ryanSrich

And I think the online reality is much closer to the truth than AFK reality. I can't think of a single founder I've talked to in the past two years that's building with rails. That doesn't mean rails dies overnight, but it does mean it's simply all downhill from here.

Two ways I use skills

1. Personally - these are for apps I use like Codex. This one is pretty simple

2. For our product (which is mostly an internal tool, with minimial customer facing UI) - we have a skills factory that lets our employees create reusable instructions for our internal agent (fully custom built harness with routing). User describes the task and writes the instructions (can attach reference files, etc.). Custom skills and their versions are stored in postgres, with attachments in file storage. The assistant loads those instructions and references when it uses the skill. To update a shared skill, users edit a draft, test it, and submit it for review. Once approved, that version becomes live. Skills can learn or rewrite themselves from conversations (cuts a new draft and prompts the user if they want to update/improve the skill).

EDIT: I should say that our employees have a particular set of expertise and knowledge that make skill sharing insanely useful. Which is why I took the time to build this out. It's helped reduce manual work, and has increased our AI usage drastically. We also measure AI output (in terms of quality) and the reduction in slop has sky rocketed.

Not a great argument. You're describing what LLMs are trained to do, not necessarily every capability or property produced by that training. We do not know what conditions are sufficient for consciousness. Any statements saying it's not possible for consciousness to emerge (or that it hasn't already) in such a system is no more established than claiming that it has

Consciousness can factually exist even though another being’s subjective experience is not directly observable. we can measure its behavioral and neural correlates and infer consciousness from them but we cannot directly observe the experience itself or conclusively prove its absence in another being. I don't think we'll ever get to a point where subjective experience in another is directly observable. But I don't think we need that to happen to prove consciousness factually exists.

I haven't used fable since they brought it back. But based on my experience before they removed it, I would agree that sol is pretty close.

For anyone on the fence, I was a hardcore CC user since it was released. I made the full switch to 5.6 sol and Codex about a month ago.

It's the better experience. The limits are way higher (I almost never burn through my $200/m plan), and the output is better than Opus 4.8 (Opus 5 is completely unusable for me).

> but maybe it's 2 lines of code with 6 lines of comments (looking at you Claude), maybe it defines three helper functions it doesn't really need, maybe it does something "here" when it should be doing that something "there" instead, maybe it finds itself in a framework and completely disregards how the framework is supposed to do things, etc.

I would fully expect a brand new college grad to call these things out. There's nothing in here that requires extensive experience to understand. These are basic principles any SWE should know. Nonsense comments are common sense to pull, if the LLM is pulling in a framework you should look into that framework and understand how it works. Don't know the framework during the interview? Say that. Tell the person interviewing you "looks like it's pulling in XYZ. I'm not entirely familiar with that. I understand at a high level what it's doing, but I'd want to dig deeper and understand if the LLM is doing this part right"

SWE was a sub degree within the school of CS where I went to school. You could do CS with a minor in SWE and get the best of both. I suppose if you're just doing a straight ticket CS degree you'll have little exposure to engineering (I believe when I went to school 13 years ago there were 3 courses over 4 years on engineering within a pure CS degree).

> I’m sorry to say but colleges don’t teach the kinda stuff you’re gonna use day-to-day.

This was not my experience in college. A lot of it was VERY applied. Granted, that was 13 years ago.

But even so, if you're at a college where you feel that you're not getting enough exposure, that's why I also called out "Have done dozens of projects" and "Have done several (at least 2) internships".

> This all sounds good on paper but I have an honest question: How do you develop judgement as a junior or mid level engineer to critique AI if you yourself never learned that skill by making mistakes in the first place?

Shouldn't this be a pretty fundamental part of a degree? If you're in school right now for a CS or SWE related degree, I would imagine you're learning how code actually works, how the math actually works, etc.

If an LLM makes a mistake, you should be able to call that out.

