janpeuker

Armin is a hero

I don't think it's a paradox at all and it might also be a hint why the word is used in the title: Using AI makes you _want slaves_, and I think it creates a culture of treating people who do the boring work the same way. For me that's what Enshittification and The Annoyance Economy mean: The mindset that because I optimize better than you, I now own you - and people notice that disdain not only against themselves, but when being forced to use it against their best intentions against others, too (e.g. yelling at chatbots doesn't make you feel good).

Thank you. I stood against Maven back then so I salute you.

+1 especially on (2). In that sense the article being from 2023 is itself interesting as a document of change. The article mentioned no one cared about Bezos for example, but with Data Centers wreaking havoc on communities with energy prices, water supply and noise while he takes over Venice, suddenly it was in people's backyards and turns out they do care.

On (1) I do like "Annoyance Economy" as an extension of that (https://www.nytimes.com/2026/04/12/business/annoyance-econom...)

Gotta appreciate the hook solution to save context and cost

I love the app idea but I don't think it's beginner friendly - for example it starts zoomed out of the globe and there is no button to zoom to the location; also it's unclear what the hatched lines until one zooms in.

The idea of this liminal space (J-space) during inference reminded me of the concept of the "error flow reservoir" during training: https://elonlit.com/scrivings/a-theory-of-deep-learning/. Would be interesting to see if they are somehow connected.

Exactly - Readability Review [1] at Google was tedious but I generally liked the idea of having 2 separate discussions with different goals

1) https://abseil.io/resources/swe-book/html/ch03.html#readabil...

Simon Wardley made an important comment on LinkedIn which is worth repeating here because I really feel the settler-colonial language here is unhelpful and obnoxious (what are we implying with 'legends are formed from chaos', destroying everything that exists before and erasing its history is good?):

PST (pioneer-settler-town planner) is just the original naming of EVT (explorer - village - town planner). I changed the naming because after 18 years of doing this, I finally accepted the colonialist overtones of the original naming. That was 3 years ago.

This is an extremely common technique against investigative reporting, in particular because certain social media / blogging platforms allow backdating posts [1]. So people just copy your post, claim DMCA, and then take it down quickly after.

1) https://news.ycombinator.com/item?id=39355869

Started Claude Code and showed me an orange warning "3 MCP servers need authentication" - turns out they are for claude.ai Gmail, Google Calendar and Drive. Thanks enshittification.

I’d be in favour of a law that if a product cannot reasonably be purchased legally obtaining it via other means is not piracy (e.g. in my country 80% of movies are not available simply because the market is too small, even though I would be ok with English - I still don’t want to pirate so I buy physical media)

Paper under https://arxiv.org/abs/2606.23050

(As a side note, I do OCR locally as a small RAG for citations I read in books and also chunk input, but merely to save RAM - interesting this natural approach also work in a streaming model)

The biggest issue I've seen with people burning through tokens is using very long sessions, especially starting with plan mode and then "iterating" over extended periods. I was burnt badly by extra usage so now I run on $20 Pro. I ruthlessly create new sessions/agents, always ask to create markdown files first (no plan mode) and minimise context aggressively - for example I have a lot of skills that use lazy loading and a small local MCP for lookups plus openrouter with a local model for image detection and fulltext search. Basically I use Claude Code in pi.dev style.

This is beautiful. I even had people reach out to me with suspiciously long "long time no chat" instant messages until I realised they were AI written (in one case misspelling the name of their own partner). "If you are requesting human attention, demonstrate human effort" is going to be my new answer to that!

Ban the domestic use of fully autonomous weapons.

"Domestic" is an interesting shift here from the earlier _general_ discussions on autonomous weapons. So robot imperialism is good for Dario. But the imperial boomerang is a thing, in which case the proposed regulation itself is smoke and mirrors or just regulatory capture?

workflow improvements that would have taken days or weeks of engineering

It's a nice article and good point but I feel "design" in the title is misleading - the example given has an extremely reduced visual or spatial scope (something models are still not good at). The post is more about rapid prototyping.

I find it so interesting "Agent legibility is the goal" picks up James C. Scott term (without defining it, so I assume that's what they mean) which is _not a good thing_. Legibility is a governance effort to box in life.

I bought a Super Nintendo Mini and it's the best thing ever - children love it and don't feel left out of digital entertainment

ERR_CONNECTION_TIMED_OUT

Ah yes, EU Sovereignty when a post makes it to the HN front page.

Great post showing the ironic revenge of opinionated architecture in times of cheap code. Exactly what LLMs can’t deliver, they always seem to be bias towards added complexity, not simplification.

Outsourcing usually gives you exactly what you pay for, arguably more transparently than other ways. It’s just that transparency (i.e. the price for quality) is sometimes not passed on from management / procurement taking that decision down to the team eventually having to work in a distributed fashion.

I think that’s also where the assumptions of the original post are off - the difference between DeepSeek and a frontier model is not usually what low quality outsourcing can cover. So you probably end up paying a highly qualified outsourced engineer who may not be significantly cheaper (most outsourcing is not just due to cost but capacity and capability).

