manmal

I think you’re probably overthinking it. The same model will in my experience find errors in the same thing it just generated. I think reviewing is a totally different place in latent space, than implementing. Anyhow, it works well for me.

I often tell codex to launch a subagent without prior context to „remove BS phrases and make the prose sound more natural and higher readability“. That‘s usually enough to get better results.

I’d recommend to instead write a de-slop skill that instructs to launch a sub agent with fresh context, and analyze for such phrases in the new commits, and remove those. Find -> fix just works better than preemptive instructions, in my experience.

And if you manage to do this automatically before committing, you’ve built the backpressure everybody is talking about.

I don't think that's opinions, but, rather, going wherever the wind blows.

There is no MacBook Pro with OLED (yet).

I‘ve built this anti-k8s stance pre-LLMs, and just realized that, actually, agents should be pretty helpful in dealing with it? Is avoiding kubernetes still advisable for projects that will likely never use its full complexity, given how easy it is to maintain now?

Why would I ever use a local model by that logic? A usable model means my computer was very expensive so I‘d have the funds for a Pro plan as well.

I would just, not wait for things to finish because it’d be instant? No need to create slop just because something is faster.

TIL there will be 35 degrees Celsius in London today. I thought that basically never happens. I remember people telling me a few years ago that they are lucky to ever get 30 degrees.

While my colleagues are running 6 parallel agents at 50-100t/s each, with an actual SOTA model? Don’t you think I‘d get fired after a few weeks of that?

But what is it doing for you that you couldn’t do yourself at that speed? I‘m really curious and on the fence of partly going local.

> but the speed is a consequence of the design, not the pitch.

You kinda lost me there. I‘m supposed to use a central technology whose author can’t be arsed to write a few paragraphs?

I don’t agree with 2). It’s ok to qualify. Sounds sycophantic to not do it.

Carmack might think that there are certain areas he will be better due to decades of experience. Overall programmer isn’t a bad qualifier at all, it’s actually making it sound less offhand and more honest.

Have you tried the 27B dense version? It’s way better for coding.

Sure, and the body makes its own glucose. The only way to deplete that is prolonged fasting.

If you‘re specifically aiming for low glutamine, going vegan won’t cut it though, depending on what foods you leave in. Soy is high in it. Eg a glass of milk is lower glutamine than a serving of tofu.

Isn’t glutamine also part of vegan diets? I don’t eat meat myself, but your assertion has me wondering about glutamine.

May I ask, how much money you have spent so far on this effort?

I think author meant he vibe coded some deterministic system. Maybe comparing the whole genome to a healthy one, and pointing out all diffs?

Why do I need shortcuts though, I want that to be transparent.

If they are using some mid model and are stingy with web search, I won’t use it more than a couple times.

Are you not worried about where your data will end up? By now I‘m feeding things to Codex that I‘d rather not have in a leak.

Usually when they push back, it’s for obvious reasons, things I already know and actively decided to ignore. They are trained on mediocre software, and it shows.

I like using voice input a lot, I get way more info out of my brain and into the context that way.

Process wise, for bug fixes I usually just throw the ticket in and optionally some thoughts on how to fix. But if I don’t know the cause, I let it write instrumentation tests until the bug is reproed, and then the fix is easy.

For new features in brownfield projects, I usually need to align with team members because we‘re closely aligned between platforms. We iterate on what you could call a spec, which is just a mix of requirements, magic numbers we want, algorithms we‘ve picked (often by vibing prototypes), and sometimes going very specific on parts that must be done right. Eg for interfaces with other teams, and there’s not yet a document to describe that, we put that in the spec as well. We do use agents to shoot holes in those specs, and often they find inconsistencies. But architecturally, they seem to get caught up too much in what’s already in those specs, and personally I haven’t seen any worthwhile feedback that I‘d have taken up.

Sometimes we use this spec to vibe a first draft. Often the draft is so good that it can be bent to our liking. Sometimes, it just serves as a reservoir of ideas, and the feature must be implemented (with assistance) by re-assembling the pieces differently.

Sorry I have to ask. How senior are you? The notion that I‘d allow an agent to talk me out of something seems weird. 99% of cases, it’s the other way around. Architecture is just not where they shine.

Usually there’s some environmental disturbance eventually, that makes it burst.

That’s an interesting proposition, are you saying people do TDD just for the heck of it?

> With TDD I would be taxed heavily and velocity slow to a crawl.

And the code will be good.

Isn’t what you are describing, a programming language? I‘m not sold on specs being everything you need to implement correctly.

We are now writing specs for important components and algorithms, and spend quite a bit of time aligning on them before implementing the production version. Those specs are often informed by vibed prototypes, but usually it’s also two or more people really thinking through an algorithm, and aligning with interfaces to the adjacent systems. They are usually very information dense.

I don’t believe spec driven development is a good idea though. The architecture should be made with intention as well, or I feel we‘d end up with whatever happens to be ranked highest in the latent space. But the specs are great to align cross platform teams behind shared concepts, and they are a good input to automatic reviews.

If they earn that, surely they don’t have many customers or they would earn more?

Dentists are usually booked well, how would that work? Is that vibe dentistry?