Richard Juggins

Karma: 79

I am building a research agenda tackling catastrophic risks from AI, which I am documenting on my substack Working Through AI. Where it feels suited, I’m crossposting my work to LessWrong.

What Success Might Look Like

Richard Juggins17 Oct 2025 14:17 UTC

22 points

6 comments15 min readLW link

The Iceberg Theory of Meaning

Richard Juggins26 Jun 2025 12:13 UTC

10 points

9 comments5 min readLW link

How to specify an alignment target

Richard Juggins1 May 2025 21:11 UTC

14 points

2 comments12 min readLW link

Making alignment a law of the universe

Richard Juggins25 Feb 2025 10:44 UTC

0 points

3 comments15 min readLW link

Brighton Rationalish—Jun ’23 Meetup

Richard Juggins13 Jun 2023 17:36 UTC

1 point

0 comments1 min readLW link

Richard Juggins

What Suc­cess Might Look Like

The Ice­berg The­ory of Meaning

How to spec­ify an al­ign­ment target

Mak­ing al­ign­ment a law of the universe

Brighton Ra­tion­al­ish—Jun ’23 Meetup

What Success Might Look Like

The Iceberg Theory of Meaning

How to specify an alignment target

Making alignment a law of the universe

Brighton Rationalish—Jun ’23 Meetup