I will forgive it using load bearing as long as it finds the right seams.

Yeah, you definitely don't want to hang things off the wrong seams, or you'll end up with quite the blast radius

Let's not paper over that gap and find the root cause instead

I think the scary part is that someone gives gmail access to Claude.

Or access to a filesystem that contains things like an image of their signature.

I also thought that's crazy. Why even bother for these kind of bounties.

That's what I thought too. I used speckit quite a bit before and I've had mixed results at best. You are just moving ambiguity and code review from one place to another without really gaining anything.

I just rely on a log of user messages, all messages the user typed in a project as raw data and do a pass with agents to synthesize intent. Then use this for planning and validation of code. I think the user messages are the most valuable data in a project for this reason. Doing this reflection pass on messages takes just a few minutes even for thousands of messages. It keeps global perspective which is often lost in local work.

If you could easily benchmark the quality of code then models would be trained on these benchmarks/metrics.

that is true, but if the metric is what we want optimized, then that's fine.

However it is more likely to be something which can be detached..

Code quality is probably isomorphic to the halting problem, or can be reduced to the halting problem in the simplest case. I.e. it’s intractable.

I have been quite disappointed with Astra. I switched over a week ago and I didn't notice a massive difference compared to Sol at first, but I figured I'd use it anyway because it surely can't be worse. Then I saw the bill, it's burning my subscription 10x faster than Sol for essentially no benefit. Not only is it more expensive per token, it also seems less token efficient. And not obviously any better. I'm back to a combination of Sol + Claude.

I also use Astra at work where I don't need to worry about token cost on highest effort and same story there, I don't see any difference in everyday work other than it being more expensive. Of course my experience is highly subjective, but with how meaningless/overfit the benchmarks are, subjective experiences are imo what matters.

Horrible advice. This may have been good advice 10 years ago, but not today. There are no positions for people who "kind of understand how toy LLMs work" because so many engineers do these days. Most of the real LLM optimization work is at the edge of research and highly proprietary and not something you could ever do without infra that costs millions.

But of course, 10 years ago this wasn't obvious.

The point of courses like "Nand to Tetris" is not to become CPU designer. It is not useless just because you can't build a chip factory.

Watching Karpathy's "Zero to Hero" won't make you AI specialist. It will improve your understanding of the basics.

you don't reach cutting edge immediately. you start with the basics

I think the answer then is to get a Phd? I mean, one should learn it to satisfy their curiosity and to build things but I don't think it's going to help you career in any significant way.

Yeah he's a moron with a lot of money, that's about it. I'm sure he's said the same thing about various other bags he had bets on throughout the years.

What would be better advice for a 17 year old?

Throw the computer and the smartphone out of the window.

Or more reasonably, the same old thing : use Linux, hack a little, why not learn programming basics. But learn to own your technology, fight against centralization of technology. The same old RMS story.

IDK where the tech industry is going, if there will be jobs anymore or not, but what I'm sure (and what have been the case for the last 10-15 years anyway) is that for most tech jobs, having good technical knowledge beyond the basics is pretty useless and will probably not be recognized.

If you can, stay a computer geek if that's your thing, but don't make it your career choice, the Eldorado is behind us.

As someone who very much enjoys self learning, I can't comprehend what you wrote. It doesn't make any sense. In fact, I don't believe you've played in the same sandbox at all.

> why not learn programming basics

Do you think implementing an LLM from scratch would not require programming!?

A generic project based goal like this is the best approach to self learning, because you fight your way to it, picking up what you need to know on the way. And, once it's all working, and you get your first meaningful sign of success (in this case, some tokens out), after your long path, you fucking celebrate!

Stay in school, get good grades.

Stay away from the internet and learn how to build a local business instead.

"it doesn't matter what you choose to study because no job is safe from being outsourced overseas, handed over to an indentured servant, or made redundant by a machine. you will spend your whole life surviving while the cannibalistic pedophiles who own everything invent new ways to make you own nothing. be frugal, don't get married, don't have children, do everything you can to stay healthy and independent, and you just might live a reasonably comfortable life."

Most reasonable advice I've seen under this post. Having graduated in 2025 I've experienced the horror of competing with infinitely many third worlders in my small country, who will gladly take 1/3 my pay and be serfs.

I really hope we get another hiring boom like in 2020 when I decided to study CS. Otherwise my career will be very rough. I love it and can't imagine doing anything else.

> Having graduated in 2025 I've experienced the horror of competing with infinitely many third worlders in my small country, who will gladly take 1/3 my pay and be serfs

You should really read up on disruptive innovation. Many of those who you call "serfs" who'll "take 1/3rd of my pay" will tomorrow establish themselves, justify their presence, and move up the wage/income scale, while you'll be left complaining.

I am from and live in a third-world country and have spent some time in a first-world one. I've seen the ETH Zurich tag open doors that I didn't even know existed. If you aren't leveraging your passport, your education and your network to reach a place where you don't need to worry about "serfs", then you're doing something seriously wrong. What you have, compared to the competition you denigrate, is invaluable, making best use of it is your job.

Horrible. Which country is this? Canada maybe?

Switzerland. I graduated from ETH Zürich.

very compelling. do the nations that never participated in colonization -- such as Switzerland, for example -- get exemption, or is the blood guilt shared among all wh*te people?

say that to visa laws that were designed by your ancestors that carry around the world. Say the same to currency arbitrage, freedom of mobility and everything that you enjoy for granted in protected walls.

The reason remote worker can out compete you is because of this currency arbitrage you designed. Your pennies goes a long way in this so called third world. Your one day dinner at nice place is a months salary for family of 4.

Seriously, if you can’t compete globally, then you don’t deserve your privilege of being born in rich world.

Stop labelling other humans as serf when your entire wealth was built on shaky foundations.

You == not you the person, but the government and laws.

Once again *I* didn't design and of it. Leftists don't like hearing that.

The fix would be obviously to control and limit foreign workers by regulating companies.

> don't get married, don't have children

Bad advice. You’re going to need family connections and loyal people you can bet your life on to survive if the rest of what you’re saying is remotely true.

the likelihood of finding a partner you can bet your life on is nonexistent. the likelihood of the opposite outcome is well-known at this point.

We always hoped that we wouldn't live to see the dystopia in Snow Crash become reality.

We never imagined that we'd live to see Snow Crash depict a utopia by comparison to what we got.

Implement a linear regression or Bayes' theorem.

Learn math

Be first to invent and patent the "$15 dollar, battery-less, flying carbon capture drone" and save the world from global warning.

What? You want me to tell kids not to be ambitious?

Very silly reply. If you learn how toy LLMs work at 17 don't you think that would help you at university and grad school? There's plenty of time to go into the private sector workforce later.

I built my own pipeline for this because in my experience the YouTube auto transcripts are quite bad.

I download the raw audio track with yt-dlp, give it to qwen asr for raw transcription, then DeepSeek flash for transcription cleanup, formatting, corrections with web search enabled, etc. I use openrouter to call the models. It's a few cents per video (mostly the asr model at ~12 cents per hour) and quality is great. You could probably use a local asr model if you want to save money, I just don't bother because it's so cheap already.

That only makes sense for videos that don't have official (not auto-generated) transcripts of course. If there are official transcripts that are good you can just get them directly with yt-dlp.

Would you mind sharing your code?

You can do remote control / handoff with it, i.e. start on desktop and move to mobile. doesn't work with the cli

I don't think it's about YC specifically, more about VC-driven enshittification of open source software in general.