You might be arguing that a junior engineer may not have the RWE to make those judgements, but by the time you've completed a 4-5 year degree, you should have done the following:

- Completed coursework where you've learned the fundamentals of programming and software engineering

- Have done dozens of projects (building everything from basic web apps to more advanced pieces of software) where you've seen what works, what doesn't work, etc. This also gives you real world exposure to the latest and greatest frameworks, tools, etc.

- Have done several (at least 2) internships where you've worked at a real company writing real code, and have seen/been mentored into what AI is good at, where it fails, etc.

So the moral of the story is, don't build a frontier model in the US. Got it.

Question: for a smaller SaaS tool, or even internal product. If a team doesn't want to manage AWS or another IaaS provider, what are the best alternatives for the following

1.) Vercel - having a bad month

2.) Supabase - having a bad month

3.) Railway - now having a bad month

Generally agree. I use AI very heavily, but rarely am I letting it actually think for me. It's a tool that reduces the time it takes for ideas in my head to manifest into reality. If you don't have those ideas, or a poor understanding of the system the AI is working on, you're going to produce slop. If you can't recognize this slop, you're more susceptible to having psychosis.

Having tried most (all?) of the commercially available + open source options, and even tangential competitors like CC, Conductor, Antimetal, etc. I haven't found anything that's close to the experience of Cursor. The harness they've built is incredible.

I'd even go so far as to say that any competitors that are direct (windsurf, kiro, etc.) aren't even in the same universe. Cursor is just so much better, faster, has better features (plan and debug mode), and squeezes much better results/code out of the same models. They absolutely have some secrete sauce that the other options just don't have.

Not quite first party, but composer 2 is far superior to grok for coding. Unless you're eluding to them using SpaceX infra to train their own model vs. using grok

For programming, the way I would build a curriculum is to force students to actually learn how to program and code first. This is simple by requiring them to write code inside the classroom by hand for all exams.

I would make this the focus for 90% of the first 2 years of their degree.

I would then have them spend 75% of their last 2 years learning how to use and program with AI. Aside from knowing how things actually work, there's no more important skill now than mastering AI.

The cynicism or even lack of interest is because it's extremely underwhelming.

If you ask 100 people in 1969 what humans would be doing in space in 57 years I can guarantee not a single person would guess that we've done nothing of substance. And that the most exciting thing we have done that involved human space travel is simply flying around the moon, people wouldn't believe it

MacOS is a bug filled nightmare, and it's still light years better than Windows. I haven't used Ubuntu extensively since early 2019, but it still wasn't comparable to OSX at the time.

Apple and specifically MacOS is significantly worse than it has ever been, but again, still far better than the alternatives.

The equivalent of about $20/hr today for those wondering

Yes. https://x.com/claudeai/status/2014834616889475508?s=46

This has always been my personal definition of AGI. But the market and industry doesn't agree. So I've backed off on that and have more or less settled on "can do most of the knowledge work that a human can do"

So it's even more human than we thought

This is entirely solvable with skills, memory, context, and further prompting. All of which can be done in a way that's reliable and repeatable.

You wouldn't expect a Jr. dev to be the best at keeping things dry either.

I would and have done the same with Jr. devs. It's not an argument against it being AGI.

Giving opus a memory or real-time access to the current year is trivial. I don't see how that's an argument against it being AGI.

I think "tested" is the hard part. The simple part seems to be there already, loops, crons, and computer use is getting pretty close.

AGI is here. 90%+ of white collar work _can_ be done by an LLM. We are simply missing a tested orchestration layer. Speaking broadly about knowledge work here, there is almost nothing that a human is better at than Opus 4.6. Especially if you're a typical office worker whose job is done primarily on a computer, if that's all AGI is, then yeah, it's here.

The market has clearly passed it by. I was a huge Heroku fan. It even inspired my first startup in 2014 (basically a healthcare tech version of Heroku). At the time, I thought it was the future, and found messing around in AWS, etc., too time-consuming and unnecessary. That was when Rails was all the rage.

That's the idea yeah. There are other people actively working on this. You can follow vx-underground on twitter. They're tracking it.

Seems like a job for an LLM