Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

There is minimal downside to switching to open models

marble.onl

Post reply on HN
Print view View original

171–180 of 351 posts

Re: There is minimal downside to switching to open models

#171

Post by calgoo »

itwaswatson wrote: post #47
julianlam wrote: post #6

I think it's interesting that people write off open weight models because they're "a few months behind" proprietary models. I know LLMs move at the speed of light (especially these past few quarters), but if Opus and GPT "a few months ago" were really like open weight models, then there's really no reason to not switch, especially for those who were using these models a few months ago. Your codebase didn't change, so…

We have a provider with Deepseek V4 flash at our work. It can handle 95% of the "actually functional" workload at a tenth of the cost. I still pull up beefier ones sometimes, but that's after some consideration. The moat is so flat, it only gives +1 food and +1 production. +1 gold with a road.

Same, i feel that V4 Flash is great at task implementation, but im still looking at bigger models for design. Now, GLM 5.2 with high thinking is actually getting really close now. I have switched for all personal projects right now and am quite happy with the results. I think the magic is in the big context window (1m) + a lot of thinking gets us very close to at least Opus 4.6 level. Im currently running directly on z.ai with a lite coding plan, and have bought API credit on deekseek as well. I will be looking at EU based hosts next and then i might switch over some of the more critical flows.

Re: There is minimal downside to switching to open models

#172

Post by t-3 »

hdgvhicv wrote: post #117
earthnail wrote: post #90

Earlier quoted context omitted.

From all the large governmental institutions, the EU is the one currently holding up traditional western values. That gives it street cred in this subject.

https://www.theguardian.com/us-news/ng-interactive/2026/feb/... The age old joke; A Russian and an American are drinking at a bar The Russian says "I'm impressed by american propaganda. It's so subtle but effective." The american responds "What are you talking about, we don't do propaganda."

The version in my fortune file is better:

A Russian and an American get on a plane in Moscow and get to talking. The Russian says he works for the Kremlin and he's on his way to go learn American propaganda techniques.

"What American propaganda techniques?" asks the American.

"Exactly," the Russian replies.

Re: There is minimal downside to switching to open models

#174

Post by ZeroGravitas »

It seems the best self-hosted and the worst models served by big providers has some considerable overlap in quality.

Whatever reason people have to run those (cheaper? backwards compatibility once you get something running) surely applies to the open models too, maybe even more so.

Re: There is minimal downside to switching to open models

#175

Post by qznc »

julianlam wrote: post #6

I think it's interesting that people write off open weight models because they're "a few months behind" proprietary models. I know LLMs move at the speed of light (especially these past few quarters), but if Opus and GPT "a few months ago" were really like open weight models, then there's really no reason to not switch, especially for those who were using these models a few months ago. Your codebase didn't change, so…

To be a little bit more precise than "a few months behind", what probably matters is before or after "Claude Opus 4.5 from Nov 24, 2025". That was the model which started the OpenClaw hype over Christmas.

Re: There is minimal downside to switching to open models

#176

Post by NonHyloMorph »

throwaway27448 wrote: post #106
earthnail wrote: post #90

Earlier quoted context omitted.

From all the large governmental institutions, the EU is the one currently holding up traditional western values. That gives it street cred in this subject.

I'm honestly not really sure what "traditional western values" have to do with where to store data. What does that even refer to—individualism? Christianity? Representation in court by lawyers? How does this intersect with the topic at hand? Edit: c'mon people, if you're going to use such ambiguous phrases at least have the spine to clue the reader in to what you want them to refer to in this context.

Well there have been a lot.. philosopy, polis, democracy, hemlock cup, enlightenment (note the perversion of "the dark enlightenment"), modernity, the resistance (against Nazism), psychoanalysis, postmodernism and critical studies (postmodernism in the genuine sense of the philosophies/theories that you would assign that label to and not in the misguided sense of relativism as arbitrarity; basically continental philosophy, frankfurt school (e.g. adorno horkheimer, habermas) and the french (e.g. foucault, derrida, deleuze (& guattari))

Of course there were also absolutism, colonialism, the jacobines, nazism & facism, to name just a few. Part of western values, from my perspective at least, is an implicit promise, that what happened in the 20th century with facism was the darkest hour, so to speak-> never again

Re: There is minimal downside to switching to open models

#177

Post by fuck_google »

OtomotO wrote: post #89

I am absolutely pro local and true open source models. Personally I haven't seen any productivity gain since Opus 4.5 times. But: I can't fully get behind the opinion that (so called) "open source models" are simply superior and will be in the future, because when I asked some models who they are, they answered with "I am Claude from Anthropic", which could mean they have been trained by exfiltrating Claude. I have N…

[dead]

Re: There is minimal downside to switching to open models

#178

Post by nickserv »

throwaway27448 wrote: post #139
Phlogi wrote: post #136

Earlier quoted context omitted.

US Data Privacy is not sufficient.

For what? Does the EU not want to spy on its citizens? That strikes me as... unlikely. Why not host in east asia? Or southeast asia? Or south america? Or africa? Then you avoid both the government with incentive to spy on you (assuming you live in the EU) and american companies.

EU member *countries" certainly do, but that's true of all countries that have the ability.

If anything the EU puts limits on what EU member countries and companies can do. By hosting in one of the EU countries you have stronger legal guarantees on data privacy than in any other area. A possible exception is Switzerland (not a EU member), which historically has had even stronger privacy laws, though these have been weakened recently IIRC.

Re: There is minimal downside to switching to open models

#179

Post by _pdp_ »

There are downsides depending on how good is your harness. Switching the model is easy enough. Ensuring that the harness continues working the way it did is a completely different thing. This is not just about the prompts but also general behaviour around the model and its infrastructure.

So while it is not complicated and certainly something that can be solved, it is not plug and play.

That being said, we switch to open weight models earlier this month and the results has been more than positive so far. The cost savings are also hard to dismiss.

Re: There is minimal downside to switching to open models

#180

Post by reacharavindh »

It was easy to be a rebel and use Linux when it was clearly competent, but needed hacks and extra elbow grease to get it polished for use. IME, the open models are “not there yet” in terms of capability or operational needs. Sure, GLM5.2 looks competent, but I will only be able to get it to run that competent if I had a huge cluster of GPUs.. if I am accessing an open model via hosted API, I might as well run a closed model via hosted API. The incentives fall apart in comparison to using Linux 15 years ago.

Don’t get me wrong. I wish I could run a local model and be happy about it. At the moment, I’m not.

Post reply on HN