Joaquin

[Joaquin @joakin]

@GosuCoder It's a very good model, it bullshits less than Claude. I love how dry and direct it is.

What reasoning do you rock it with? I usually do medium and low, but lately for some things I've been using xhigh and I've been surprised by it, can be slower but more nuanced and thorough

[Joaquin @joakin]

@valigo First paragraph is pure rage bait 😆

SPLIT COLUMNAR KEYBOARD 4LIFE!!1

[Armin Ronacher ⇌ @mitsuhiko]

This is such a good post. https://t.co/IdmAnh18Nt

[Joaquin @joakin]

@djsmith42 I think you are right, but if you think those things don't happen in office or are solved automagically I would say you are wrong. The disfunction may be different or less obvious but it can be as damaging.

I think the failure modes are just different and show in different ways

[Nic Barker @nicbarkeragain]

@ThePrimeagen My happy place when programming these days is when I can go days on a project without having to use the internet once, because I have control over almost everything. When I need something, I figure it out and implement it myself. Feels like when I first started as a kid.

[Joaquin @joakin]

@iamdavidhill Gpt 5.7 pro? 🤔

[Joaquin @joakin]

@badlogicgames Is it gpt 5.5? It does love making single use small functions... It's annoying. It's even worse when the fun just wraps one line of code. Like... C'mon!

[Joaquin @joakin]

@jordwalke

[Adam @adamdotdev]

It's 2026 and your CEO just sent you a 2,400 line pull request.

You get a cup of coffee and sit down to review it.

It's a disaster. A dozen unrelated refactors. Unused methods with names like `convertFromBase10` and `normalizeBeforeSerialization`.

You catch a few hardcoded API keys, but that's ok. It's part of the dance. They didn't consider that someone might look at this diff. Here's a comment buddy.

They respond in an hour (after Copilot, qodo, CodeRabbit and Greptile finish their reviews) saying we shouldn't worry about "implementation details" anymore, those are relics of the past. Hey let's jump into a room and figure it out. We can't just agree to disagree, this is probably my last job in tech and I can't watch this fucker burn the place to the ground.

The PR merges and goes to prod. You feel a shared sense of apathy and dread with Hannah the intern (she has to review his AI generated social media posts ever since Grok got too imaginative).

That night you go to sleep and have nightmares of that code. You can still see the shapes of it on the backs of your eyelids.

You go to work the next day ready to quit. You no longer understand the system. There is no foundation. Time to use those savings and an SBA loan to buy a liquor store and never login to GitHub again.

[Mario Zechner @badlogicgames]

recommended reading. strongly recommended reading.

i really like the pain avoidance angle. slots into my "paon/friction is when you learn" angle. when combined > cognitive debt.

https://t.co/clzPIgXaSU

[Joaquin @joakin]

@jamwt Would go have been a viable option too?

[Nic Barker @nicbarkeragain]

Like it or not, in the world we live in now, your attention span is one of the most vital resources you have. More important than intelligence IMO. If your attention span is completely wrecked, purposefully improving it will make a huge difference to your quality of life.

[Joaquin @joakin]

@rfleury @MicrosoftLearn You are on fire lately 😆

[Joaquin @joakin]

@LukasHozda It's missing Claude anus or nipples

[Łukasz | Wookash Podcast @wookash_podcast]

Aaaand it's out! The one where @nothings writes a twin stick shooter game from scratch in C, on the spot, in 90min while answering my questions.

It's a pure joy to see Sean at work. I was amazed how quickly you can get graphics up on screen with using older OpenGL and sidestepping complexity coming from more modern APIs, when your goal is to get sth visual.

Lastly, and most importantly, if you're wondering what is the Sean's keyboard, that's the one you can see hanging on the wall behind him lol!

https://t.co/cxZrPxkUsB

[Gergely Orosz @GergelyOrosz]

In an age of slop AI content everywhere, doing >> consuming:

"Remind yourself entertainment is not learning. Instead of scroll, like, scroll: read long books, try to replicate that tutorial you bookmarked, or maybe spend some time in the docs. Push yourself to DO, not consume."

