Mikeysee (@mikeysee) 's Twitter Profile
Mikeysee

@mikeysee

Professional Tinkerer @ convex.dev

ID: 20140140

linkhttp://www.mikecann.blog calendar_today05-02-2009 11:36:39

9,9K Tweet

699 Takipçi

624 Takip Edilen

Benjamin Todd (@ben_j_todd) 's Twitter Profile Photo

Why can AIs code for 1h but not 10h? A simple explanation: if there's a 10% chance of error per 10min step (say), the success rate is: 1h: 53% 4h: 8% 10h: 0.002% Toby Ord has tested this 'constant error rate' theory and shown it's a good fit for the data chance of

Why can AIs code for 1h but not 10h?

A simple explanation: if there's a 10% chance of error per 10min step (say), the success rate is:

1h: 53%
4h: 8%
10h: 0.002%

<a href="/tobyordoxford/">Toby Ord</a> has tested this 'constant error rate' theory and shown it's a good fit for the data

chance of
James Cowling (@jamesacowling) 's Twitter Profile Photo

The #1 rule of scalable systems is to avoid congestion collapse. This is when a system slows down, starts timing out, then gets hammered by retries that also time out, in an infinite loop. I’ve accidentally broken Dropbox and Convex this way. Here's 7 tips how not to:

The #1 rule of scalable systems is to avoid congestion collapse.

This is when a system slows down, starts timing out, then gets hammered by retries that also time out, in an infinite loop.

I’ve accidentally broken Dropbox and Convex this way. Here's 7 tips how not to: