Even if it were about consent (and it's not), it's difficult to show that a relationship with such a power imbalance is consensual. If it were consensual it should have been disclosed. And as a CEO he has a greater responsibility to follow these kinds of rules. He knows it, and he did it anyway, and then he got caught doing it. There's really no other action to take besides removing him.
Maybe it's a generational thing? The younger generations seem to have some sort of anxiety with respect to consent and power dynamics, where even something as trivial as a modest age difference is viewed with suspicion. The movie Obsession can be seen as that anxiety translated into the horror genre.
To be fair though, a CEO having an affair with a subordinate should be seen with at least some suspicion...
It does really take a load off my mind, knowing that he's completely out of binance now, and instead they have an independent CEO like... his wife. Yep. Can't get more independent than that.
I've just tested Strata on a simple 50 image vision benchmark. The task is to output the exact coordinates of a requested object. The result via Strata had a median error distance of 154.8 pixels, avg of 168.8. Running the exact same GGUF and vision adapter weights on llama.cpp gives me a median error of 46.5, avg 81.4.
To put that into perspective, here are some more numbers from other models via llama.cpp:
Median/Average
Qwen 3.5 9B BF16: 46.5 / 193.3
Qwen 3.6 35B Q4 K XL: 38.4 / 76.4
Qwen 3.5 122B Q3 K M: 32.9 / 68.6
The difference in vision performance is as large as the jump from a 9B model to a 35B model. All tests were performed at temp=0.
I have done no further testing, as these results line up perfectly with my expectations.
I had similar experience that same model running on Strata made more mistakes and hallucinated more when compare to llama.cpp.
Once the model swift-Qwen3.8 FN iq-xxs, got confused that it has already created few py files and they disappeared from disk, then I check all logs and it never created those files.
To be done right, such vision benchmark should consider the peculiarities of the vision tower, and was it quantized and optimized. So a lot of success/loss of quality may not be due to the transformer.
Second of all, the "find coordinates" of something is super difficult task of any model, so you tried to test a small quantized buddy with a tri-star challenge. Not sure what expectations were set.
disclaimer: myself do large volume VLM work daily, including in production, for more than 1.5 years now.
>To be done right, such vision benchmark should consider the peculiarities of the vision tower
As per my previous comment, I used the _exact same weights_ for the comparison. The vision tower is always kept as an unquantized BF16 file for GGUF, as I believe is the default.
>Second of all, the "find coordinates" of something is super difficult task of any model
It is in fact not (anymore), and most recent VLMs I tested have been standardized to point and bbox in a relative 0..1000 coordinate system with decent enough accuracy.
And finally, none of this excuses that Strata performs so much worse with the same weights. Which does kinda leave me confused as to what the point of this reply is.
> Which does kinda leave me confused as to what the point of this reply is.
to point out that 1)measuring VLM is not straight-forward, and needs considering what was actually ablated.
and that 2) perhaps such metric is the most challenging one for a brutally quantized and otherwise lobotomized model.... which otherwise performs well in other tasks (which I also doubt - for the record!).
i can subscribe to the idea that the Strata performs worse because it stripped the model of important quality, but not entirely to the fact it was really properly evaluated.
the way such models/attempts degrade can_be/is insightful on its own.
Real world: I use QFN38 to build 3d models. I use build123d + blender and this model is the first local model that does a good job. It is kind of amazing. This model is as good as DSV 4.1 on most tasks and I think it only loses when specific knowledge matters.
at least for vision? Are there similar comparisons for language? It seems like vision is often an afterthought when it comes to bootstrapping these newer inference engines
Vision functions the same way as language when inference is done. It's a stream of tokens.
It's just easier to measure the "right" answer (and deviation therefrom) on a vision task than a language one due to the underspecified nature of language.
my understanding is the vision component of the original model is an independent preprocessing step(except for things like Gemma 12b). And it would be possible for engine to have broken that phase of translation before it hits the real model as encoded text. I am not familiar with Strata engine and their claims, but this seems like an interesting way to test models with relatively straightforward inputs.
reply