Brazilian who became Canadian. Building AI agents at @Shopify. I like systems thinking, simplifying things, and JRPGs that don't require reflexes.
Toronto, Ontario
Joined August 2007
- Tweets5.9K
- Following752
- Followers985
- Likes24.8K
dirceu retweeted
Sometimes it's better to focus less on BEING a thing and focus more on MAKING things
I've known a lot of people who called themselves writers and never actually got around to releasing a book
Let go of the identity. Focus on the product.
dirceu retweeted
Message threads are now in public beta on the Messages API.
The API caches your conversation on the server between turns, so instead of resending the full conversation, you send only new messages and the previous message ID, and Claude starts responding sooner.
dirceu retweeted
IaC isn't dying, it's becoming more essential. Non-deterministic layers add new volatility to the stack, but they don't break the core principles. For example, it's becoming more obvious that we want some layers to be truly reproducible.
dirceu retweeted
an era of abundance where you are free to build your own "choose your own adventure" digital lego universe
...is good, actually
dirceu retweeted
Vibecoding with no understanding and learning just in time is the default for all major codebases
School brainwashed you into thinking you need to learn something first completely before doing it. No, you just do it and learn along the way. If you get stuck learn more.
Everything is figureoutable.
I like the term code archaeology but I prefer exploring the code labyrinth. You never know what you will find
it is very hard for humans to fully understand all the code even on human written codebases. I’ll share a real example from a codebase i helped maintain: React
no one, even the OG team members can fit the whole thing in their head. we have always relied on code archaeology and imperfect/JIT understanding to deal with complex software
dirceu retweeted
I've been thinking about this a bunch lately. Codebases have become organic, perhaps they always were, and we require new abstractions to do excellent engineering.
Cybernetics is back. What's old is new again, and this is the current best way to think about it. For all their flaws, Anthropic has the *exact* right idea with "SuperFans". I mean, I'm sort of in awe of how good that particular blog post was. There's this commitment to excellence that I greatly admire, and a level of AGI-pilled reasoning that meets the moment.
In my opinion, you should work with models you trust and then give them the autonomy to own part of your codebase. This doesn't mean they don't get audited, or manually checked, or interviewed - it just means that each component gets a type of guy who is obsessed with that component.
If you think about this from a higher level of abstraction, what you're really doing is enabling *zones of dynamic attention* where the models are using their fluid intelligence to design a component and then justify that component in the context of all the others. If a new one gets built that may cause issues, that model works with the model for the other component to ensure mutual compatibility. It's almost like the components themselves have come to life and are trying to figure out how best they might fit together.
The old ways of engineering are over. Codebases that are built like this will be far more competitive almost inevitably as the skill of the model surpasses that of the average programmer and sheer parallelization wins the day. Obsession over PRs, dedication to reading every line, these are vestigial neuroses that must be abandoned if we are to succeed well into the future.
Operational excellence without constant human oversight is possible with good enough models and clever enough scaffolds. The hardest part is almost always going to be turning it on and managing the first few problems. These systems will probably never be perfect, but they are the path forward.
we will need to rebuild and rewrite much of software to adapt to a new, faster pace.
code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases.
this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing.
your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos.
the time for mourning coding is long over
dirceu retweeted
we will need to rebuild and rewrite much of software to adapt to a new, faster pace.
code used to arrive one drop at a time. soon, if not already, code will be written as if it were a continuous stream, like a violent river twisting and turning as it pleases.
this is not a new thing: big tech cos have had to deal with this with the enormous scale of their engineering teams. but now ai has brought an incredibly elastic and capable workforce wielded by every engineer. this is your problem now, and the only way to adapt is to evolve your systems so agents - even and especially the ones with little context about the right way of doing things - can thrive. make the easy thing the right thing.
your codebase is becoming organic architecture. agent contributions grow around the constraints and guardrails you’ve designed. good software engineering matters even more now! and no, the continuous stream of code is not something you have to watch helplessly. be more ambitious and design systems, frameworks, and languages to control the chaos.
the time for mourning coding is long over
dirceu retweeted
usually kind of blithe about old actors dying but i kind of regard captain picard as the closest humanity has ever come to a portrayal of The Ideal Person
Patrick Stewart, 'Star Trek's' Captain Picard and 'X-Men's' Charles Xavier, Dies at 86 variety.com/2026/tv/news/pat…
dirceu retweeted
Software is not disappearing, we are producing more software than ever. What is changing is the premise. The modern foundations of software engineering has been built around encapsulation. Today, it's getting hard and sometimes impossible to defend the layering.
dirceu retweeted
The coding interview is dead, at least for my team at Anthropic. I've seen enough to know that it no longer provides signal. I removed it from loops this month.
I have a spicy, optimistic take - I think there's an opportunity for junior engineers: felixrieseberg.com/hunger-be…
dirceu retweeted
Finally summarized what I've been sending to friends in DMs View article
dirceu retweeted
after the rust rewrite I was like
wow the language doesn’t matter anymore. we can choose whatever is best instead of whatever we know best
dirceu retweeted
New talk! About the divided human & agent worlds, boundary objects, and building thicker interfaces
I've been exploring how to improve "planning", aka. deciding what agents should build, how you want it built, & making the whole team part of that process
maggieappleton.com/planning-…
dirceu retweeted
"Why is formal verification exploding NOW?"
1. Cost of proofs is going DOWN (as AI gets more capable)
2. Cost of exploits is going UP (as AI gets more dangerous)
3. Proofs exterminate exploits
4. Bonus: proof checking = perfect math/coding RL reward
The rest is economics
dirceu retweeted
one of the most interesting things about humans is that when people are honest - even in good faith - they often get brutally angry about it
Jascha at Anthropic is frankly telling students what they need to hear: there is no career security, the regime of earth-intelligence is changing and you need to transform / surf it, and it will be uncomfortable
^ this is honest and good
then this dude posts "OMG! he's EVIL for saying this!"
humans do this thing where if what someone says is something they won't WANT to hear, they get angry with the person who said it...
...and they do this INSTEAD of dealing frankly and squarely with the actual uncomfortable thing being talked about
...as if complaining and banging the table and killing the messenger will make everything better
Anthropic employee tells students at university that their career won't exist when they graduate.
Imagine the levels of psychopathy it takes to give a speech to students trying to make their future better, then telling them don't bother, don't plan for the future, your degree is worthless and you wont have jobs.
dirceu retweeted
What a surreal time to be releasing this work, on a day when the number of CVEs being discovered is exploding - well, Theorem in partnership with Anthropic introduces a brand new way to programmatically discover bugs and get provable security guarantees on your software. So proud of my team!
New on our Frontier Red Team blog: using Claude to formally verify software at large scale.
Formal verification can prove that code is free of certain bugs, but historically it has only been feasible for small codebases (or required a lot of expert time).
With AI models, however, this is beginning to change. In collaboration with @theoremlabs, we used Claude to prove security properties in over one hundred real-world open-source libraries over the span of a few weeks.
Read our research in full here: anthropic.com/research/forma…
