habosa

These tools are explicitly marketed as a way for non-technical people to code. If we expect those same people to understand sandboxing we're dreaming.

Apple has totally failed to deliver interesting AI experiences so far ... and I still think they're going to be the dominant provider of AI in 5 years. We're just one or two advances in chips / models / both away from being able to run very good local models for free on mid-tier Apple devices. The privacy, cost, and latency story there will be too much for OpenAI/Anthropic/Google to beat.

Just writing this down so I can be praised/mocked in 5 years.

Codeapprove creator here! I made it to fill the exact gap you're lamenting, and I still think that gap exists. For a while it seemed like Graphite was going to be the answer but over time they ended up focusing more on the AI angle and less on human review tooling and now it feels just as cluttered and slow as anything else.

I home some other Xoogler comes along and delivers a Critique build for 2026, I still think there's a need!

Makes sense for them as a business, but still a bummer to have AI music mixed in with human music at all. To me there is literally no point to AI music. Music is communication. The artist is communicating with the listener through a pretty unique and magical asynchronous medium. AI (as we know it today) can't meet that bar and so it does not meet my definition of music.

In the long run I truly believe local AI will win and Apple will be the world's most important AI company because of these chips. Imagine something like today's Opus running for free and in complete privacy on your local machine with a beautiful Apple UX on top. For most tasks for most people, that's a much better proposition than a frontier model in the cloud you have to pay for and send all your data to and that only works when you're online.

At work we use Anthropic models and have basically no limits. So I am very familiar with what Opus can do. I also see the bills, I know what it costs.

At home I make a point of trying other models / tools on my side projects. So I've been using OpenCode and trying tons of models via OpenRouter. I tried Kimi, Deepseek, MiMo, etc.

GLM 5.2 is a _major_ step up from every other non-GPT/Claude/Gemini model I've tried. It's not as good as latest Claude Opus, but it feels every bit as good as Opus from ~4 months ago at a fraction of the price.

To me this model is the "it just works" moment for open weights models. We had this for closed weights models in late 2025 when Opus 4.5 landed. This is the same feeling I'm having with GLM 5.2. It's 90% as good as what I get from Anthropic for 1/5th of the cost and without any concern of lock-in.

The most jarring thing to me is seeing how kids (high school and college age) use Airpods now. I will see a group of friends hanging out in public and none of them take their Airpods out! They are talking and socializing, but they feel no need to remove the Airpods from their ears when nothing is playing. They're frictionlessly moving between real life conversation and content on their phones. This includes situations where you really think you'd want to take the Airpods out, like playing pickup basketball.

I don't know how to feel about this. I guess I'm happy that they're out of their house at all, but it does feel very sci-fi. In sci-fi books a common trope is for characters in the future to have neural implants that seamlessly and permanently connect them to some mega-internet. 24/7 Airpods is like the caveman version of that.

How much of the "financial gravity" do you attribute to VCs?

I've noticed that VCs try very hard to separate the world into "VCs + founders" and "everyone else" and that the more time a founder spends in the VC+founders bubble the more distorted their worldview can become.

I saw someone on Xitter say "Any CEO who wants to replace jobs with AI should first have to replace their own assistant with AI" and I think that's the perfect rule. Every AI demo is some version of a personal assistant, surely AI can do that job right?

I think we'd get zero volunteers from CEOs who have assistants.

(Note: this is not meant to be an insult to human assistants! I think they do a valuable job and should not be replaced by AI either).

This feels more like AI delusion, but I do worry about AI psychosis (which we're seeing in smaller numbers). People literally losing their ability to make sense of reality due to talking to AI all day.

We all know that celebrities/athletes frequently end up demonstrating psychotic behavior in public. Us normal people commonly attribute that to the distorting power of wealth and fame. When you're surrounded by "yes men" who give you only positive feedback and fans who adore you, it's easy to spin out of control.

AI means normal people can have the same experience. A constant companion that tells us we're smart and insightful, that we're making all the right decisions, that generally affirms our every belief and bias. If you spend all day talking to an AI who is _literally_ programmed to please you, I believe you'll eventually experience psychosis.

This is shockingly cheap, and by all account it's a very smart model. Is there a US-based provider for DeepSeek V4 Pro that offers a similar cost? I want to use this at work but can't justify sending company data to Chinese servers.

https://x.com/gnoble79/status/2031757996510839191

We are the liquidity here. If you have index funds, SpaceX is going to get more of your money much faster and on better terms than any other IPO in history. Even if you love this stock and this valuation, you should find this type of retail investor manipulation disturbing.

