petval 💙💛

Man of 1 dad of 3. Sw developer, former yoga & mindfullness teacher, avid skier. Curious in mind, society, tech, human rights, dance, psychedelics, sex
🇨🇿🇪🇺

[petval 💙💛 @_petval]

@UsmevavyA Gaussova křivka je neúprosná a v kombinaci s demografickým trendem a všeobecným volebním právem činí populismus nejvýhodnější volební strategií.

Pokud se to těm, kteří tu šarádu svou produktivitou platí, nelíbí, musí vymyslet funkční řešení. Skupinové nebo individuální.

[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.

[petval 💙💛 @_petval]

@enkocz Daniel Drake je asi slušná nastavprdel. Šmejdi.

[petval 💙💛 @_petval]

@MotejlekSkocdop Člověk nemusí být pokrytec, když nepotřebuje být falešná mocichtivá svině.

[petval 💙💛 @_petval]

@MotejlekSkocdop Těším se na fázi, kdy Trump v koutě začne tvrdit, že za to všechno nemůže on, ale jeho zdravotní stav, kognitivní nemoc tak úžasná a nová a vážná, jakou ještě svět neviděl, a kterou dokáže zvládat jen stabilní genius jako on 😁

[Thomas C. Theiner @noclador]

Italian news has begun to call ICE "Trump's squadristi".

Squadristi, as every Italian knows, were members of Mussolini's "squadre d'azione", which raped, tortured, mutilated, murdered opponents of fascism... but in Italy the government never paid the squadristi a salary.

[petval 💙💛 @_petval]

@ZelenskyyUa I hope you have plan B and route around him like the plaque he is.

[petval 💙💛 @_petval]

@narendramodi Nazi concerned about another Nazi.

[petval 💙💛 @_petval]

@PeterMcCormack https://t.co/Ox51c0cuyF

From Czechia with love

[petval 💙💛 @_petval]

I wonder how many countries have plans or are working on them to remove Trump and Vance from the equations.

I bet Russia does not.

[petval 💙💛 @_petval]

@BrigidLaffan @Artemisfornow Because labeling something as hate is easier and attractive to many compared to dealing with its content and gist of its point.

Eg. argumenting about uselessness & backwardness of religion, using satire on it, can endanger the commenter really quickly. Ask Rushdie or Van Gogh.

[petval 💙💛 @_petval]

@Artemisfornow Central Europe will block it. We still have experience with nazis, communists and Soviets.

Irish antisemite catholic lunatics can go fu.k themselves.

[petval 💙💛 @_petval]

Truman:

​"I don't care for it. It’s a raw deal. I got word of it this morning. You know who told me? Marshal Stalin told me. He told me they shelled the Chancellery... forced that poor fella in the bunker to take his own life. I tell you, I was sore as hell about it."

[Aaron Rupar @atrupar]

Trump on a report that Ukraine tried to strike Putin's residence: "I don't like it. It's not good. I heard about it this morning. You know who told me about it? President Putin told me about it ... I was very angry about it."

[Drew Pavlou 🇦🇺🇺🇸🇺🇦🇹🇼 @DrewPavlou]

Australian police just called me at 8 PM at night to demand I delete one of my X posts about the Bondi terrorist massacre.

I thought they were calling me to offer me protection because an ISIS preacher in Sydney publicly threatened me online today.

But Queensland police instead called me to demand I delete a post I made criticising someone who said murdering 15 Jews was not anti-Semitic.

I asked them what law I broke. They told me I hadn’t broken the law but they still wanted me to delete the post.

I politely informed them that this wouldn’t be happening.

This is insane. This is Australia now. Police phone calls at night to try intimidate normal Australians into deleting Tweets. With no reference to the law at all.

Meanwhile jihadists are still allowed to run wild with zero penalties.

Two tier legal system.

[petval 💙💛 @_petval]

@plavacek Už jsem to viděl víckrát. Nejdřív potřebují řešit problémy a náklady akceprují. Po vyřešení a maximální automatizaci pak vidí IT jako zbytečný náklad. Schopni odejdou a může začít nový cyklus 😁

[petval 💙💛 @_petval]

@MichaelAArouet If real estate value implodes, young people can finally afford to buy places where they can have enough sex to reproduce. No pensions? Tough but if older people created such world, they should live its consequnces.

[petval 💙💛 @_petval]

@anders_aslund Condemn? Sanction that c.nt and his gang businesses.

[petval 💙💛 @_petval]

@TomasRoud ÚS: "a přesto se rozhodl řešit situaci protiprávní svépomocí"

Ničeho se zákeřný stát nebojí víc než lidí, kteří se nebojí chránit sebe sama. Monopol na použití síly si přece uzurpuje on.

A pak se diví, že v sobě lidé nemají odvahu a vůli bojovat, přitom je aktivně vykořeňuje.

[Khaled Hassan @Khaledhzakariah]

🚨🚨Important update: Cairo has outright rejected Starmer’s reported assertion that he was unaware of Alaa’s record of incitement to violence, maintaining that British officials were explicitly briefed on the matter.

Late tonight, I received a message from a well-connected Egyptian source indicating that the Egyptian government may be considering revoking Alaa’s Egyptian citizenship.

The apparent aim would be to shut down any discussion in the UK about revoking his British citizenship. Such a move would place the British government in a bind, as UK law prevents the removal of citizenship if it would render an individual stateless.

If pursued, this would be a calculated attempt to embarrass Starmer and force Britain to retain responsibility for Alaa, as well as teach Britain not to pressure Cairo over human rights-related cases in the future.

The message is clear. You got involved. You didn't need to. It's your mess now.

[petval 💙💛 @_petval]

@GibisVB Mrtvotvůrce

[petval 💙💛 @_petval]

@Mio_Mind @cpaforerp Or when I tell somebody world will be a better place if they remove themself from it 😁

Many Americans will say "their platform, their rules" and still fail to understand Europe has their own rules too and same logic applies.

There are too many mislead simpletons, globally.