Tabflows 🏴☠️ retweeted
I think of max effort as “there are a lot of things you should think about and the correct solution is unlikely to be the solution you lazily come up with first”
Which when you put it that way makes more sense why max effort on some tasks is either wasteful or makes the agent fail to do the simple stupid thing
Tabflows 🏴☠️ 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.
Tabflows 🏴☠️ retweeted
a good portion of the best engineers have moved around to companies where they can more directly work with ai
so you see founders of the companies they're leaving posting how they're doing really interesting ai work
but it's futile, competing for talent is impossible right now
new prayer before i go to sleep at night 🙏
I have been approaching this startup game wildly different than others but it all makes sense if you know my 20 rules
1. Stay consistently making progress
2. Don’t die go broke burn out or quit
3. Make bets that can improve positioning even when they fail
4. Invest big when conviction is high
5. Discover conviction don’t force it
6. Never make contrarian bets on things you are not an expert on
7. Be patient yet honest when progress is slow
8. Make sure big decisions like raising money are strategically sound and not coming from emotion or impatience
9. Constantly look for weaknesses and avoid common pitfalls like sunk cost fallacy
10. Focus more on creating value before capturing it
11. Build in public
12. Create feedback loops
13. Prefer less users who love a product over many users who like it
14. Be paranoid when things are going well
15. Be optimistic when things are going poorly
16. Respect and care about users
17. Focus on what competition does well. Steel man their decisions
18. Never sell to a willing buyer if you don’t believe it’s actually going to help them
19. Avoid zero sum or negative sum games
20. Remember rule 1 and 2
Tabflows 🏴☠️ retweeted
One thing the engineering community will (re)discover is that every program can be ① hardened (edge cases squashed, inputs tightened, errors handled) and ② optimized (profiled, benchmarked, rewritten) basically ad infinitum.
There are real costs in every direction: time, attention, opportunity. You can literally explore input spaces that will never be hit or optimize performance of something that will never be used ("you have no users".) Even in an infinite token world, you need to know when to stop and what tradeoffs to accept. Agents will happily drill no matter what.
Tabflows 🏴☠️ retweeted
1. Oh shit, AI can do my job better than me
2. Software engineering is dead!
3. I can vibe code as much slop as I want!
4. Oh, things are not going well. Fable/Sol/Opus all suuuck
5. But what if I constrain the agent? Put it in a straitjacket?
6. Oh, the results are pretty good now. How do I go deeper?
7. *Orders 12 software engineering books from Amazon*
8. Software engineering is alive!
Tabflows 🏴☠️ retweeted
Oh shit I just realised
that grilling
is where the meat and the metal interact
Tabflows 🏴☠️ retweeted
My hot take from chatting to @poteto is that we should use MORE abstractions in the AI age
You can use them (combined with harsh lint rules) to reduce the design space available to the agent and constrain them only to good decisions.
Combined with the fact that high-leverage abstractions let you do more with less code - so, more token efficient.
Plus, unwinding the damage from a bad abstraction is much cheaper with agents.
This runs counter to a lot of folks thinking that agents just want to read the raw code. They can, but they're not maximally efficient that way.
Be braver! Design abstractions.
Tabflows 🏴☠️ retweeted
Devs will make their agent wait on the rust compiler rather than admitting golang is the best agentic language
Tabflows 🏴☠️ retweeted
I want a harness that doesn’t write code for me, but instead tells me what I should do and then forces me to write the code. Imagine me basically trying to build something but instead of it writing code for me it’ll tell me what I need to write and then I can ask follow ups and it will point me to API docs, but it will never write a single line of code. I think this is the best way to stay grounded and continue to be a programmer if that’s something you wanna do that way you’re learning at much faster speeds. You’re basically guaranteed to arrive at the most optimal stack overflow link like the good old days.
Tabflows 🏴☠️ retweeted
Why should the specific harness that someone is using matter at all to the server? This is like making sure only Firefox can access your website - makes no sense at all.
