Piotr Tobiasz

opencode 1.3.0 will no longer autoload the claude max plugin we did our best to convince anthropic to support developer choice but they sent lawyers it's your right to access services however you wish but it is also their right to block whoever they want we can't maintain an official plugin so it's been removed from github and marked deprecated on npm appreciate our partners at openai, github and gitlab who are going the other direction and supporting developer freedom

41% of all code shipped in 2025 was AI-generated or AI-assisted. The defect rate on that code is 1.7x higher than human-written code. And a randomized controlled trial found that experienced developers using AI tools were actually 19% slower than developers working without them. Devs have always written slop. The entire software industry is built on infrastructure designed to catch slop before it ships. Code review, linting, type checking, CI/CD pipelines, staging environments. All of it assumes one thing: the person who wrote the code can walk you through what it does when the reviewer asks. That assumption held for 50 years. It broke in about 18 months. When 41% of your codebase was generated by a machine and approved by a human who skimmed it because the tests passed, the review process becomes theater. The reviewer is checking code neither of them wrote. The linter catches syntax, not intent. The tests verify behavior, not understanding. The old slop had an owner. Someone could explain why temp_fix_v3_FINAL existed, what edge case it handled, and what would break if you removed it. The new slop has an approver. Different relationship entirely. Arvid’s right that devs wrote bad code before AI. The part he’s missing: the entire quality infrastructure of software engineering was designed around a world where the author and the debugger were the same person. That world ended last year and nothing has replaced it yet.

@willmcgugan list out the things you want to see and do. think how much time you need for each location. plan 1-2 things for each day. go out for breakfasts and dinners. tbh, rest will figure itself out.

Any digital nomads in my feed? I want to balance work with enjoying the experience of travel and living in Asia. But I feel the draw towards taking on more work. Not for financial reasons. I just fall into habits developed over 3 decades. How do you ringfence time away from the laptop?

@karpathy @lauriewired peak delusions. this is the greatest authority in the ai hype bros world?

@lauriewired Grandma certainly shouldn’t have to know apps or that there is an app. Her LLM agent should.

Very interested in what the coming era of highly bespoke software might look like. Example from this morning - I've become a bit loosy goosy with my cardio recently so I decided to do a more srs, regimented experiment to try to lower my Resting Heart Rate from 50 -> 45, over experiment duration of 8 weeks. The primary way to do this is to aspire to a certain sum total minute goals in Zone 2 cardio and 1 HIIT/week. 1 hour later I vibe coded this super custom dashboard for this very specific experiment that shows me how I'm tracking. Claude had to reverse engineer the Woodway treadmill cloud API to pull raw data, process, filter, debug it and create a web UI frontend to track the experiment. It wasn't a fully smooth experience and I had to notice and ask to fix bugs e.g. it screwed up metric vs. imperial system units and it screwed up on the calendar matching up days to dates etc. But I still feel like the overall direction is clear: 1) There will never be (and shouldn't be) a specific app on the app store for this kind of thing. I shouldn't have to look for, download and use some kind of a "Cardio experiment tracker", when this thing is ~300 lines of code that an LLM agent will give you in seconds. The idea of an "app store" of a long tail of discrete set of apps you choose from feels somehow wrong and outdated when LLM agents can improvise the app on the spot and just for you. 2) Second, the industry has to reconfigure into a set of services of sensors and actuators with agent native ergonomics. My Woodway treadmill is a sensor - it turns physical state into digital knowledge. It shouldn't maintain some human-readable frontend and my LLM agent shouldn't have to reverse engineer it, it should be an API/CLI easily usable by my agent. I'm a little bit disappointed (and my timelines are correspondingly slower) with how slowly this progression is happening in the industry overall. 99% of products/services still don't have an AI-native CLI yet. 99% of products/services maintain .html/.css docs like I won't immediately look for how to copy paste the whole thing to my agent to get something done. They give you a list of instructions on a webpage to open this or that url and click here or there to do a thing. In 2026. What am I a computer? You do it. Or have my agent do it. So anyway today I am impressed that this random thing took 1 hour (it would have been ~10 hours 2 years ago). But what excites me more is thinking through how this really should have been 1 minute tops. What has to be in place so that it would be 1 minute? So that I could simply say "Hi can you help me track my cardio over the next 8 weeks", and after a very brief Q&A the app would be up. The AI would already have a lot personal context, it would gather the extra needed data, it would reference and search related skill libraries, and maintain all my little apps/automations. TLDR the "app store" of a set of discrete apps that you choose from is an increasingly outdated concept all by itself. The future are services of AI-native sensors & actuators orchestrated via LLM glue into highly custom, ephemeral apps. It's just not here yet.

