Oskar Person

AI architect

[Oskar Person @PersonOfData]

This aged well

[Andrej Karpathy @karpathy]

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.

[Andrej Karpathy @karpathy]

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.

[Oskar Person @PersonOfData]

@HenHpodcast ik heb dit gevonden door zoekoen voor “bijbaan” 👌 welkom op X!

[Oskar Person @PersonOfData]

@HenHpodcast ik heb dit gevonden door zoekoen voor “bijbaan”👌

[Oskar Person @PersonOfData]

@todayyearsold you can also do it on MacOS with ctrl+fn+backspace+alt after you pay 9.99$ for a shortcuts app that you can swiftly configure in just 7 steps

[Oskar Person @PersonOfData]

@Zephyr_hg NEWS

[Oskar Person @PersonOfData]

@odedbendov @jack indeed!

[Oskar Person @PersonOfData]

@LiderowDr tak!

[Oskar Person @PersonOfData]

Great overview of building production-ready backends!

[alex fazio @alxfazio]

https://t.co/MIVbN9mKbP

[Oskar Person @PersonOfData]

Good question about a key mechanism of the law

[Richard Field @tyillc]

@elonmusk So what elected body would get the privilege to fire these judges every year ... say the Senate ... so the first judges to go would be every conservative appointee to the Supreme Court ...

Another idea best left not tweeted ...

[Oskar Person @PersonOfData]

@ChamberofFit Fantastic guide!!!

[𝐏𝐀𝐏𝐀𝐖𝐄𝐑𝐘𝐍𝐀 @Papaweryna_]

Przed chwilą dzwoniła do mnie firma windykacyjna.
Szok lekki, no bo jak, skąd?

Mają mój pesel, imię nazwisko, pani nawet powiedziała, że wie kiedy mam urodziny.

Okazuje się, że kiedyś, ponad 20 lat temu, wzięłam sobie jakiś numer z @Orange_Polska (którego wtedy nie było) i … nie wiem co w sumie. Nie płaciłam? Nie wiem, bo nikt mi nie chce powiedzieć.

Od ponad 20 lat mam ten sam numer telefonu, który nigdy nie był na mnie. Nigdy na moje nazwisko, nigdy moje dane.

@Orange_Polska twierdzi, że sprzedał mój rzekomy dług i nic mi nie może już powiedzieć, bo to nie ich sprawa, poza tym… RODO! Tak, dobrze czytacie - RODO w Orange jest tak silne, że nawet we własnej sprawie nic się nie dowiesz.
Mam wyjaśniać z firmą.

Firma windykacyjna (liczba gwiazdek 1) twierdzi, że skoro dług kupili, to dług jest i mam go spłacać.

Więc jest tak: Nie wiem skąd, nie wiem gdzie, ale mam podobno dług @Orange_Polska który ma 25 lat. Przez 25 lat rzekomego długu, nikt do mnie nie zadzwonił, nie napisał, nie poinformował, nie wysłał monitu, choć jestem ich klientką od ponad 20 lat i rozmawiałam z nimi setki razy.

Tylko czekam, aż firma windykacyjna wrzuci mnie w BIK i pewnie nigdy nie dowiem się dlaczego, bo nikt nie chce mi nic powiedzieć.
Nie wiem w jakim mieście „ktoś” zaopiekował się moimi danymi, w którym salonie i kto, czy to był abonament, telefon na kartę? Archiwum X.

W @Orange_Polska jest cała moja rodzina od ponad 20 lat, telefony, telewizja, internet, zakupy aparatów. Rachunki noszę w zębach każdego miesiąca.

Chcę podziękować drogi @Orange_Polska za szacunek do stałych klientów, za wsparcie i pomoc.
To mój ostatni rok, kiedy jestem waszą klientką.

Sprawę będę monitorować i opisywać.
Proszę 🙏 was o RT.

[Oskar Person @PersonOfData]

@tom_doerr Great! Have a good coffee!;)

[Oskar Person @PersonOfData]

I see that it works now, so I try to express my message again I often find your content emotional and highly opinionated. But you have also held your ground in defending the truth. I believe that seeking the truth is aligned with the objectives of this platform and Elon Musk himselfit is certainly aligned with my objectives therefore, I continue supporting your account.

[Oskar Person @PersonOfData]

@DrLoupis @elonmusk I just tried to reply to this post, but then got a notice that replying to deleted posts is not possible.

[Oskar Person @PersonOfData]

@DrLoupis @elonmusk test

[Oskar Person @PersonOfData]

“Above all, don’t lie to yourself. The man who lies to himself and listens to his own lie comes to such a pass that he cannot distinguish the truth within him, or around him, and so loses all respect for himself and for others. And having no respect he ceases to love, and in order to occupy and distract himself without love he gives way to passions and coarse pleasures, and sinks to bestiality in his vices, all from continual lying to other men and to himself. The man who lies to himself can be more easily offended than any one. You know it is sometimes very pleasant to take offense, isn’t it? A man may know that nobody has insulted him, but that he has invented the insult for himself, has lied and exaggerated to make it picturesque, has caught at a word and made a mountain out of a molehill—he knows that himself, yet he will be the first to take offense, and will revel in his resentment till he feels great pleasure in it, and so pass to genuine vindictiveness.”

[Dylan O'Sullivan @DylanoA4]

There are whole books on psychology that don't get anywhere near this paragraph from Dostoevsky

[Alexej Jordanov @alexejjordanov]

With @wmiddelkoop: "The New World Order: West and BRICS moving towards WW3"

Topics:
- The decline of the dollar and the rise of BRICS
- Cycles of financial crises and inflation patterns
- The strategic importance of gold and silver
- The future of commodities in a new financial system
- Potential war betwen the West, China, and Russia

Watch the full interview on our English @GoldRepublic Youtube (link below)

[Oskar Person @PersonOfData]

None of my business but hey, you came here for advice… understand that the narcissistic behavior she displayed might be a disorder. If she was ready to weaponize her own children, there are clearly no boundaries. She might even make an attempt at your or your children’s life. So:
1. Prioritize yours and your kid’s safety, establish a safe distance (boundaries!!!) and reevaluate.
2. Get professional help of a lawyer and a psychologist. Better pay for 1 hour with a top pro than 10 hours with an amateur. These people are qualified to give advice, your nearest and dearest are likely not.
3. Grief, allow yourself space for that with a best friend or a family member. Your nearest and dearest should be there to give you emotional comfort. If they are not doing that, put those relationships on pause until you recover.