Skip to main content

ScourDiscover Docs

Discover About Docs Changelog

You are offline. Trying to reconnect...

Copied to clipboard

Unable to share or copy to clipboard

Back to article

dwarkesh.com5w5 weeks ago

Notes on pretraining parallelisms and failed training runs. (opens in new tab)

Covered by tldr.techDiscussed on Hacker News

|

|

Feeds

Dwarkesh Podcast: Blog dwarkesh.com

The sample efficiency black hole1w1 week ago

The mistake of conflating intelligence and power5w5 weeks ago

Notes on pretraining parallelisms and failed training runs.5w5 weeks ago

Dwarkesh Podcast dwarkesh.com

The data black hole at the center of AI1d1 day ago

Ada Palmer – Machiavelli is the most misunderstood thinker of all time4d4 days ago

The sample efficiency black hole1w1 week ago

+2 more in the past month

TLDR FEED Feed bullrich.dev

World Cup Crypto Fraud Wave: Why Betting Markets Need Better Fan-Safety UX (9 minute read)1d1 day ago

Agents breaking on real websites? See how Browserbase runs 35M+ sessions a month (Sponsor)1d1 day ago

What's an AI runtime? (Sponsor)1d1 day ago

+358 more in the past week

Hacker News: Newest hnrss.org

GWT 2.13.120m20 minutes ago

Pulse, lightweight Linux monitoring dashboard written in C22m22 minutes ago

Windows UI evolution: Clicking an unassociated file29m29 minutes ago

+396 more in the past day

Keyboard Shortcuts

Navigation

Next / previous post: j/k
Open post: oorEnter
Preview post: v

Post Actions

Love post: a
Like post: l
Dislike post: d
Undo reaction: u
Save / unsave: s

Recommendations

Add interest / feed: Enter
Not interested: x

Go to

Home: gh
Interests: gi
Feeds: gf
Likes: gl
History: gy
Changelog: gc
Settings: gs
Discover: gb
Search: /

Pagination

Next page: n
Previous page: p

General

Show this help: ?
Submit feedback: !
Close modal / unfocus: Esc

Press ? anytime to show this help

Docs Blog (opens in new tab)Changelog Roadmap (opens in new tab)