Nicholas Arcolano

Text version of some of the @_jellyfish_co insights from my video earlier this week. Data across 135K devs show that creating 6+ context/skill files (CLAUDE.md, Cursor rules, etc.) means 2.3 extra PRs per week. Each doubling of investment → 29% more PRs merged.

Good news – the "tokenmaxxing" trend has run its course! Showing up in an NPR episode so that my mom can ask my "what does <blank> mean?" is the final stage of any tech trend. wbur.org/onpoint/2026/0…

🚨 New @_jellyfish_co AI Engineering Trends data jellyfish.co/ai-engineering… Top companies now generate 21% of PRs autonomously (was 3% a year ago). Power users burn 225M Claude Code tokens a week, 7x the median.

New @_jellyfish_co data on AI agent customization across 135K devs. Devs who've created 6+ context/skill files (CLAUDE.md, Cursor rules, etc.) ship 2.3 extra PRs per week. Each doubling of investment → 29% more PRs merged.

Thanks to tokenmaxxing we have a new definition for "10x engineer": someone who can double your throughput for 10x the cost. Check out this piece in @TechCrunch featuring @_jellyfish_co data on the hidden costs of raw token consumption: techcrunch.com/2026/04/17/tok…

New @_jellyfish_co data on tokenmaxxing. Top decile devs burn 69M tokens per PR vs 7M at the median – 10x more fuel for ~2x the throughput. Tokens are rocket fuel... and like a rocket, going faster takes exponentially more of it 🚀

And that's a wrap! AI Engineer Europe 2026 has concluded. Our video crew did incredible work to capture the energy, enthusiasm, and positivity of this event -- but it still doesn't come close to being there. If you're engineering the future of AI -- we hope to see you at a future event! Thank you London -- thank you Europe!

Another fantastic @aiDotEngineer in the books! Just telling @Benghamine the thing I love most is how these events let me “see around corners” – what we talk about here everyone in the industry will be talking about in 3-6mo.

raising lobsters at @aiDotEngineer

How I help claude review the code written by Claude:

Vibes from yesterday's workshop/reception day!

What's next for @openclaw - Peter Steinberger on the future of the claw

OpenClaw didn’t even exist when I was at @aiDotEngineer CodeSummit in November and now 5mo later at AIE London there’s an entire track on the main stage devoted to it. Insane.

New @_jellyfish_co data on AI token costs across 12,000 devs. – 90th percentile: 382M tokens/month (7x the median) – Cost per merged PR: $0.28 (low usage) vs ~$90 (high usage) More tokens = more output, but at a dramatically higher price per unit.

Loving the shoutout to @_jellyfish_co AI Engineering Trends benchmarks on the most recent @AIDailyBrief – thanks @nlw! Thrilled to hear our analyses are helping folks make sense of their progress on AI transformation Episode: open.spotify.com/episode/1wlB5o…

New @_jellyfish_co AI Engineering Trends update (now covering 37M pull requests!) – P90 for autonomous agent PRs 10% → 14.5% (gap widening fast!) – AI-assisted teams still seeing ~2x PR throughput – Reverted code creeping up 5-11% as adoption grows jellyfish.co/ai-engineering…

@claudeai Every session basically looks like this

Is anyone actually getting @claudeai remote control to work reliably? I've tried it every time there's an update and it's still basically unusable – super laggy, constantly disconnecting, basically can't get through a turn or two of a project without giving up.

@claudeai I desperately want it to work – have tried in the desktop app and on mobile, hosting on my wired Mac Mini vs. laptop, various qualities of internet – it's never worked well, not once.

New @_jellyfish_co data on autonomous agents: – P90 companies: 14% of PRs from agents – Feb alone: 119K agent PRs created, only 70K merged – Merge rates: humans 80%, agents 64% Agent adoption is accelerating; actually shipping agent code is becoming the bottleneck.