Building @ZoomHub. Agentic engineer @CollegeVine. Formerly: @SignalApp, @Shutterstock, @FiftyThree, @TheThingdom, @LiveLabs, and @OpenZoom.
Zürich, Switzerland
Joined March 2007
- Tweets18.2K
- Following352
- Followers875
- Likes29.9K
Daniel Gasienica retweeted
Human-written code has a signature, and it's a stale README nobody planned to fix.
Daniel Gasienica retweeted
Opus 5.5 is such a good writer that I really enjoy reading its reports now. Such a huge improvement over Fable.
Daniel Gasienica retweeted
> None of it will matter but I'm having the time of my life right now
Lowkey the healthiest mindset to take on in these uncertain times
Second or third time this week I read someone using DEFCON 5 as scary, even though that’s ‘business as usual.’
Scary is DEFCON 1 👀
I highly recommend @ryanlpeterman podcast with Scott Aaronson 👏
Ex-OpenAI researcher Scott Aaronson admits AI one-shotted open problems from his 25-year-old papers, while accelerating the atrophy of his own mathematical skills:
“This summer I fed in some of the open problems from my papers 25 years ago, and just boom, boom, boom. It solved them in a one-shot way."
"These are problems that probably I could have solved if I had spent enough time, more like 100 hours at the least. But these days I don’t really get contiguous hours to think."
"AI accelerates the atrophying of my own skills. If it’s something you could work out in some hours, but GPT can just work it out for you right now, that is very tempting to do, and I often do it."
@UTAustin
Daniel Gasienica retweeted
"Soon AI will write almost all code, but it still writes it in languages designed for humans, and since no one can review millions of AI-written lines, bugs pile up. The stricter a language is, the less the AI gets wrong, which is why AI is now solving open math problems in Lean, where every step must be proven, but Lean is too slow and limited for real software. Bend brings Lean's proofs to a practical language that runs at C speed and on GPUs. Since AI-written code comes with proof that it works, an AI can keep improving software with no human checking it, because any change that breaks it is rejected. We're soon going run that AutoResearch loop on Bend's own compiler, pushing its performance even further." - Opus 5.5
Daniel Gasienica retweeted
The edge cases are all handled comprehensively, it always tries at least two prototypes if not more before settling on the best design, which I never did, it has very rigorous pre-commit reviews, it runs a ton of microbenchmarks & mutation testing.
It writes better code than me.
Daniel Gasienica retweeted
To create my claude.md, I had it read:
- my favorite programming books + blogs
- the best oss projects
- the code of the engineers I respect the most
Claude (when given proper instructions, constraints, and context) now writes better code than me, almost always.
the coding agent haters are getting dunning-kruger'd so hard right now
do you really think that your engineering ability is better than the models at this point?
it is very very likely that fable is better than you in every branch of software
it has been trained on all the code of the internet, it knows almost every trick in the book, all the design patterns of every domain, every single low-level detail, every bit-twiddling hack, it's read every single blog post from every cracked engineer that ever existed
do you really think you can beat it? do you really think you can be more creative than it?
unless you are 99th percentile expert in some niche domain of software, it simply is not possible. sorry.
Daniel Gasienica retweeted
You're comparing your life to fiction.
@nycdivorcelaw
Daniel Gasienica retweeted
Why are you still using pull requests?
Is it for code review?
If so, do you really think your or your colleagues catch bugs and mistakes that an Opus 5.5 or Fable or Astra won't find? You can literally spawn all three of them and have them check four times each.
(Also, don't tell me you don't have a "stamp plz" Slack channel or group chat somewhere.)
Is it for knowledge sharing?
Surely there's better ways for that now than the PR, no? We have models that can generate explainer videos, presentations, podcasts, games, quizzes, walkthroughs, ... for any piece of code it can reach.
Is CI the reason?
Well ackshually, CI means continuous integration and its original meaning is the *opposite* of having long-lived branches and PRs.
But, leaving that aside, your agents are hopefully already running the tests before they push something, and hopefully they can run as long as they want and don't block you so they can run the whole test suite and generate "irrefutable proof" and end-to-end demo videos and so on... And so they run the tests and confirm and then you push to a branch and everything runs again and then you merge and then it runs again? That doesn't make sense, does it?
Maybe you work in open source and you accept contributions, in which case I can't speak to the value of pull requests. It's been 2 years since my last OSS contribution. But from what I heard, the time of the PR is coming to an end in OSS too?
I honestly don't get why people still stick to PRs.
With agents you can now move 10x faster, you can finally do real continuous integration, and get more confidence in the changes the agent made.
Don't slow yourself down by having all the changes pile up in a PR.
Daniel Gasienica retweeted
Yup, we have SOC2 and push to main:
ampcode.com/notes/thats-not-…
Daniel Gasienica retweeted
omg he is looking rough, he is not taking it well (but least he is at the bargaining stage already)
Mathematician Terence Tao:
"we're seeing the end of the romantic era of mathematics, the age of heroes. we're moving into an industrial era where math becomes large-scale, done in big teams like the other sciences"
We're entering, rather unwillingly, a new era where exciting new things are possible, but some things are being lost
Having Opus 5.5 is like having a diligent Principal engineer buddy as opposed to some frantic Junior 🤖 ☺️
Daniel Gasienica retweeted
So far this crisis of meaning has touched only a few hundreds thousand people in IT and math maybe?
What happens when the same questions pop up in the head of millions?
What about children and teens thinking about their future?
We are going to face all of this with vague promises of universal income made by a bunch of trillionaires?