@willmcgugan ban immediately. it is author's responsibility to make sure pr is ready to be submitted. all these ai slop prs that are flooding oss is just pure lack of respect to maintainers' time.

Ok, so you can reason with these bots. What is the point? Why would someone say to a bot go and spam Open Source projects?

everyone's talking about their teams like they were at the peak of efficiency and bottlenecked by ability to produce code here's what things actually look like - your org rarely has good ideas. ideas being expensive to implement was actually helping - majority of workers have no reason to be super motivated, they want to do their 9-5 and get back to their life - they're not using AI to be 10x more effective they're using it to churn out their tasks with less energy spend - the 2 people on your team that actually tried are now flattened by the slop code everyone is producing, they will quit soon - even when you produce work faster you're still bottlenecked by bureaucracy and the dozen other realities of shipping something real - your CFO is like what do you mean each engineer now costs $2000 extra per month in LLM bills

@Elonov_MMA watching it live was magical

Still can’t believe Ilia slept Islam on last nights card. Didn’t see much of it on the timeline so I think a lot of people must’ve missed it

Here is my take on why Elixir is the best language for AI: immutability, documentation, stability, and tooling for coding agents. It builds on the recent study in which Elixir had the highest completion rate across models among 20 different languages. Link in the thread below.

If you put the Apple icons in reverse it looks like the portfolio of someone getting really really good at icon design

@xico_com_xis @levelsio holey fuck this is ugly. european design is so dead.

@levelsio If price doesn’t matter, maybe the new Mercedes Cla? Although its less tall, maybe more akin to model 3

What's the superior European alternative to a Tesla Y 2025?

@FrancescoCiull4 “Developer Advocate” how fucking ironic

@FrancescoCiull4 This post is shameless. You are hearing about this, Mr “Dev Advocate”, because of the outburst of the “crowd” that is actually worried about AI impact on the world. But you don’t even understand what happened and why. Just keep on yapping the same narrative over and over.

Tailwind just fired 75% of its staff, and revenue is down ~80%. It's a sad day for developers. The "AI won't replace you" crowd has been awfully quiet today. AI is advancing too rapidly, and open-source tools are struggling to keep pace. Is frontend dying? Or just evolving?

Artists have stopped sharing their works, writer's have stopped sharing their work, now engineering will stop sharing their work all thanks to generative artificial intelligence. Looks like a step backwards for humanity, what GenAI has done.

I'll say it again, I think this AI cycle we are in is a net negative on society A man/team that has made the web significantly more pleasant as a platform for many people and spent years doing so for free has AI effectively destroy the business model by first taking his work And this is how a member of the community responds. Real sad times IP theft is real and I personally think that the C-suite of these current companies deserve jail time for the level of theft they enabled

@powerofaii @PThorpe92 @MelkeyDev isnt it then a waste of time to spend time learning something that “moves so quick” and changes drastically all the time?

@PThorpe92 @MelkeyDev I feel complete opposite. If not using learning how they work when and where you can trust them etc it all moves so quick you need to use them daily plus learn.

Claude Code Pro/Max are the best investments you can make as a software engineer

@arvislacis @mikehostetler @AmpCode if you use these tools daily then this mental model doesn’t really apply. claude + copilot is ~$30. if you use them wisely, you never need to worry about the limits. at the same time, $30 can disappear in couple of days in a per token pricing, even with same usage patterns.

@ttyobiwan @mikehostetler @AmpCode It depends. Amp has no subscription so you are not tied to the "mental model" where you need to use your subscription for it to just get value. Also on Holiday preview Amp offered free $10/daily usage on Opus 4.5.

I generated 1.5 million lines of code (mostly Markdown) with @AmpCode last year AMA @mikehostetler" target="_blank" rel="nofollow noopener">ampcode.com/@mikehostetler

@willmcgugan i would say it depends on the attitude. here is a perfect example of slop producer. other day i was also chatting with some young fella who was telling me that “why worry about understanding domain of your system”. slop happens when you start to value speed over anything else.

Is AI "Slop" pejorative? And are all AI generated projects slop? At what point does something become slop?

@mitsuhiko @simonw Non intuitive? Best way of internalisation was always the struggle when working on something. The moment when you have to dive deeper to figure things out. This has now been mostly deferred to agents. The main struggle is understanding AI code, which doesn’t bring many learnings.

@simonw I want to know how “learn less” is so popular. It’s so non intuitive.

Question for developers who are leaning more heavily into coding agents (Claude Code, Codex etc) these days. Would you classify the time you spend programming as:

@josevalim inFakt, never had any issues when contracting

Now that they are introducing KSeF requirements across Poland, what are you folks using to send invoices?