Cameri

Too soon to be authoring these kinds of posts. The author jumped the whole weapons cache on this one.

Do you really believe that inference is their only service? Come on.

Does this amount to gross negligence?

It comes down to which backdoored models you trust.

The dev comes as self-serving. Not what you’d expect to see. Calls it heated when he himself caused it with their tone deaf response… it’s next level.

It sounds like the job was already soul-sucking to begin with. My experience has been quite the opposite actually. Maybe it's time to change jobs.

Maybe don’t delegate without a contract. You don’t just hire someone to run your shop and not train them for the job, or at the bare minimum clearly communicate expectations, duties and responsibilities.

Accountability was not in the NFRs.

This is a legitimate question so I don't understand why it would get downvoted. The Printing Press _already exists_ (https://github.com/mvanhorn/cli-printing-press) and it's not limited to SaaS providers like Aclif seems to be.

How does this differ from the printing press?

I’ve found this to be true as well. It’s got really poor attention and will derail into world-building fast. I’m convinced Google is just shipping it to capture market share but they know Gemini isn’t ready for serious use.

Gemini is the most sycophantic and world-builder of all LLMs I’ve used. I’m sure all models do it but Gemini seems to have no guardrails and it will happily induce AI psychosis on you sooner or later. Just no.

From brutal to cruel. Nice!

They probably even got compensated.

IIRC Tailwind was toast a few months ago (laying off the few engineers that kept it going), so is this Shopify rescuing the company?

I’m sure lots of egos were bruised by that one neon sign.

Was this vulnerability disclosed responsibly by the author?

You'll now pay a compliant packaging company to package goods for you.

Nothing beats the feeling of having a proposed idea dismissed just to have the higher ups “come up” with it some time later. Don’t even dream about getting a footnote mention.

False. The protocol doesn’t forbid it. Theres actually a negentropy NIP for relay sync.

Did you read the actual protocol or are you just making things up on HN?

I’d challenge that definition. 0 spam messages are a solved problems, any positive integer greater than zero and it’s still a problem.

This one will age quite remarkably.

Plonked how many times?

I think you are assuming that people use AI to communicate with others because they don’t want to hurt their feelings: it’s likely hardly the case. The article here is just virtue signalling corporate version. Just tell the person doing it not to send you messages produced by AI directly and candidly. It’s clear you are not afraid of “hurting their feelings”. It’s rather weak to need a website to speak for you but maybe I’m wrong.

I have non-English speaking coworkers that use AI to translate.

This just comes as Karen-like behaviour: shaming people for using a tool in a way you don’t like.

No way this individual is fun at parties!

How is OneCLI different from Databrick's Omnigent?

Check out AI-DLC or another structured development workflow for your team and stick to it. If you’ve got devs: not using any structured workflow, or using a variety (speckit, openspec, superpowers, their own) it’s going to be hard to control the quality of the development process itself and its outputs: you are just producing slop.

What many businesses are going through is the industrialization of software development.

Not enough ads!

The whole framing analyzing LLMs as if they were humans is completely off, laughable. LLMs have no agenda and no feelings. We should stop pushing everything through an human-centric lens. LLMs will world-build if that’s the bias you put in, and often even if you don’t.

Nice to see Nostr show up randomly!