websap

After over a decade of software engineering I've rarely if ever found a bug that needs to patches ASAP over an incident due to a poor abstraction. The bugs are usually the actual code inside the abstraction which you are most definitely handing over to LLMs and losing context over.

I’d rather watch an explainer video that goes over how to build IKEA furniture, than try to follow those terrible manuals.

That's good! The economy is thankful for it.

I'm very curious what your prompt / conversation was. I'm an avid claude code user, and maybe I have something to learn about how not to prompt.

I'd pay $20 / month for a Youtube subscription with no ads or sponsored content. Unfortunately even with sideloading on iOS there's no alternative live youtube vanced.

We love these devices, because these are the best devices overall.

Sounds like a skill issue if your infra can't validate these changes.

Steve Jobs built sand castles at Apple, these guys are building Kings Landing.

Same, I don't get it? I think event Sonnet 5 can build reasonable-y decent software. I'm a little surprised with how many people resonate with this.

I spent 30 mins today planning a change that affected multiple modules, and then handed it off the plan to the Claude to implement, and came back to 4 PRs fully ready to merge 15 mins later.

1 year ago, this kind of work would have taken me a better portion of the day, especially given the amount of searching I would need to do to build context.

Yes, people pretend to not understand the difference.

I still don’t understand what polish is missing.

I’ve been using computers since almost 3 decades now.

My MacBook feels like a computer that even 5-6 years ago I would classify as too futuristic.

I rarely ever switch it off, I run 40+ chrome tabs, 2 coding agents, and 2 editors all the time, with slack and a few other utilities running.

I can install power user software like Raycast and Handy.

Sounds more like regulatory capture, than building state of art sovereign models.

Yeah, as a business AMD should first care about getting their DC grade hardware optimized for inference workloads. It's unfortunate that most of HN discussion has devolved to me-ish.

> Apps are (rootless, hardened) containers, so it can run existing software with minimal changes - and in a reasonably secure sandbox.

WTF? I’m selling you a car with no brakes but it slows down reasonably fast?

I detest these doom and gloom articles.

We’re entering a new phase of software development, and with every phase there are new challenges.

Some questions the author might want to first answer: 1. If AI is constantly reacting to smaller incidents, is it surfacing larger issues in your codebase and architecture? 2. What kind of new telemetry do we have to build? 3. How do we build new deployment systems that help us validate fixes without requiring hours to go through traditional CI/CD systems

I’m old enough to remember the days when engineers would monkey patch their code on live servers with additional logging and metrics to learn about failure modes during incidents.

Mac OS has been hands down one of the best OS that I’ve used in a long long time. What problems are you running into?

The code is cheap, but the mistakes in production are very expensive!

You want to be leading the agent, not lagging the produced code.

It's hard to compare - prior to Opus 4.5 my code was 95% hand-written, with the occassional tab completion.

Now, I would say 80% of my code is written through an LLM, and the last 20% is usually me reviewing adjusting, etc. The part that I find cumbersome is that even when I make manual adjustments, I still need to tell the LLM, otherwise it leads to context drift.

When I compare these 2 times, I think I remember fewer specific details, but I'm getting better at creating more checkpoints.

I've always found it difficult to break into medium and large sized opensource projects, because it takes so long. In one of my jobs, I worked with someone who knew the maintainer in one of the areas, and I realized that social coding is basically an uphill battle, unless you have a real life social connection.

Yikes! I've been a software engineer for over a decade, and I've never had more fun in my career. Running an AI assistant on a cloud machine to pair with me, explore my ideas, learn new tricks, and even write code that I would never write due to timelines and deadlines has been fantastic.

Using coding agents to search for patterns, understanding why our abstractions might not be working because of how users integrate, etc etc.

Not everything vibe coded is bad software, not all bad software is vibe coded.

Hahaha! Thanks for the laugh.

CPU requests are cgroup weights.

Scheduler overhead for CPU limits? Are you talking about the Linux Scheduler or the k8s scheduler?

For the love of god - care about other pods on the node, especially in a multi-tenant setup.

Sorry for the cheeky response.

CPU Limits have a place, you don't want a bad change for 1 deployment object affect all neighbors by taking all the CPU. You need to be able to constrain the blast radius. This doc gives me strong AI vibes. Setting CPU limits isn't free. You still need to care about how the programming language that you use discovers those limits, and correctly handles them. For e.g. if you spin up a 100 Java threads, but only have 1 cpu as the limit, that's bad design.

Why not both? Having auto mode, plus having good guardrails is the way forward.

Needs 0 investment and 0 committment?

- You at least need a capable machine, so that's not 0 monetary investment. - You need to spend at least an hour decicding between ollama, llamacp, mlx, etc. - You need to find the correct quantized version of the model that works for you based on the architecture. - You need to figure out the correct context window size to get reasonable performance. - You need to setup a harness that works against your model - You might need to setup additional websearch tools, image tools, etc since harnesses like pi don't come with the model. Ofc you can't use codex and claude code, because those aren't opensource and you are anti-AI.

Or, you could sign up for Opencode for $10 and just be productive.

I'm particularly calling out the hypocrisy of the original comment. Being Anti-AI, and then spending hours on setting up a less than frontier AI model.

I'm not against AI. I'm calling out the hypocrisy in the comment. I'm anti-AI, but will spend hours trying to setup a local model, instead of just getting access to frontier intelligence in 15 mins, and actually getting useful work done.

If you're learning about model inference, then it's a different and you are definitely not anti-AI in that case.

What!? You are skeptical of AI but will go through the manual process of hosting a model that’s less than frontier intelligence (talking about Qwen 3.6)? Anti-AI folks are always odd to me