[Joaquin @joakin]

@thdxr I use handy a bunch with parakeet 3 and it's very good but it struggles sometimes when doing code things like file names or function names using the proper casing.

The Codex app has added a global shortcut to use the open AI dictation from anywhere, that one does even better

[Joaquin @joakin]

@SebAaltonen Personally it's more about the obligation than the design itself.

If they are so good why not let people decide on them.

I hate them and I hate that I can't choose alternative designs or the old ones. I've never in my life lost a cap from a bottle, it's never been an issue

[Nic Barker @nicbarkeragain]

To be a little less vague, I suspect that we're likely (not certain, but likely) to be entering into a period of unprecedented software degradation, and we're going to be seeing an increasing frequency of outages like this across many high profile products.

But IMO the cause is actually not just the-one-thing-that-everyone-is-always-talking-about, it's a number of things that have all been bubbling away at just below critical levels for a long time. Some of the things off the top of my head:

- Poorly designed / optimised software has been getting a free ride on hardware improvements pretty much since the invention of the computer. That chapter is now coming to an end, and will only be worsened by the enormous industry-wide pivot to producing & innovating on AI specific hardware, rather than general purpose CPUs etc.
- The ZIRP era created a temporary suspension of reality in our industry, and now that it's ended we need to deal with the hangover. Companies that spent years making no profit, paying extravagant compensation to employees / shareholders and giving away server time for free are now pivoting into extraction mode, which is putting further pressure on their low quality software. QA is being laid off, hardware budgets are being reduced, timelines for shipping features are becoming more aggressive, etc.
- The enormous amount of free money incentivised too many new people to join the industry too quickly. This has led to an abundance of poor quality education programs (bootcamps, uncertified colleges etc) and an influx of people into the industry who frankly aren't interested in programming. If you compared the average person in the industry now to 20 years ago, I suspect the difference in motivations would be stark. I'm not saying it's these people's fault necessarily, it's simply an inevitable result of the absurd compensation / performance expectations ratio that our industry has enjoyed for the last 15+ years. Working for a tech company has also become socially prestigious, which further adds to the problem.
- Because computer programming was once an incredibly niche area of interest, many of our fundamental systems are built on trust. We're now starting to see that if systems like open source, public supply chain, discussion spaces, education etc become flooded with bad actors, we have no real mechanisms to deal with them.
- Our hiring / recruitment pipeline has totally misaligned incentives. Even before the AI resume / AI HR-filtering arms race disaster that we're experiencing now, the widespread adoption of the leetcode style interviews IMO selected for a very narrow personality type, and filtered candidates that would have made great contributions to the industry long term.
- The pivot from purchasing long term stable releases of software, to paying a subscription for constantly updating software has done huge damage to software quality as a whole. Companies have lost their incentive to get their software "right" because they can just "fix it later", and for the consumer - you can't just go back to the version of github that still works because the new one has problems.

This was all happening well before AI entered the picture. I won't belabor the point because there has been endless discussion about it. But to me personally, there are two additional and deeply worrying problems with AI code generation.
- It's undeniable at this point that it negatively affects the people who use it. It stops juniors from getting better, and it burns seniors out and makes them hate their jobs. Like it or not, humans are still the core of this industry, and I don't see this ending well.
- It's completely unfit for purpose in the most important, high-stakes situations. One of the reasons that we excuse all the small errors it makes, is because it's low effort to type "do it again and fix this bug". That kind of thing doesn't fly when you only get one attempt because a mistake results in data loss or an outage. The damage is done.

All the above has led to a silent exodus of many of our most experienced and impactful people. There are so many amazing programmers who made enough through stock options / compensation that they didn't need to work anymore, and were only doing it because they enjoyed it. Many of these people have just quit the industry and switched to doing hobby projects in the last 5 years. These are the types of people who have the experience and foresight to prevent the types of outages that we're seeing at github today.

It's very easy to assume that the proverbial straw that broke the camel's back is entirely to blame here. But I think it's a reckoning that has been on the horizon for a very long time.

[Simon @iced_coffee_dev]

Hyped about AI? Hate AI? Have literally no opinion on AI?

I made a video about AI & agentic coding, and what it might mean for you as a developer.

https://t.co/19bOerYS6f