Thanks for clarifying the rule - I wasn't aware of that and follow it next time. But I also don't think it's a marketing link. The post explains why specifically in the cases of transaction fraud other signals are important, with specific SQL examples, and that should translate to any other payment provider.

I agree the post looks a little AI written but generally this kind of analysis is quite common. Leaving aside human heuristics that are generally too well known to catch real scammers (like time travel or "7 days", which is bad because often weekly patterns are important so at the very least look at 10 days) and actually have low precision, what I find odd it that all results just return a user ID.

So this is really just surfacing cases, but with not enough context to be useful to prioritise. I would expect a score to be included.

Apart from that it misses a lot of signals like refunds, declines, disputes etc [1].

1) https://stripe.com/gb/guides/improve-fraud-management-with-r...

While I agree most of this seems to go too far I do like the idea of the Socratic mode with State-Challenge-Reflect reflection. I often use LLMs in the same way with a skeleton "brief" document and separate chapters that I ask it to fill based on my input, basically augmented note taking (such as references, coherence, in-scope vs out of scope, arguments considered, pressure points, vulnerabilities etc)

Excellent text and Winner's "Cyberlibertarian Myths And The Prospects For Community" is a milestone.

Further reading:

1) Barbrook, Richard, and Andy Cameron. ‘The Californian Ideology’. Science as Culture 6, no. 1 (1996): 44–72.

2) Harvey, David. Spaces of Neoliberalization: Towards a Theory of Uneven Geographical Development. Franz Steiner Verlag, 2005.

3) Turner, Fred. From Counterculture to Cyberculture: Stewart Brand, the Whole Earth Network, and the Rise of Digital Utopianism. University of Chicago Press, 2006.

4) Mirowski, Philip. Never Let a Serious Crisis Go to Waste: How Neoliberalism Survived the Financial Meltdown. Verso, 2013.

5) Brown, Wendy. In the Ruins of Neoliberalism: The Rise of Antidemocratic Politics in the West. The Wellek Library Lectures. Columbia University Press, 2019.

6) Greer, Tanner. ‘The Silicon Valley Canon: On the Paıdeía of the American Tech Elite’. The Scholar’s Stage, 21 August 2024. https://scholars-stage.org/the-silicon-valley-canon-on-the-p....

7) Stevens, Marthe, Steven R. Kraaijeveld, and Tamar Sharon. ‘Sphere Transgressions: Reflecting on the Risks of Big Tech Expansionism’. Information, Communication & Society 27, no. 15 (2024): 2587–99. https://doi.org/10.1080/1369118X.2024.2353782.

8) Lewis, Becca. ‘“Headed for Technofascism”: The Rightwing Roots of Silicon Valley’. Technology. The Guardian (London), 29 January 2025. https://www.theguardian.com/technology/ng-interactive/2025/j....

9) Bria, Francesca, and José Bautista. ‘The Authoritarian Stack’. Friedrich-Ebert-Stiftung (FES) Future of Work, 8 November 2025. https://www.authoritarian-stack.info/.

10) Durand, Cédric, Morozov, Evgeny, and Watkins, Susan. ‘How Big Tech Became Part of the State’. Jacobin, 24 November 2025.

11) Spiers, Elizabeth. ‘The Anti-Intellectualism of Silicon Valley Elites’. Elizabeth Spiers, 1 April 2026. https://www.elizabethspiers.com/the-anti-intellectualism-of-....

The European Payments Initiative (Wero) made the mistake of only aiming for Peer-to-Peer QR code payments, carefully avoiding competing with cards so each country could keep their card schemes (Cartes Bancaires, Girocard etc). I don't think it will ever even _compete_ with cards in the near future.

Europe already has plenty of alternative card systems e.g. France's Cartes Bancaires (CB) and ironically Germany just last year turned it's Girocard/Maestro system off in favour of Visa/Mastercard; the problem is the banks in individual countries in Europe are not willing to give up their control in favour of a compatible standard.

Lots of other Asian countries already did something similar, e.g. Singapore had PayNow QR Codes (probably the closest to Pix) since 2017, Thai PromptPay was even earlier and India UPI (slightly different wallet system) since 2016. China was even earlier but different though private superapps.

What has changed, and I find interesting, is that Card rails are more and more used for political pressure [1], and I feel the "American hemisphere" is probably the reason Pix gets more of this pressure than Asian countries.

1) https://www.icc-cpi.int/news/icc-strongly-rejects-new-us-san...

Yes I get the irony but also let's not forget that it's over for the Code that Uncle Bob likes. Which is bad, verbose, dogmatic, unreadable, elitist code [1] with "discipline" [2] and a dash of sexism. And that has luckily been over for a _long_ time before LLMs.

1) https://qntm.org/clean

2) https://blog.cleancoder.com/uncle-bob/2017/10/04/CodeIsNotTh...