@testingham

Economics & AI @ @METR_Evals (ex-openai) https://xitter.cf/t.co/FZobuYjdOc

 San Francisco, CA
tecunningham.github.io/about.html
Joined March 2009
  • Tweets836
  • Following3.2K
  • Followers11.9K
94Media
1
14
5
156
Expanding on yesterday's single-sentence macro model, here's a longer version, trying to explain the key themes of macroeconomics as exchange among farmers in a village: tecunningham.github.io/posts…

Ten Farmers Model of Macroeconomics | Tom Cunningham

Tom Cunningham blog

tecunningham.github.io
tom cunningham
@testinghamOct 17
One sentence macro model: On the way out the door, every farmer's wife says to every farmer, "the weather's looking bad so don't buy as much at the market this week, but also don't sell our crops for less than the usual price."
2
5
52
4,568
tom cunningham retweeted
Cheryl Wu
@cherylwooooOct 17
I like @ramez’s article, but I worry that experiments are an input, not an output. As AI capabilities go up, it is not obvious what should happen to the number of experiments. It is possible that AI with better research taste could produce more progress with fewer experiments by identifying promising ideas and avoiding unproductive trials. One could imagine that the 1.6x experiments are each 10x more efficient than before, so the ultimate algorithm efficiency improvement is 16x. Again, what we really need is to measure algorithmic progress!
Noah Smith 🐇🇺🇸🇺🇦🇹🇼
@NoahpinionSep 27
In this long and excellent guest post, the great @ramez explains why he's skeptical about Recursive Self-Improvement: noahpinion.blog/p/wheres-the…

Where’s the “intelligence explosion”?

Ramez Naam gives a skeptic’s take on Recursive Self-Improvement.

noahpinion.blog
3
4
56
3,636
one stanza macro model: Tonight the baker eats just what she baked ‍‍‍‍‍‍‍‍ the fisherman eats just what he caught Because this morning at the market ‍‍‍‍‍‍ everyone tried to sell more than they bought.
1
7
420
74,314
One sentence macro model: On the way out the door, every farmer's wife says to every farmer, "the weather's looking bad so don't buy as much at the market this week, but also don't sell our crops for less than the usual price."
26
56
13
2,022
438,258
tom cunningham retweeted
METR
@METR_EvalsOct 14
If an AI developer was on track to lose control of its internal agents, would anyone outside the company know? Today, we are sharing METR’s vision for how we would work with AI developers to openly assess and share evidence about this.
47
111
29
679
79,675
Interactive version: tecunningham.github.io/eci-b…
9
477
Slightly scary that the current frontier model (Opus 5.5) doesn't get below 50% on any of its benchmarks.
3
17
1,392
ECI and its components ECI treats each benchmark as having a logistic distribution, so it's linear in log-odds. This implies if you plot log-odds of each benchmark the lines should all be increasing together, though each has a different x-position (difficulty) and different dispersion (slope).
5
3
2
87
4,637

No more items