- a PR that is quickly drafted by LLM based on a prompt

- a careful spec designed by humans, worked on by AI

- a feature built with a dev and LLM closely working together, with code reviews

- a feature with parts fixed up by AI, but 90% human written

- human written, checked with AI

etc

Is anyone moving towards a standard way of describing this? I'd love something that can go at the bottom of an communication / PR / proposal.

Comments URL: https://news.ycombinator.com/item?id=48235855

Points: 2

# Comments: 4

2 tickets: you can either sell them both back, OR change ONLY one name once. This means you have the option of buying two tickets up front, before you lock-in your companion.

It works well, I’ve experienced this for festival tickets.

It’s 17m for a tool which hopes to serve companies and charge money and make more than 17m in profit as a result.

If you look at the set of dev tooling, teams will frequently pay many hundreds per dev on things like CI, Git tools, code review, etc.

And to be fair, GitHub is really quite bad for a lot of workflows. I haven’t used gitbutler, but my team pays ~$30 a month per dev for tools which literally just provide a nicer interface for stacking PRs, because it saves us WAY more than that in time.

This isn’t even an egregious example of VC, it’s just an enterprise dev tooling bet.

If you then expect an exemption because your phone use is different then I challenge that you don’t actually support the experience.

If you want to read news in a phone-free environment: bring a newspaper, a kindle, etc.

I often find, if I've got a complicated solution, it’s because I haven’t fully examined the problem.

So a reasoning LLM that does the comparisons and checks “like a human” still fails the author’s test.

That said, this still feels like a skill issue. If you want to learn, see opposing views gather evidence to form your own opinions about, LLMs can still help massively. You just have to treat them research assistants instead of answer providers.

“I don't want to live in a world where someone makes the world a better place, better than we do.”

Context gathering and refinement is the biggest issue I have with product development at the moment.

Hypothetically: Substitute Microsoft for a company with “zero downtime” as one of their company values.

Now imagine you were asked “What impact did your actions have in contributing to zero downtime at Hostingsoft?”

That wouldn’t be a controversial question.

You’re talking about autism. The reply is about autism spectrum DISORDER.

Different things, exacerbated by the imprecise and evolving language we use to describe current understanding.

An individual can absolutely exhibit autistic traits, whilst also not meeting the diagnostic criteria for the disorder.

And autistic traits are absolutely a variant of normalcy. When you combine many together, and it affects you in a strongly negative way, now you meet ASD criteria.

Here’s a good description: https://www.autism.org.uk/advice-and-guidance/what-is-autism...

I'm pretty sure it was that series that also described https://en.wikipedia.org/wiki/Liquid_droplet_radiator , with the side effects of different ships having very distinct heat patterns because of their radiator patterns. And that if a ship ever had to make a turn while they were active, big glowing arcs of slowly-cooling droplets would be flung out into space and leave a kind of heat plume.

I like to make stuff, hack on projects. I code, I woodwork, I solder, I build. I love AI in the same way I love a router and dovetail jig in the workshop.

My son and I were playing minecraft, and we wanted to build a massive egg, just for fun. (My son is 5).

We try, we fail, we try again. We start learning about spheres and how to draw circles, this is peak project-based-learning. But we still can't build an egg that looks good, and now it's becoming less fun and there's no drive to keep trying.

So I spin up claude after hours and in ~30 mins I have an parametric egg-generator in 3d space, mapped to voxels. There is no universe in which my child would be interested in the many years of training to get to the point of building this himself. I also don't have 20 hours free to learn and implement my own 3d voxel rendering systems, just to build an egg in minecraft as a silly teaching exercise.

That weekend we try to use this tool, and we see it's really hard to just see an egg model and build it, so 15 minutes later it can now show us a sliced layer-by-layer view.

The weekend, my son built a massive fucking egg in Minecraft and he's been talking about circles and radiuses and eggs and coding software ever since. He was SO excited to see that we could take a running program, something "real" in the world, and then directly change it. (And now he's trying to learn about code and graphics and stuff. Again, he's 5 - this is the passing interest of curiosity in a child, he's not studying 50-hour courses to learn low level skills)

Are you saying that's not a massive win for everyone involved?