Guilherme

@TheEduardoRFS @foryouyeji Fiquei curioso com seus valores pra fazer esse calculo. Usei dados que eu sei que são “reais” no site indicado e, em 30 anos, o site mostra grande diferença. Ainda pra ser generoso, considerei imóvel só acompanhando a inflação e Selic a 14% por 30 anos (bem alta).

@foryouyeji Se você quiser não ter liquidez e ter um patrimônio menor sim, use uma calculadora, tem várias do tipo. Comprar imóvel e ter lucro é díficil, é uma aposta de que você sabe o que vai performar melhor que o mercado. calculadoraimovel.com.br

Financie sim uma casa, papo de coach isso ai

A few random notes from claude coding quite a bit last few weeks. Coding workflow. Given the latest lift in LLM coding capability, like many others I rapidly went from about 80% manual+autocomplete coding and 20% agents in November to 80% agent coding and 20% edits+touchups in December. i.e. I really am mostly programming in English now, a bit sheepishly telling the LLM what code to write... in words. It hurts the ego a bit but the power to operate over software in large "code actions" is just too net useful, especially once you adapt to it, configure it, learn to use it, and wrap your head around what it can and cannot do. This is easily the biggest change to my basic coding workflow in ~2 decades of programming and it happened over the course of a few weeks. I'd expect something similar to be happening to well into double digit percent of engineers out there, while the awareness of it in the general population feels well into low single digit percent. IDEs/agent swarms/fallability. Both the "no need for IDE anymore" hype and the "agent swarm" hype is imo too much for right now. The models definitely still make mistakes and if you have any code you actually care about I would watch them like a hawk, in a nice large IDE on the side. The mistakes have changed a lot - they are not simple syntax errors anymore, they are subtle conceptual errors that a slightly sloppy, hasty junior dev might do. The most common category is that the models make wrong assumptions on your behalf and just run along with them without checking. They also don't manage their confusion, they don't seek clarifications, they don't surface inconsistencies, they don't present tradeoffs, they don't push back when they should, and they are still a little too sycophantic. Things get better in plan mode, but there is some need for a lightweight inline plan mode. They also really like to overcomplicate code and APIs, they bloat abstractions, they don't clean up dead code after themselves, etc. They will implement an inefficient, bloated, brittle construction over 1000 lines of code and it's up to you to be like "umm couldn't you just do this instead?" and they will be like "of course!" and immediately cut it down to 100 lines. They still sometimes change/remove comments and code they don't like or don't sufficiently understand as side effects, even if it is orthogonal to the task at hand. All of this happens despite a few simple attempts to fix it via instructions in CLAUDE . md. Despite all these issues, it is still a net huge improvement and it's very difficult to imagine going back to manual coding. TLDR everyone has their developing flow, my current is a small few CC sessions on the left in ghostty windows/tabs and an IDE on the right for viewing the code + manual edits. Tenacity. It's so interesting to watch an agent relentlessly work at something. They never get tired, they never get demoralized, they just keep going and trying things where a person would have given up long ago to fight another day. It's a "feel the AGI" moment to watch it struggle with something for a long time just to come out victorious 30 minutes later. You realize that stamina is a core bottleneck to work and that with LLMs in hand it has been dramatically increased. Speedups. It's not clear how to measure the "speedup" of LLM assistance. Certainly I feel net way faster at what I was going to do, but the main effect is that I do a lot more than I was going to do because 1) I can code up all kinds of things that just wouldn't have been worth coding before and 2) I can approach code that I couldn't work on before because of knowledge/skill issue. So certainly it's speedup, but it's possibly a lot more an expansion. Leverage. LLMs are exceptionally good at looping until they meet specific goals and this is where most of the "feel the AGI" magic is to be found. Don't tell it what to do, give it success criteria and watch it go. Get it to write tests first and then pass them. Put it in the loop with a browser MCP. Write the naive algorithm that is very likely correct first, then ask it to optimize it while preserving correctness. Change your approach from imperative to declarative to get the agents looping longer and gain leverage. Fun. I didn't anticipate that with agents programming feels *more* fun because a lot of the fill in the blanks drudgery is removed and what remains is the creative part. I also feel less blocked/stuck (which is not fun) and I experience a lot more courage because there's almost always a way to work hand in hand with it to make some positive progress. I have seen the opposite sentiment from other people too; LLM coding will split up engineers based on those who primarily liked coding and those who primarily liked building. Atrophy. I've already noticed that I am slowly starting to atrophy my ability to write code manually. Generation (writing code) and discrimination (reading code) are different capabilities in the brain. Largely due to all the little mostly syntactic details involved in programming, you can review code just fine even if you struggle to write it. Slopacolypse. I am bracing for 2026 as the year of the slopacolypse across all of github, substack, arxiv, X/instagram, and generally all digital media. We're also going to see a lot more AI hype productivity theater (is that even possible?), on the side of actual, real improvements. Questions. A few of the questions on my mind: - What happens to the "10X engineer" - the ratio of productivity between the mean and the max engineer? It's quite possible that this grows *a lot*. - Armed with LLMs, do generalists increasingly outperform specialists? LLMs are a lot better at fill in the blanks (the micro) than grand strategy (the macro). - What does LLM coding feel like in the future? Is it like playing StarCraft? Playing Factorio? Playing music? - How much of society is bottlenecked by digital knowledge work? TLDR Where does this leave us? LLM agent capabilities (Claude & Codex especially) have crossed some kind of threshold of coherence around December 2025 and caused a phase shift in software engineering and closely related. The intelligence part suddenly feels quite a bit ahead of all the rest of it - integrations (tools, knowledge), the necessity for new organizational workflows, processes, diffusion more generally. 2026 is going to be a high energy year as the industry metabolizes the new capability.

