Viewing profile — mrfox321
mrfox321
HN member- Joined
- Fri, Jul 26, 2019, 12:28 AM UTC
- HN karma
- 396
- Public activity
- 193 items
- HN profile
- View on Hacker News ↗
About mrfox321
No profile information was provided.
Recent public activity
- comment
-
comment
Comment #49068704
No. Distillation trains on a teach model's logits or output tokens.
-
comment
Comment #46089207
... the toppings contains potassium benzoate
-
comment
Comment #44502794
I know right? They have always been behind. Why would this time be any different?
-
comment
Comment #44282185
Read the paper. They control for the data being in-distribution Their dataset also has examples of the problem being solved.
-
comment
Comment #44054151
Sounds like excuses
-
comment
Comment #43289112
They didn't show this, they just increased the length where accuracy breaks down.
-
comment
Comment #43102882
What's your leg circumference at, now? Mine is also smaller, due to patella tendinopathy.
-
comment
Comment #42577630
Who do you think the shareholders are? What demographic are they?
-
comment
Comment #42471909
It's because they originally built their recommendation system to recommend friends and their content. Here, the social graph makes complete sense as the foundation for their simpl…
- comment
-
comment
Comment #42471769
I mean, it's their serving infra, but not their features. See my reply in another parent comment.
-
comment
Comment #42471728
It's simpler intuition but more complex from a data / ml perspective. Their algorithm is really built around their features. Specifically, temporal representations of user interest…
-
comment
Comment #42471671
IG users and Tiktok users were / are quite similar. Especially when Tiktok wasn't yet eating IGs lunch.
-
comment
Comment #42471174
IG has plenty of data (I did ML at IG). Don't be naive.
-
comment
Comment #42470991
Not true. Why do IG reels and YouTube shorts suck, then? They clearly built something superior. And it can't seem to be matched by the biggest tech companies.
-
comment
Comment #42270315
At a big co I worked at, the lack of consistency between trading systems caused money to (dis)appear (into)out of thin air. Prior to one of these hiccups, I hypothesized, given how…
-
comment
Comment #42261028
Second order methods, and their approximations, can be used in weight updating, too.
-
comment
Comment #42050584
20 to 15 is insane. Are these low 15s or high 15s? Regardless, that's fantastic progress. Do you respond better to intervals or longer aerobic efforts? I ask because Ive always won…
-
comment
Comment #41776430
simultaneity is relative. That's all.
-
comment
Comment #41687384
More importantly, he invented diffusion models: http://proceedings.mlr.press/v37/sohl-dickstein15.pdf
-
comment
Comment #41541052
China does this, for better or for worse.
-
comment
Comment #41223459
Similar, but specialized to softmax(QK)V computation
-
comment
Comment #41215646
These people want to win. It's not just society wanting to define winners.
-
comment
Comment #40298408
Michael Phelps is an alien..