YB

6.1K posts

YB banner
YB

YB

@yb_effect

Katılım Mayıs 2021
4.2K Takip Edilen22.5K Takipçiler
YB retweetledi
tylercowen
tylercowen@tylercowen·
My new "generative book," fully written by me, the last chapter is on how AI will revolutionize the sciences (and us): tylercowen.com/marginal-revol…
English
9
64
358
39.4K
YB retweetledi
sophia
sophia@sodofi_·
i built a telegram bot that turns your social media feed into an agent brain how it works: > send content to the bot > bot stores content on obsidian > use obsidian file path for your agents context the smarter the brain the smarter the agent
English
63
20
379
33.8K
YB retweetledi
Justin Skycak
Justin Skycak@justinskycak·
Intellectual obesity is what happens when you consume too much and produce too little.
English
101
1.4K
7.5K
337K
YB
YB@yb_effect·
@signulll can a memory come back "to life" after it's been decayed? i wonder how relevant the context has to be in order for it to be indexed on again
English
0
0
1
125
signüll
signüll@signulll·
this post cuts to something i’ve been personally thinking & posting about a lot which is how the human mind’s forgetting machinery is underrated as a design primitive. in our first product we’ve built our memory model around a specific decay factor influenced by multiple variables.. each memory degrades by default unless actively reinforced. this relies on a combination of recency, retrieval frequency, & contextual reactivation. this ain’t perfect any means. but it’s annoying af that current llm memory implementations essentially treat every retrieved fact as equally alive. that’s likely not how cognition works. idk if our approach is the final answer but i’m increasingly convinced the forgetting curve is as important as the learning curve. & the right memory model may be way more about what you let go than what you store.
Andrej Karpathy@karpathy

One common issue with personalization in all LLMs is how distracting memory seems to be for the models. A single question from 2 months ago about some topic can keep coming up as some kind of a deep interest of mine with undue mentions in perpetuity. Some kind of trying too hard.

English
69
27
642
55.3K
YB
YB@yb_effect·
@johncoogan @tbpn Just realized that uber mc is 30x Lyft rn, thought they were right next to each other for the longest time just bc it was that way pre-pandemic
English
0
0
0
580
YB
YB@yb_effect·
clear thinking is downstream of having a commonplace practice. now more so than ever
kepano@kepano

@benspringwater the desire to hold thoughts in our hands is as old as humanity

English
0
0
3
479
YB
YB@yb_effect·
@notbylght barbell strategy of doing without thinking and thinking without doing works best. trying both at the same time is what holds us back
English
0
0
1
42
notbylght
notbylght@notbylght·
@yb_effect andressen fuming wat good is self awareness innit
English
1
0
1
38
YB
YB@yb_effect·
You still need to be self aware of whether you’re actually being productive with agents or just doom prompting to avoid solving the problem
YB tweet media
English
2
0
4
303
YB retweetledi
Minh Nguyen
Minh Nguyen@oneminhnguyen·
study old ads
Minh Nguyen tweet media
English
56
315
3.9K
366.4K
YB retweetledi
Ashley Mayer
Ashley Mayer@ashleymayer·
This is my #1 piece of comms advice for startup founders.
Ashley Mayer tweet media
English
27
50
729
42.3K
kepano
kepano@kepano·
what are the chances this thing will be abandonware in a month? you can make something in a few days but will you commit to maintaining and improving it for the next few years?
English
98
61
1.3K
103.9K
YB
YB@yb_effect·
reminds me of @collision's "the world is a museum of passion projects"
YB tweet media
English
1
0
5
291
YB retweetledi
Neet
Neet@neet_sol·
pattern recognition is the highest paying job in the world right now
English
234
1.1K
12.8K
323.3K
YB
YB@yb_effect·
@ccarella @_brianpotter same, loving it so far. all the examples make you realize how much of the things around us we take for granted
English
0
0
1
16
YB
YB@yb_effect·
The intro section of The Origins of Efficiency by @_brianpotter hooks the reader so well. - Acknowledges up front that efficiency is not a sexy topic compared to miracle moments praised in tech & science (0 -> 1 vs 1 -> 100) - Tells the story of Penicillin as it normally is and then catches the reader off guard by saying "aha tricked you" - Explains that the Alexander Fleming discovery tale of Penicillin would be useless without 99% of the efficiency work that came in the years after - Proceeds to double down with similar stories in agriculture, textiles, and printing to back his claim that "efficiency is the engine that powers human civilization" By the end of the intro, the reader is on board with the fact that though it's always serendipitous breakthrough stories (car exterior) that get the praise, they're truly nothing without the systems and processes (the engine) that get built after to support the discovery.
YB tweet media
English
1
0
4
471
YB retweetledi
Benjamin Kunkel
Benjamin Kunkel@kunktation·
How about taste?
Benjamin Kunkel tweet media
English
17
49
476
173.7K
YB retweetledi
Patrick McKenzie
Patrick McKenzie@patio11·
Doing the reading is a superpower, and it's even better in a world where "no one" is doing the reading. (Inspired by a conversation I had with some college students.)
English
51
231
2.5K
115.6K
YB
YB@yb_effect·
once a month I have the thought that if I just read every Stripe press book all my problems will be solved and end up buying another one and reading none of it
English
0
0
5
560
YB
YB@yb_effect·
writing is thinking
YB tweet media
English
0
0
5
419