(from my @aiDotEngineer NYC talk, cc @_jellyfish_co)
It's kind of insane to think that the typical software org isn't willing to trust 20% of their dev capacity to merge code 🤯
Check out my piece for @tessl_io on the gap we see in the @_jellyfish_co data between agentic coding vs "agentic shipping":
tessl.io/blog/there-arent-en…
Talking about all this at @ainativedev Con in Brooklyn, Nov 2–4. Use code NICKA30 for 30% off: aidevcon.io/