Join the discussion
Write your take first — we'll ask for email only when you're ready to publish.
- Hacker News
- One funny thing about incompetence is that they don't have the competence to know that their incompetence is straightforward to verify by a competent person.by ekjhgkejhgk
- I wouldn’t describe what happened here as incompetence. As a “carioca”, I am pleasantly surprised to know that the government’s IT department is involved in AI work — even without the budget to create its own models from scratch.by thimabi
- Why would they care? They get their salaries and pensions and bonuses, and the tax payer is footing the bill.by carlosjobim
- You just described every single vibe coder...by root-parent
- They really missed out by not calling it Neuromancer.
- I'm honestly surprised that they even had the inclination to attempt creating a model. I guess it's bullish that a municipal IT department had the guts to try this?by fkozlowski
- I like the [dead] comment theory that they proposed a huge LLM training budget to the government, kept most of the money, and released a cheap merge to justify the grift.by axus
- Merges and fine tunes are within reach of individuals with some money to burn so I’m sure a muni can do itby Havoc
- Can someone please explain or link to some information about how models are merged? Is this genuinely merging weights mathematically or some kind of distillation (presumably not if they’ve done zero training as the post suggests).by jordz
- There’s nothing to read.
Model A: A_1, …, A_n Model B: B_1, …, B_n
C_i = A_i * p + B_i * (1 - p)
In other words, it’s just a linear combination of the other models’ weights, per position.
by jxmorris12 - This is a good starting point: https://huggingface.co/docs/peft/developer_guides/model_merg...
But yes, in general, merging refers to techniques that directly blend the weights of different models mathematically. It had a big moment of popularity ~2 years ago, with many so-called "Frankenmodels" popping up on leaderboards.
I tend to think of merging as belonging to the same general umbrella as things like "abliteration", or other techniques that surgically modify the weights of a model without a traditional training/tuning loop. Maxime Labonne is a great person to follow if you're interested in this general area.
by calebkaiser - “Well, Steve (Jobs), I think it’s more like we both had this rich neighbor named Xerox, and I broke into his house to steal the TV set, but I found out that you had already stolen it.”
-- Bill Gates
by jrm4 - lmao i really hope this is a real quote cuz it’s a bangerby wunderlotus
- What’s more funny to me is the set up to that quote:
> Bill Gates had somehow manifested, alone, surrounded by ten Apple employees. … Steve started yelling at Bill, asking him why he violated their agreement.
And what’s more interesting is the conclusion:
> Apple filed a monumental copyright lawsuit against Microsoft in 1988, but they eventually lost on a technicality (the judge ruled that Apple inadvertently gave Microsoft a perpetual license to the Mac user interface in November 1985).
Microsoft didn’t steal Apple’s GUI … Apple gave it to them.
by ckcheng - The model's webpage at https://huggingface.co/prefeitura-rio/Rio-3.5-Open-397B says it's a merge now. It previously didn't contain this paragraph:
>The model is built via a merge of https://huggingface.co/nex-agi/Nex-N2-Pro and https://huggingface.co/Qwen/Qwen3.5-397B-A17B, proceeded by On-Policy Distillation from a stronger model. We detected an incorrect upload in the previous version, where the base merged version was upload instead of the final distilled model. We are sorry for the confusion and apologize profusely.
Incidentally are people using Github issues as blogs now?
by AlienRobot - Edit: I didnt even notice until someone pointed out this was on the Nex-n2 repo not the rio one, now I understand the OP’s confusion!
It wasnt framed as an issue which is the norm breakage I think you’re reacting to, as in they didnt ask that the readme be updated etc, but it is common now for folks to use a project’s issue tracker to name and shame them in a place they cant easily ignore.
Whether that’s right, prosocial, or professional is up for debate (as well as if any single definition of etiquette can be expected in 2026 on an issue tracker).
But surely you can see the optics reason why someone would take their complaint to the repo directly? It pressures the maintainers to respond, it allows for a pile on from the internet, and makes any decision to lock down a hostile thread into its own kind of statement.
The maintainers should absolutely post an official response and lock the thread though, it will likely get ugly in there.
by jonchurch_ - Oh no, someone is profiting off of their work without proper attribution!?!?by zinodaur
- "Their work"? First you had the original content creators that did 99.99% of the work. Then you had the US companies bundle it up into a frontier LLM. Then "they" did the "work" of using the US model as a foundation for their own. So in the sense of doing 0.00001% of the actual work that went into their product, sure.
I'd say it's more like someone forking a Linux distro, adding a few themes and fonts, and then complaining when someone else forks their distro and adds another theme.
by bachmeier - Attribution isn't the relevant part. Lying about your lab's capabilities is.by internet2000
- This is a pure scam on tax payer money. But what else would be expected?by carlosjobim
- How do you feel about the government or government contractors saying they did a bunch of work when they did nothing instead?
- This is an open weights model based on other open weights models.
The dispute is that they released it with claims about having done some post training that improved the outputs. It was discovered that the model was not post trained like they claimed.
The HF page now says it’s a merge of models, which wasn’t there before. They’re trying to claim they accidentally uploaded the wrong model to HF and that they’ll upload the real one soon.
Basically, they thought they could splice two open weights models together and claim their team had accomplished some amazing post training, but they weren’t smart enough to realize that other researchers would discover that there wasn’t any post training.
by Aurornis - The municipality of Rio de Janeiro (via its IT company IplanRIO) released Rio-3.5-Open-397B, presented as a homegrown Qwen3.5 fine-tune that beats comparable open models on benchmarks. The linked issue argues it's actually a weighted merge of ~60% Nex-N2 Pro + ~40% Qwen3.5-397B-A17B - Nex-N2 having been released about a week earlier.by unrvl22
- Rio better have the best IT infrastructure and software in the world if they are spending time on LLMs. What a waste of tax payer money.by vasco
- So the problem isn’t in the missing attribution to Qwen, but with the fact that they didn’t mention Nex-N2 Pro right?by Lucasoato
- I didn't know model merging like that was possible. (Obviously possible from a pure software standpoint but I'm surprised it's effective)
- > Every weight tensor in Rio is, to thousands of standard deviations, the same 0.6/0.4 blend of Nex and Qwen — across all 60 layers and every component of the network. Other finetunes cannot be explained as interpolations.
I find it amazing how robust the current deep learning models are. A simple linear combination of every weight did not degrade the performance of the model, but enhanced it.
by hintymad - by kristjansson
- What I find fascinating is the idea that there might be a set of "secret" tweaks that when applied to those weights (or even smaller models) could result in an intelligence simulation that could vastly surpass even something like Fable.by tarruda
- > A simple linear combination of every weight did not degrade the performance of the model, but enhanced it.
Which could be a signal that your "performance" was so abysmal in the first place that even randomly applied training methods can't make it _worse_.
by themafia