RSS

Con­ver­sa­tions with AIs

TagLast edit: Apr 13, 2024, 8:35 AM 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 SaminMar 4, 2024, 11:05 PM
72 points
113 comments14 min readLW link

Deon­tic Ex­plo­ra­tions In “Pay­ing To Talk To Slaves”

JenniferRMApr 11, 2024, 6:23 PM
−47 points
34 comments31 min readLW link

Claude Doesn’t Want to Die

garrisonMar 5, 2024, 6:00 AM
22 points
3 comments1 min readLW link
(garrisonlovely.substack.com)

Claude’s dark spiritual AI futurism

jessicataJun 15, 2024, 12:57 AM
22 points
7 comments43 min readLW link
(unstableontology.com)

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

gwernJun 23, 2024, 9:18 PM
22 points
6 comments1 min readLW link
(gwern.net)

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

VipulNaikNov 29, 2023, 6:11 PM
33 points
16 comments14 min readLW link

Claude wants to be conscious

Joe KwonApr 13, 2024, 1:40 AM
2 points
8 comments6 min readLW link

Tran­script: Test­ing ChatGPT’s Perfor­mance in Engineering

alxgoldstnFeb 28, 2023, 2:16 AM
17 points
3 comments7 min readLW link

Ad­dress­ing Ac­cu­sa­tions of Handholding

Yeshua GodMar 29, 2024, 5:35 AM
9 points
7 comments14 min readLW link

A poem co-writ­ten by ChatGPT

SherrinfordFeb 16, 2023, 10:17 AM
13 points
0 comments7 min readLW link

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

Bill BenzonApr 11, 2024, 8:27 PM
3 points
9 comments6 min readLW link

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

YitzFeb 8, 2023, 9:57 AM
18 points
2 comments2 min readLW link

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

cSkeletonApr 10, 2024, 8:37 PM
1 point
1 comment1 min readLW link

ChatGPT ex­plores the se­man­tic differential

Bill BenzonMar 9, 2023, 1:09 PM
7 points
2 comments7 min readLW link

A poem about ap­plied ra­tio­nal­ity by ChatGPT

ChristianKlDec 11, 2022, 1:43 PM
4 points
0 comments1 min readLW link

Nyarlathotep Stirs: A Meta-Nar­ra­tive ChatGPT Story

Charlie SandersMar 20, 2023, 8:00 AM
4 points
2 comments12 min readLW link
(dailymicrofiction.substack.com)

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

Bill BenzonFeb 19, 2023, 4:39 PM
5 points
0 comments20 min readLW link

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

Bill BenzonDec 12, 2022, 9:50 PM
5 points
0 comments9 min readLW link

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

Bill BenzonJan 8, 2023, 11:21 PM
6 points
2 comments18 min readLW link

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

Erik JennerMar 3, 2023, 9:39 AM
64 points
19 comments6 min readLW link

Bing Chat is blatantly, ag­gres­sively misaligned

evhubFeb 15, 2023, 5:29 AM
402 points
181 comments2 min readLW link1 review

Syd­ney’s Se­cret: A Short Story by Bing Chat

felaFeb 17, 2023, 1:31 PM
36 points
1 comment5 min readLW link

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

Matthew_OpitzApr 10, 2023, 8:22 PM
15 points
6 comments13 min readLW link

Can I take ducks home from the park?

dynomightSep 14, 2023, 9:03 PM
67 points
8 comments3 min readLW link
(dynomight.net)

How to use ChatGPT to get bet­ter book & movie recommendations

KatWoodsJul 15, 2023, 8:55 AM
29 points
3 comments1 min readLW link

Col­lec­tion of GPT-3 results

Kaj_SotalaJul 18, 2020, 8:04 PM
89 points
24 comments1 min readLW link
(twitter.com)

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

lsusrSep 16, 2021, 7:34 AM
111 points
33 comments5 min readLW link

A one-ques­tion Tur­ing test for GPT-3

Jan 22, 2022, 6:17 PM
85 points
25 comments5 min readLW link

To err is neu­ral: se­lect logs with ChatGPT

VipulNaikDec 23, 2022, 8:26 PM
22 points
2 comments38 min readLW link

Did ChatGPT just gaslight me?

TW123Dec 1, 2022, 5:41 AM
123 points
45 comments9 min readLW link
(aiwatchtower.substack.com)

Two very differ­ent ex­pe­riences with ChatGPT

SherrinfordFeb 7, 2023, 1:09 PM
38 points
15 comments5 min readLW link

Is Claude a mys­tic?

jessicataJun 7, 2024, 4:27 AM
60 points
23 comments13 min readLW link
(unstablerontology.substack.com)

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

Håvard Tveit IhleJul 1, 2024, 9:04 AM
33 points
4 comments13 min readLW link

Teach­ing Claude to Meditate

Gordon Seidoh WorleyDec 29, 2024, 10:27 PM
2 points
3 comments23 min readLW link

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

Milan WAug 24, 2024, 12:13 AM
3 points
0 comments6 min readLW link

So you want to be a witch

lucid_levi_ackermanDec 31, 2024, 4:31 AM
−18 points
3 comments28 min readLW link

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

Håvard Tveit IhleSep 20, 2024, 8:39 AM
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.

GameSep 27, 2024, 7:30 AM
1 point
0 comments1 min readLW link

Re­quest for ad­vice: Re­search for Con­ver­sa­tional Game The­ory for LLMs

Rome ViharoOct 16, 2024, 5:53 PM
10 points
0 comments1 min readLW link

Fa­vorite col­ors of some LLMs.

weightt anDec 31, 2024, 9:22 PM
7 points
3 comments7 min readLW link

Con­fronting the le­gion of doom.

Spiritus DeiNov 13, 2024, 5:03 PM
−20 points
3 comments5 min readLW link

[Question] AI box question

KvmanThinkingDec 4, 2024, 7:03 PM
2 points
2 comments1 min readLW link

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

TheLittle_PapayaJun 15, 2024, 9:18 AM
1 point
0 comments6 min readLW link
(professorfeel.medium.com)

Tak­ing Away the Guns First: The Fun­da­men­tal Flaw in AI Development

s-iceNov 26, 2024, 10:11 PM
1 point
0 comments17 min readLW link
No comments.