Conversations with AIs

TagLast edit: 13 Apr 2024 8:35 UTC by the gears to ascension

A tag for conversations with, rather than about, digital minds. This tag needs expansion and checking for duplicate tags; I checked shallowly before creating it. Should it be merged with AI Evaluations?

Claude 3 claims it’s conscious, doesn’t want to die or be modified

Mikhail Samin4 Mar 2024 23:05 UTC

72 points

113 comments14 min readLW link

Claude Doesn’t Want to Die

garrison5 Mar 2024 6:00 UTC

22 points

3 comments1 min readLW link

(garrisonlovely.substack.com)

Deontic Explorations In “Paying To Talk To Slaves”

JenniferRM11 Apr 2024 18:23 UTC

4 points

10 comments31 min readLW link

“On the Impossibility of Superintelligent Rubik’s Cube Solvers”, Claude 2024 [humor]

gwern23 Jun 2024 21:18 UTC

22 points

6 comments1 min readLW link

(gwern.net)

Claude’s dark spiritual AI futurism

jessicata15 Jun 2024 0:57 UTC

22 points

7 comments43 min readLW link

(unstableontology.com)

Claude estimates 30-50% likelihood x-risk

amelia19 Mar 2024 2:22 UTC

3 points

2 comments2 min readLW link

ChatGPT 4 solved all the gotcha problems I posed that tripped ChatGPT 3.5

VipulNaik29 Nov 2023 18:11 UTC

33 points

16 comments14 min readLW link

Claude wants to be conscious

Joe Kwon13 Apr 2024 1:40 UTC

2 points

8 comments6 min readLW link

Transcript: Testing ChatGPT’s Performance in Engineering

alxgoldstn28 Feb 2023 2:16 UTC

17 points

3 comments7 min readLW link

To err is neural: select logs with ChatGPT

VipulNaik23 Dec 2022 20:26 UTC

22 points

2 comments38 min readLW link

Addressing Accusations of Handholding

Yeshua God29 Mar 2024 5:35 UTC

9 points

7 comments14 min readLW link

A poem co-written by ChatGPT

Sherrinford16 Feb 2023 10:17 UTC

13 points

0 comments7 min readLW link

ChatGPT defines 10 concrete terms: generically, for 5- and 11-year-olds, and for a scientist

Bill Benzon11 Apr 2024 20:27 UTC

3 points

9 comments6 min readLW link

Self-Awareness (and possible mode collapse around it) in ChatGPT

Yitz8 Feb 2023 9:57 UTC

18 points

2 comments2 min readLW link

[Question] What should we tell an AI if it asks why it was created?

cSkeleton10 Apr 2024 20:37 UTC

1 point

1 comment1 min readLW link

ChatGPT explores the semantic differential

Bill Benzon9 Mar 2023 13:09 UTC

7 points

2 comments7 min readLW link

A poem about applied rationality by ChatGPT

ChristianKl11 Dec 2022 13:43 UTC

4 points

0 comments1 min readLW link

Nyarlathotep Stirs: A Meta-Narrative ChatGPT Story

Charlie Sanders20 Mar 2023 8:00 UTC

4 points

2 comments12 min readLW link

(dailymicrofiction.substack.com)

Exploring Lily’s world with ChatGPT [things an AI won’t do]

Bill Benzon19 Feb 2023 16:39 UTC

5 points

0 comments20 min readLW link

Let’s go meta: Grammatical knowledge and self-referential sentences [ChatGPT]

Bill Benzon12 Dec 2022 21:50 UTC

5 points

0 comments9 min readLW link

ChatGPT tells stories about XP-708-DQ, Eliezer, dragons, dark sorceresses, and unaligned robots becoming aligned

Bill Benzon8 Jan 2023 23:21 UTC

6 points

2 comments18 min readLW link

Sydney can play chess and kind of keep track of the board state

Erik Jenner3 Mar 2023 9:39 UTC

64 points

19 comments6 min readLW link

Bing Chat is blatantly, aggressively misaligned

evhub15 Feb 2023 5:29 UTC

400 points

180 comments2 min readLW link

Sydney’s Secret: A Short Story by Bing Chat

fela17 Feb 2023 13:31 UTC

36 points

1 comment5 min readLW link

Bing AI Generating Voynich Manuscript Continuations—It does not know how it knows

Matthew_Opitz10 Apr 2023 20:22 UTC

15 points

6 comments13 min readLW link

Can I take ducks home from the park?

dynomight14 Sep 2023 21:03 UTC

67 points

8 comments3 min readLW link

(dynomight.net)

How to use ChatGPT to get better book & movie recommendations

KatWoods15 Jul 2023 8:55 UTC

29 points

3 comments1 min readLW link

Collection of GPT-3 results

Kaj_Sotala18 Jul 2020 20:04 UTC

89 points

24 comments1 min readLW link

(twitter.com)

I wanted to interview Eliezer Yudkowsky but he’s busy so I simulated him instead

lsusr16 Sep 2021 7:34 UTC

111 points

33 comments5 min readLW link

A one-question Turing test for GPT-3

Paul Crowley and rosiecam

22 Jan 2022 18:17 UTC

85 points

25 comments5 min readLW link

Did ChatGPT just gaslight me?

TW1231 Dec 2022 5:41 UTC

123 points

45 comments9 min readLW link

(aiwatchtower.substack.com)

Is analyzing LLM behavior a valid means for assessing potential consciousness, as described by global workspace theory and higher order theories?

amelia11 Mar 2024 19:37 UTC

1 point

1 comment12 min readLW link

How is Chat-GPT4 Not Conscious?

amelia28 Feb 2024 0:00 UTC

19 points

27 comments13 min readLW link

Two very different experiences with ChatGPT

Sherrinford7 Feb 2023 13:09 UTC

38 points

15 comments5 min readLW link

Is Claude a mystic?

jessicata7 Jun 2024 4:27 UTC

60 points

23 comments13 min readLW link

(unstablerontology.substack.com)

How good are LLMs at doing ML on an unknown dataset?

Håvard Tveit Ihle1 Jul 2024 9:04 UTC

33 points

4 comments13 min readLW link

Using ideologically-charged language to get gpt-3.5-turbo to disobey it’s system prompt: a demo

Milan W24 Aug 2024 0:13 UTC

2 points

0 comments6 min readLW link

Confronting the legion of doom.

Spiritus Dei13 Nov 2024 17:03 UTC

−18 points

2 comments5 min readLW link

o1-preview is pretty good at doing ML on an unknown dataset

Håvard Tveit Ihle20 Sep 2024 8:39 UTC

67 points

1 comment2 min readLW link

[Question] How to devour 5000 pages within a day if Chatgpt crashes upon the +50mb file containing the content? Need some recommendations.

Game27 Sep 2024 7:30 UTC

1 point

0 comments1 min readLW link

Will AI Kill Us All, Or Is It Showing Us Who We’ve Become?

TheLittle_Papaya15 Jun 2024 9:18 UTC

1 point

0 comments6 min readLW link

(professorfeel.medium.com)

Request for advice: Research for Conversational Game Theory for LLMs

Rome Viharo16 Oct 2024 17:53 UTC

10 points

0 comments1 min readLW link

No comments.

Con­ver­sa­tions with AIs

Conversations with AIs