lukaslalinsky

That was their headline for Opus 4.8, I guess the invested into some post-training to get them to write this, and I like it, it's a great way to identify AI posts from Claude.

https://www.anthropic.com/news/claude-opus-4-8

God I hate reading these LLM-written articles. It also feels like it was one-shotted by Claude, not just the kernel.

If I had coworkers with the ability to program like Sonnet 3.7 did, I'd be extremely happy. In reality, I can probably count 1-3 people like that, out of many over the years. Honestly, pair programming with Opus is better than any pair programming I had with a human, especially at understanding the reasons behind my designs.

As much as I hate to say this, I think it is an user error. Fable is very to the point, much more so than any other Anthropic model. I found it to be cheaper to use Fable, than using Opus for same task, but in order to achieve that, it needs to be given a targeted task.

My hope is that Opus 5 will be released soon, basically a rebranded Fable.

I'll have to try it. I was using earlier GLM models, incluing 5.1, and was always disappointed.

I considered Opus 4.5 to be the peak for a while. Opus 4.6 tended to over think, and generally get lost in thinking. I asked something and Claude Code would just spin for 15 minutes. And it was not the harness, if I changed the model to 4.5, it was fine again. So I skipped the following releases. I've been working with Opus 4.8 the last weeks and while I don't like how talkative it is, but it is fine to work with interactively. I've also used Fable for the few days it was available, and indeed, that was model worth using for my use case. To the point, but still very interactive.

Zig has multiple issues, but syntax is definitely not it. It might take a little bit of time getting used to, if you are coming from another language, but it's one of the most readable languages I've ever worked with.

I was never able to get these models to collaborate with me the way Opus does. I'm probably an outliner, I don't one-shot projects, I don't vibe code. I basically use LLMs are if I was working with a coworker, fairly smart one, but with short memory and often missing the big picture. Sometimes I can delegate more, sometimes less, but I know I always have to stay on top of what's happening, because it WILL create mess when it hits something hard. With the Antropic models, this kind of cooperation is easy (with the exception of Opus 4.6, which was bad for some reason).

I don't have an example, but I know the pattern. You are working on your software, security researcher finds a bug, it's in your project, for you it's just another bug, but for them it's a point on their CV, so they make a theater about it, and expect priority in dealing with it. It must get tiring if you get many of these.

I feel that Zig will stay a niche language. In this world, there is no reason for corporations to use anything but Rust for this kind of code. And without the corporate push, it will probably still exist for a long time, but the D trajectory is what I predict. I really like the language and I hope it gets more popular, but it seems unlikely to me.

With the amount of problems I had using Redis Sentinel, I really wish there was another way. On multiple occasions, with completely different deployments, it got itself into a non-repairable state where the only option was to drop it and setup the replicas manually. I was hoping someone would do a Patroni-like project for Redis, but I've not found it yet. I've moved all persistent data to PostgreSQL and use a number of Valkeys behind Envoy proxy as a cache.

I've switched to Valkey and I'm not really looking back. I'm much more comfortable with those people maintaining the software.

Well, I'm just an extremely happy user. I've honestly tried to find an alternative, and couldn't. I'm using it in the context of solo developer and it provides a huge value to me.

It's actually common, many companies develop their products this way. The source is available, you can see the VCS, but you can't participate in the development. That's why I see this as signal that it's going to turn into a company.

What made open source great, is the fact that if you find a problem, you can patch it. It's what motivated me, anyway. Ladybird is not SQLite, it's under development and very likely will be forever. To me it looks like they are transitioning into a company, where this model makes sense.

Indeed, while there is communication that the situation with merging external pull requests should improve, the reality is that it's easier to land a patch in Linux, than in Zig.

I wonder how can a new browser engine survive with the source available model. Like, why would anyone support this, unless they have business association with the Ladybird developers?

I've tried many AI code review tools. Nothing comes close to the depth of CodeRabbit reviews. It's the only such tool that can find real logical bugs. I'd love to be able to get Claude Code to do similar quality of review, but I can't get it right, no matter how I try.

That's possible, but who are you to tell a person what they should and shouldn't do in their free time.

Just going away from computers for a few days should be enough, the mob will get tired soon.

Look, it's not that long time ago when we had the xz malware. The pattern is always the same. Maintainer of the project is doing X, people start to pressure them to do something else, maintainer gives up and opens the project up to other maintainers, and then many things can happen. If there is any lesson from the incident, open source maintainers should never allow the pressure to happen, ignore it if it's too strong, block people. Rsync has been maintained for a very long time. Bugs happen, even regression bugs happen. People don't get to dictate how should the volunteer do development.

The thing is, showing the annoyance to the volunteer, who is already doing their best, has two possible outcomes:

1) they stop volunteering

2) they will ignore you

In neither of that is your issue solved. So maybe it's better to deal with the frustration on your own and then file a bug report.

The result might be closing bug trackers for the core open source projects. Or make them invite only. Even fundamental projects like Linux or LLVM accept AI contributions.

That's up to the maintainer to decide, no? If they decide to use AI to write more tests, then they do it. It's not like they owe the public something. If the "public" wants to take the project over and maintain it, they can fork it, but it's a thankless job.

I've tried building your project, but hit problems due to dependency hash mismatches. Do you have a screenshot somewhere?

There are going to be builtins to control this. The compiler will not do it on its own.

It's not just I/O, it's also mutexes, condition variables, time, etc. It's not horrible, but it does add up, so calling it super efficient is a stretch.

I've said it before, but I don't like Opus past version 4.5. It became unresponsive, thinking for too long without feedback, sometimes seemingly getting stuck. I guess it might be marginally better for some benchmarks, but when using it as coding assistant, the new models are worse. Even the new Sonnet versions do that. I'm slowly getting used to Haiku-level LLMs with the hope to run it locally at some point. It's less autonomous, but maybe that's for the best.

My work was kind of similar to the `std.Io` plans, so when I learned about it, I started aligning the project to that interface. Now it's a full fledged implementation of the interface. It's actually the first async implementation of the interface, the one in stdlib is very far from finished.

There are many shortcomings in the API, especially missing timeouts everywhere. It was clearly designed by people working on the compiler and other local tools, and not much network services, but I think it's a great improvement in the Zig ecosystem and hopefully people can now write reusable libraries.