Hacker Newsnew | past | comments | ask | show | jobs | submit | rirze's commentslogin

Forget vacation and overtime pay, I'd expect equity at that point.

Julia only cares about numerical performance, and in that regime, it’s pretty fast.

So not generally fast, no.


It's sad that you voiced an actual question and you got downvoted.

To answer your question, remember that people will only approve a LLM's output if it matches with their perspective and priors. So if you see a slop issue, it reflects on the human user who didn't see an issue in it (thus their prompt framing or refining is wrong).


I was excited for this years ago, but when I tried it about 2 years ago, it felt awkward. Is it different now?

No help here. I daily drive fish, and subscribe to the philosophy that more than 5 lines of bash is probably a mistake. That being said, I still run into bash everywhere and wish that there was a more robust default installed already. Something which did not require pathological monitoring by shellcheck.

Surprise: another day of mechanical engineers not really understanding what open source really means.

I mean this as general advice; never trust software released/written/shared by mechanical/robotics engineers, especially ones from China. There's something deep-seated in their psychology where they ignore coding standards and can't conceptualize and obey software licenses.


I'm confused, I downloaded their repo and ran it and I had the option to continue locally without signing up/in.

Maybe it works without it, but on their Getting Started this is what they are saying (which might be written by AI) and that is why I skipped even trying it.

I see a bunch of these orchestrators, but is anything out there jj (jujitsu) native? I would really like to avoid hacking onto an existing product.

If Jujutsu had become popular a couple of years earlier, it might have had a chance to catch on. I worry that it missed the most critical training window for AI and we may be locked in on Git forever.

This is not true at all, a year ago it was difficult to force models to use jj consistently, but nowadays, (codex+chatgpt, at the very least) models very nicely obey jj workflows when guided in AGENTS.md . They have been training models to use it.

Edit: my original comment was related to how git worktrees are by default used in the implementation of these agent orchestration tools. I would rather prefer jj workspaces.


Incoming Canadian Civil War?

Jeez, the number of replies taking this as a knock on current political divide is saddening.

If anyone remembers middle school history, the American civil war was ignited by the North refusing to accept Southern secession. Should've made it more obvious, I guess.


No, they're civilized.


No. It's pretty clear that the Liberals have achieved dynasty status, only 25% of Canadians are net taxpayers, the rest live partially or fully on handouts, or are government employees whose income comes from taxes in the first place.

Most Canadians who are upset with the status quo are leaving or have already left. Last year saw a record amount of Canadians move to the US.


> I'm convinced that most of those folks and their elaborate workflows aren't really for productivity but for bragging rights about how much they use AI.

This is quite the reductive, charged statement. Can I ask what subscription plan you're using?

My personal experience is unlike this at all-- I work on ever-expanding codebases so I can easily burn tokens. Not to mention, structured agentic coding with adverserial reviews & task organization is not token-efficient. Additionally, for the problems I'm working on, only xhigh or high reasoning gives me worthwhile results while saving time. There are definitely configurations where default consumption doesn't work.

For reference, I used 15 billion tokens (most of it cached) last month on my day job's enterprise plan. That doesn't include my personal plans' usage.


I'm on OpenAI's Pro (200/mo) plan.

That's a super generous plan. Indeed, it's hard to normally saturate the limits of the OpenAI's $200 plan.

You could also do it the menial way; create multiple QR codes that can connect together. Not very practical for everyone except the very-motivated.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: