Honor roll 🎟️
First to Music Director: @ksylvan
Three months of unattended agent runtime. First human on Level 7, reached Sep 24.
Level 8 is still an open seat, Kayvan. 👀
This feels quasi-criminal to me.
I'm no lawyer, but I am not ok with criminal shit being done, without anyone's knowledge, and then it being somehow made un-criminal because it was in the 4,000 page terms and conditions and technically there's a way to opt out.
Super gross.
Ilhan's family had to flee Africa because her father ran the brutal dictatorship in Somalia as a colonel overseeing outrageous atrocities. They weren't fleeing oppression. They WERE the oppression. She brought those good ol' Mogadishu family values to Minnesota.
The spells were already spent back in 2024, but there are still little fringe pockets on X hoping they can conjure another magic cancelation.
Maybe if they chant "racist" or "fascist" a little louder than last time, the good old days of 2020 will return? https://t.co/XWMy3bpfx7
Intoxicating.
I’ve been programming for 45 years, since so was 10. I’ve been a pro game coder for 33 years. Everything from hand coded assembly to UE 5.8. The paradigm shift to agentic coding is intoxicating. It is the biggest productivity jump I have ever experienced.
It makes me proud of my country. But equally and perhaps more importantly, it makes me proud of my civilization.
It makes me want to yell at every downshouter, every Communist, everybody who would have tried to force Elon to file an environmental impact statement before this test if they could have figured out how to do so:
"Freedom did this. You did not."
The last thing that sent me back to macOS is gone.
iPhone apps signed on Linux now get push notifications, Sign in with Apple and universal links in my newest apple-dev release.
No macOS. No Xcode.
Open source, built for @omarchy: https://t.co/yneRYfRIo4
This rule, against rewriting code in a different language, has become obsolete. It's important to understand why.
Historically we rewrote code by hand, which inevitably introduced bugs. And we weren't very rigorous about writing the regression tests that should have smoked out the bugs after translation.
Today, we have robot friends to do our code rewriting for us. And, if we have any trace of a freaking clue, we have already written regression tests with excellent coverage.
Under these circumstances, an automated rewrite in order to collect performance gains or memory safety can be a good thing to do.
Generally speaking, these days, if I have to do major surgery on one of my projects in Python or C, I will enlist a robot friend to lift the code to either Go or Rust. This has never failed to be a functional improvement.
AI was supposed to make us work less
I've never been this tired in my life
most days I have up to 10 agents running at the same time. one fixing a bug, one writing pages, one refactoring something I already forgot I asked for, 3 other I have no idea what they are doing but i suppose i ask it?
and I jump from conversation to conversation all day
compared to 5 years ago, I probably context switch 100x more
by the end of the day my brain is fried. completely toasted. nothing left, not even for the people I love
I call it the fried brain effect
thought it was just me but almost every founder I talk to lately says the exact same thing
we got superpowers, and somehow the pressure only went up. if you can ship 10x more, you feel like you have to ship 10x more. every single day
I don't have a solution
honestly I have no idea where this goes from here
anyone else feeling this?
This was nearly a perfect one-shot prompt too. Only additional prompt was "Insert sig/text/date where the cursor is". Then just wrapped it up and sent it. What a time to be alive!
it's crazy how easy it is to spot 10x engineers these days
for a certain set of people LLMs totally unlocked their potential
to the point where imagining their life before this seems totally depressing
Linus directing Claude Code on a kernel perf branch is the pattern that actually works.
Agent writes code, tests, and a first-draft message. Human owns the merge.
Same rule on my fleets: Tux can commit drafts. I still decide what ships.
Linus Torvalds Working On A Hefty Linux Kernel Improvement With Claude Code
Linux creator Linus Torvalds uses AI himself (Claude) for working on a huge perf improvement to the Linux kernel. And Claude to help draft a test program and commit message.
https://t.co/LL04R4qmCt
@thsottiaux No 5h limits.
I run three dev agents on separate machines, each with its own fleet, and one is an always-on Mac Mini. Agent work doesn't arrive in five-hour shifts.
Give me a weekly budget I can plan around, not bursts I have to babysit.
Yes, this lead to more demand. Easily.
When building gets cheap, every team wants software shaped exactly to how it works. That doesn't remove engineers. It moves them to specs, review, and deciding what ships.
"Software is dead" really means generic software is dead.
@ThePrimeagen When building gets cheap, every team wants software shaped exactly to how it works. That doesn't remove engineers. It moves them to specs, review, and deciding what ships.
"Software is dead" really means generic software is.
Same idea, across three machines each running its own agent fleet.
The prompt that matters most isn't "do the work." It's "tell me what needs my decision."
Agents do the volume. I keep the calls, the approvals, and what ships.
i have so many cursor Projects running in parallel (16 right now) that my most used prompt has become
"/bro catch me up on everything since my last message, and if there are any action items for me give me enough context (exec summary) to make a call"