remember/recognize

Always seeing people praise Turing so quickly while they don't even recognize the name of Church is weirdly annoying to me (maybe the Imitation Game movie + Turing machines more commonly taught in CS effect). en.wikipedia.org/wiki/Church%E2…

@hehehenrihenri Apple cat

@hehehenrihenri Oh, it’s literally orb lol

@hehehenrihenri Name pls

the orb anime is GOATED. i can't stop watching this

@devatreides congratzz

Balões e tals..

@hehehenrihenri Hehe

I spent so much money the past month I'm broke now

@noghartt Structured Outputs. If the model does not support that: - You can define a grammar to follow for the LLM output, i.e. in case you're using llama.cpp: github.com/ggerganov/llam… - You can try to enforce the output by prompting and fine-tuning as well (that's the worst option)

thinking about testing LLM outputs, would have a way to simulate or apply a kind of deterministic simulation testing for LLMs? given a set of "properties", it should assert that the LLM output follows it

@VictorTaelin Gemini 2.5 might be a good balance, but I need to test it more.

@VictorTaelin Meanwhile, Sonnet tends to be the complete opposite, sometimes doing even more than I asked for, which is also annoying, but less annoying than receiving an incomplete answer.

I don't understand why o3 is so bad at generating complete files. You ask it to port a 1000-LOC file, and it gives you a 200-LOC file with 20% of the contents and features. Which is a shame because the model is actually really smart. I wonder if this will be fixed on o4

@vitorsalmeida_ LOL

@hschmaiske same as quality of life (with quality of life, I meant stuff like security); it depends on where you gonna live

@KindSloth How about safety?

Pros vs cons of living in São Paulo?

@hschmaiske - Infrastructure, in general, is probably the best in the country by quite a margin Cons: Costs and Traffic 🫠

@hschmaiske Pros: - You have everything here; All types of cuisine if you enjoy going to restaurants, all types of entertainment, all types of courts if you like to play sports, etc. - Good quality of life depending on where you gonna live, ofc (More on the 🧵 …)

are* I won’t pay Elon to edit tweets. Mistakes happens and you need to deal with it

Bad assumptions usually is the cause of all problems

tech literacy is falling bc kids don't have to google about port forwarding to play minecraft with friends anymore