Huh? I'm seeing improvements in products _everywhere_. E.g. Linear. My team has been a heavy user of Linear for years. They have shipped a huge amount of things in the last 6 months, and the gaps between major changes is dropping.

It is twice as useful for our team as it was last year.

I'm genuinely impressed.

I have 6!

Hope you don't mind the public ask, it seems useful for others.

If we're using depot runners, and want to use them directly, or move off of github actions being the controller for when things run: what do you suggest?

Trigger the workflows directly on depot via CLI?

- 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.