RSS

Meta-Honesty

TagLast edit: 16 Apr 2020 22:20 UTC by Ruby

Meta-Honesty is the attempt to be honest about in which situations one will not be honest. It derives from the recognition that an object-level commitment to never lie under any possible circumstance is untenable. A meta-honest person might say something like “I will lie in circumstances similar to an axe-wielding murderer coming to my door and enquiring after the location of my friend.”

Meta-Hon­esty: Firm­ing Up Hon­esty Around Its Edge-Cases

Eliezer Yudkowsky29 May 2018 0:59 UTC
143 points
155 comments27 min readLW link4 reviews

Firm­ing Up Not-Ly­ing Around Its Edge-Cases Is Less Broadly Use­ful Than One Might Ini­tially Think

Zack_M_Davis27 Dec 2019 5:09 UTC
132 points
43 comments8 min readLW link2 reviews

[Re­view] Meta-Hon­esty (Ben Pace, Dec 2019)

Ben Pace10 Dec 2019 0:37 UTC
29 points
4 comments10 min readLW link

Deep Honesty

Aletheophile7 May 2024 20:31 UTC
165 points
26 comments9 min readLW link

Notes on Honesty

David Gross28 Oct 2020 0:54 UTC
46 points
7 comments20 min readLW link

Con­sis­tent Glo­ma­riza­tion should be feasible

Stuart_Armstrong4 May 2020 10:06 UTC
17 points
12 comments1 min readLW link

Coun­ter­fac­tual Mug­ging Poker Game

Scott Garrabrant13 Jun 2018 23:34 UTC
126 points
4 comments1 min readLW link

The Mir­ror Trap

Cameron Berg6 Jun 2025 22:30 UTC
94 points
13 comments4 min readLW link

The In­co­her­ence of Honesty

Gordon Seidoh Worley8 Jun 2018 2:28 UTC
20 points
16 comments3 min readLW link

On the Chatham House Rule

Scott Garrabrant13 Jun 2018 21:41 UTC
69 points
25 comments4 min readLW link1 review

Not Tech­ni­cally Lying

Psychohistorian4 Jul 2009 18:40 UTC
51 points
86 comments4 min readLW link

Lan­guage Field Re­con­struc­tion The­ory: A User-Origi­nated Ob­ser­va­tion of Tier Lock and Se­man­tic Per­son­al­ity in GPT-4o

許皓翔15 Jun 2025 16:28 UTC
1 point
0 comments2 min readLW link

The Onion Test for Per­sonal and In­sti­tu­tional Honesty

27 Sep 2022 15:26 UTC
164 points
31 comments3 min readLW link3 reviews

EchoFu­sion VX1C38 – A Si­mu­la­tion-Based Model for AI Safety

Vishvas Goswami2 Jul 2025 10:48 UTC
0 points
0 comments4 min readLW link

De­sign­ing a Be­hav­ioral Ar­chi­tec­ture for Self-Direction

Slotherium Studios4 Aug 2025 16:46 UTC
1 point
0 comments2 min readLW link
No comments.