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

That's also what trucks already do to eliminate dead angles and help the driver manoeuver in tight spaces


I get where it's coming from but I think it is also very funny if someone actually believes their claims (except as a CYA strategy)

The AI companies have already shown how little they care about other peoples intellectual property and they won't care about their customers either if it stands between them and the promises they made to their investors.


This might be a reasonable thing for an individual consumer to believe about the value and enforceability of agreements with large companies, but given the context I think you’re off base.

ZDRs are backed by contracts negotiated against extremely capable and well-resourced counterparties. Being found to violate them would bankrupt even OpenAI and Anthropic many, many times over.

To the extent that you view these companies as your adversaries, it’s worth improving your mental model of their actual incentives and constraints.


Open weights are certainly something that is very eagerly being adopted in some companies.

It's not even that expensive because even the 15€/month/employee bill for people who use AI very little can stack up.

Beside that though, many companies already have most if not all of their data in some cloud (Microsoft would be a prime example). Giving them a few extra bugs to get a (potentially) very useful tool is not out of the ordinary.

If you are under the impression that not going AI would threaten your business right now (which may very well be true for some companies) then there isn't really a choice even if you believe the vendors will steal everything eventually (which they totally will)


>Open weights are certainly something that is very eagerly being adopted in some companies.

A large local MSP that has significant colo space just started a big marketing push towards hosted LLMs for their corporate customers.

I think its about to kick off everywhere.


It's not just putting up colo space for local models.

It's more about the harness and API proxy you use. They need to be smart enough to know when a (self)hosted model is enough and when to forward to a SOTA model.

The SOTA model _can_ do everything, it's just expensive as fuck. But so is shoving a difficult task to a sub-par model that takes (relative) ages and comes back with the wrong result.


I think the average corporation has 2 concerns largely:

1. Getting some exposure to LLMs while building out their AI strategy. 2. Preventing data loss via end users following desire paths to Gemini, OpenAI etc.

You really don't need bleeding edge models for that. A lot of these things are going to be writing emails and adjusting config files and whatnot.


glm-5.3, kimi k3 and qwen3.8 are SOTA.


I strongly suspect most companies don't spend that much either.

Unlimited tokens aka unlimited cost is something that not every use case needs.


I think most good engineering companies are spending >$1000/employee/month. Subscription users spend $100-200.


My personal best case scenario is that LLMs are commodotizing and that the "We'll rule the world with our frontier models" vision of OpenAI and Anthropic is not working out.

They can and probably will still be very successful but what they pitched so far is not going to work if their is any meaningful competition not too far behind.

But who knows. VC money allows them to try a lot of stuff before their eventual IPO.


What you are seeing is not typical VC money - institutional investors are involved now.

Do any of you here actually know what you’re talking about?


Eventually 2028 and 2029 will come around and at some point today's data center builds will be (economically) full.

In addition to that there are extra fabs build and (for example) China can use the high margin to catch up with their processes without breaking the bank.


That is a concerning possibility but I wonder what the threat model is.

They have all that information already and could simply classify and pass it on without the need to encode it with a probability.


One possibility is that you have Claude write something that would not get you in trouble and concatenate that with something you wrote by hand that would.

Your signature from the safe material is now associated with your content on the dangerous part, and then the brownshirts come knocking on your door.


This is really nothing new and has always be the case It's not possible to tech yourself out of a political problem.

So if there is something being done we should choose a solution that has at least some accountability to the general public (through elected representatives).

The alternative is Google, Apple etc where almost anyone has exactly zero influence and the government can still block as they like.


If all alternatives are bad you should do none of them, not squabble about which one is slightly less bad.


Not doing anything is also an alternative, theoretically it can be worse than other alternatives too...


I think there is also the case were companies will simply use different tiers for different tasks.

While the engineering team might need a cutting edge model (with the associated costs), the marketing department will be fine by something that can grammar correct or turn a few bullet points into prose. Likewise you already don't need Fable for Ticket -> RAG -> Reply with Faq knowledge or escalate workflows

That's already the case with other very expensive software like CAD packages were oftentimes you have different feature sets enabled for different employees.


"that can grammar correct" ... Did you do that on purpose?


I'll sneakily claim I did but the reality is English as a second language and I'm not yet ready to let a LLM do all the fun for me.


Also that can't be the whole story because Planck died in 1947 and in Germany (then and now) Copyright ends 70 years after the death of the author.


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

Search: