E-Reverance

She actively lies on twitter

https://x.com/ByrneHobart/status/2105368471198380131

Apart from their own data, a lot of people's anecdotal experience is that its pretty accurate, why would they need to banned for that?

I'm talking about bringing up a specific outdated details, not about simplifying it

I get that this is for explaining GPT-2, but I really hope laymen don't use it as an example of how modern models work (ex. absolute positional encoding is no longer used)

edit: I know that it mentions its not modern, but these kinds of details have major implications in terms of the representations a model can learn, which is in many ways the most important part!

Jacob Tsimerman claims [1] we might have superhuman expositors by April, so then what?

[1] https://youtu.be/H7_d_sgui6o?t=4436 (timestamped url)

"a tiger is just made of atoms"

Given the size of your team, have y'all considered going into niche like making a DLSS 5 competitor

In my opinion its a great idea because you get reuse hidden states which allows you to do something akin to thinking/[online learning]. If you only evolve use input space outputs you're dealing with more decoding pressure.

Also related to what I was saying see these:

https://arxiv.org/pdf/2609.16372v1

https://arxiv.org/pdf/2609.01449v1 (this one is quite mindblowing cause they noise they the actual input space every time but it still works)

https://arxiv.org/pdf/2609.11801

Slightly off-topic but thoughts on this https://arxiv.org/pdf/2410.08159

There are better ways to apply SVD to images than the way its usually taught

https://www.youtube.com/watch?v=ZGwVlnuuzt4

> there will be actual consequences for this.

Not implausible but what exactly because sometimes when people throw that phrase its just aggrieved cope

I actually strongly disagree, I think this is the natural tendency of many losers and there is a disproportionate amount of them on the internet

The HN poster of this owns an extremely anti-social page btw https://boomerdeathwatch.com/ . Before he claims that "they deserved it", note how the page itself does nothing but make them look like a weirdo lol

Yeah a lot of people have failed to internalize a lot of the meta-lessons of current culture wars

I don't share my friend's music taste and record stores for sure don't have what I like (its usually small soundcloud accounts). Also the things I like about a song are not genre bound, its usually very subtle things that are unsearchable, hence even of the songs I like I usually only like ~30% of the song itself. With a personally tuned reward model I can strictly focus on amplifying the subtleties instead of searching by means of exhausting indirection

Because there is a shortage of songs I like. I loop the same songs for weeks until I can find a new song

I really want to like ai music but none of them seem to be trained on reward models that reward "ambiance" or any sort of interesting sound design (which this paper obviously doesn't even concern), which might be reflective of the people training them not having niche music tastes

The figure on page 5 in [1] is pretty insane

[1] https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash/blob/...

The scifi pov has a good track record as this point, you people gotta be more open minded

whoops lol

Smart fridges are a pathological virus, yes /jk

At this point the primary axes for improvement seem to only/mostly be speed and personalized reward models. We seemingly have the general of notion "learning" and "intelligence" functionally complete

Are y'all using any sort of self-distillation similar to https://self-evo.github.io/ to sharpen representations?

Neither do LLMs https://arxiv.org/pdf/2607.03502

I definitely belong to the latter camp. After LLMs I view everything humans do very systematically and whenever said thing still feels fuzzy I just treat it as having a noise/smoothing term

Apologies for making the reply chain so long but I think a video like this somewhat proves how a lot of aesthetic preferences can be *ultra* sensitive to small visual details : https://youtu.be/twcMra_67-w?t=88

The video is timestamped to open at the comparison frame. I don't think an LLM can tell the quality difference without direct reference for comparison

I strictly meant using the embeddings for training a reward model, not the generator. By good for generation I just meant the reward model might find more visual cues for aesthetic preference and avoid some of the spurious semantic correlation CLIP has

> Like Dino-V3 or something of that ilk?

Yes but for generation LingBot seems uniquely compelling https://technology.robbyant.com/lingbot-vision because it has a very strong spatial prior

Regarding the LAION aesthetic predictor footnote, I don't see why a modern model and nonlinear classifier won't do a good a job. Is there a fundamental technical problem with the idea?

No one mentioning the possibility of it being StepFun?