Advertisement ยท 728 ร— 90

Posts by Parth Shah

All the classic feeds (Popular with friends, Quiet posters, Following) are endlessly repetitive.

Feed engineers - please come up with feeds that remove posts based on these repetitiveness criteria. This will make bsky atleast 2x more useful

1 year ago 3 0 0 0

2. Usually I open bluesky for a couple of minutes, browse and log off. If i come back in 30-60 minutes, a majority of the top 10 posts are going to be the same ones I've seen already which turns me off.

1 year ago 0 0 0 0

Repetitiveness is my biggest problem with bluesky.

Problematic examples:

1. After I've done interacting with a thread. I dont want to keep seeing new replies or quote tweets on it.

1 year ago 0 0 2 0

Linking the thread on the paper from the main author for people who are interested bsky.app/profile/laur...

1 year ago 1 0 0 0

I disagree

(low hanging fruit im sorry)

1 year ago 3 0 0 0

Reposting as a mechanism of bookmarking (public)

1 year ago 0 0 0 0

> The decoder often effectively is a conditional GAN

Any intuition/math/papers you can share to understand this? It's not v clear to me.

1 year ago 2 0 1 0

After training on these datasets - did you test on any other datasets not from the same distribution? (Like a coding test set instead of GSM8K test set).

How much distribution change can AdaptiveDecoder handle?

1 year ago 0 0 0 0

Great work!
Nitpick: Rewrite first tweet for emphasis on impact
- Learn to predict temperature to auto-adjust for creativity vs factuality
- Against fix-temperature, our predicted temperature wins 10% more across GSM8K and UltraFeedback datasets.
- New layer and model to learn any hyperparameter

1 year ago 0 0 0 0

3/6 is not bad either way

1 year ago 1 0 0 0
Advertisement

Right then if you phrase distribution change as learning - when context changes the distribution wouldn't you call it "In-context learning"?

I see the above relation of B follows from A well defined.

What do you see is missing?

1 year ago 0 0 0 0

Curious to understand why you think probability of y can change when given x and D are fixed.

That is not true of any probability distributions.

1 year ago 0 0 1 0

Yea I phrased it as - we "should" promote them, when I meant the current framework "should" promote them regardless.

1 year ago 0 0 0 0

Removing chaos by yourself is low visibility indeed. However, wouldn't you agree that someone one who can influence enough people to remove said chaos should ve promoted for their influence and culture shaping capabilities?

1 year ago 0 0 1 0

Awesome slides. Thank you :)

1 year ago 1 0 0 0

This is an excellent list. I would probably add @colah.bsky.social's Transformer Circuits Initial Thoughts youtube playlist along with the corresponding paper.

Do you have a website for the course I can follow?

1 year ago 1 0 1 0

Apple needs to add this to its vision pro on the minimum

1 year ago 0 0 0 0
Advertisement

Appreciate this.

More similar categorizations - "dumb" questions/obvious questions that everybody thinks they know the answer to/in between the line questions.

1 year ago 0 0 0 0