They invented a product that has no possible cost control: you don't know how much you've used until you've used it. And then we somehow made it a virtue to use as much as possible. I can't think of a more effective money printing factory.

I wonder when we'll see our first "My startup went bankrupt on AI use" post. Amazon is being dumb but at least they can afford it.

Macbook Neo is amazing, so impressed what Apple can deliver for so little.

That said, my sister this morning asked if she should buy a Macbook Neo. I pointed her to a refurb M2 Macbook Air with 16GB of RAM for the same price. I feel like that's the right call? Slower single-core performance but better multi-core and I think for 90% of normal people use cases the RAM is the limit before the CPU.

Are others making the same calculation?

So I can't browse the web with just one device? Forget which device they want me to have or any other of the million absurd insults of this plan, I feel like the most insane part is expecting everyone to have two devices with battery and internet at all times.

Can you ELI5 why this is so slow for local inference but so fast for using hosted models?

Same. Zed is so fast it's shocking. But it was using 2-3x as much RAM as VSCode or Cursor with TypeScript and the language server crashed a lot. Given that work is a TypeScript monorepo, that was a dealbreaker for me.

When people talk about AI replacing jobs, this is what it will look like. Companies that care about quality will use AI to make humans more productive and enhance their overall offering. Companies that only care about profit (read: most) will fire people, add in AI, and ship garbage. Other CEOs will see the results (read: profits) and copy this. We'll end up with shittier products and services than before and not much else.

I bought a teddy bear from them in 2014 and another in 2025. It's night and day. The earlier one is really high quality, the newer one feels like I won it from a claw machine.

There does seem to be like a 1% chance (maybe 0.5%) that this turns into a WeWork situation. It's a product that users love, but the company leadership is so used to lying and deceiving and being loose with numbers that the IPO filing could be a pretty big shock. Either they'll have to tell the truth, which will be much less rosy than the lies, or they'll lie and turn everyone off.

Probably won't happen. But not definitely.

I went to Spain as a teenager and saw Guernica in person. It was the first painting to ever really have an effect on me. It's stunning. A perfect example of how art can transmit a message between people across time and space, I just knew that I was feeling how Picasso wanted me to feel.

If you have the chance to see this painting you should, no website can do it justice (although this is a very nice try).

This is true but also not as new as the author claims. There have been various ways to abuse Google API keys in the past (at least to abuse them financially) and it’s always been very confusing for developers.

Dead on. GitHub Actions is the worst CI tool I’ve ever used (maybe tied with Jenkins) and Buildkite is the best. Buildkite’s dynamic pipelines (the last item in the post) are so amazingly useful you’ll wonder how you ever did without them. You can do super cool things like have your unit test step spawn a test de-flaking step only if a test fails. Or control test parallelism based on the code changes you’re testing.

All of that on top of a rock-solid system for bringing your own runner pools which lets you use totally different machine types and configurations for each type of CI job.

Highly, highly recommend.

This is true. If I see a Tesla I don’t immediately assume that driver is personally aligned with Elon. It’s a popular and good car.

If I see a Cybertruck I’m extremely confident that driver approves of Elons antics and likely fervently supports them. It’s a physical manifestation of his ego and mostly bought by his legions of fans.

If you’re a Cybertruck driver and you don’t want people to think that, you’re in the wrong car.

Everyone on both sides of this argument seems like they won’t be satisfied until everyone comes to their side. The maximalists want us to submit to the AI godhead. The doomers want us to go back to writing assembly longhand on paper.

I’m starting to think of AI use more like a dietary choice. Most people are omnivores. Some people are vegans. Others are maxing protein. All of them can coexist in society and while they might annoy each other if the topic comes up, for the most part it’s a personal choice.

This article has a pretty good history of how the research has evolved: https://www.newyorker.com/magazine/2025/01/13/why-is-the-ame...

The latest conclusion seems to be that the deadly combo is ultra processed foods with high calorie density. That’s what causes us to overeat garbage. Ultra processed low calorie foods are often still junk, but not what is killing us.

It’s not recommending 4 to 5, but for larger people (I’m 200lbs) to hit their protein target I’d need to eat over 1lb of chicken a day which is a lot.

They really have “anthropics” not “anthropic” on GitHub? That’s a shame, it looks like typosquatting. If people are taught to trust that it’s easier to get them to download my evil OpenA1 package.

Are these protein guidelines legit? I’m 200lbs (I’m tall) so they’re recommending 100-150g of protein per day. That feels like a lot…

So did I. I was just curious if it would really be noticeable faster and … wow yes it is. It’s really nice to use.

VSCode is still more polished and I’m going to keep it installed, but I’ve been using Zed for a month now and loving it.