Audio versions of essays by Joe Carlsmith. Philosophy, futurism, and other topics. Text versions at joecarlsmith.com.
…
continue reading
1
Takes on "Alignment Faking in Large Language Models"
1:27:54
1:27:54
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
1:27:54
What can we learn from recent empirical demonstrations of scheming in frontier models? Text version here: https://joecarlsmith.com/2024/12/18/takes-on-alignment-faking-in-large-language-models/De către Joe Carlsmith
…
continue reading
1
(Part 2, AI takeover) Extended audio from my conversation with Dwarkesh Patel
2:07:33
2:07:33
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
2:07:33
Extended audio from my conversation with Dwarkesh Patel. This part focuses on the basic story about AI takeover. Transcript available on my website here: https://joecarlsmith.com/2024/09/30/part-2-ai-takeover-extended-audio-transcript-from-my-conversation-with-dwarkesh-patelDe către Joe Carlsmith
…
continue reading
1
(Part 1, Otherness) Extended audio from my conversation with Dwarkesh Patel
3:58:38
3:58:38
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
3:58:38
Extended audio from my conversation with Dwarkesh Patel. This part focuses on my series "Otherness and control in the age of AGI." Transcript available on my website here: https://joecarlsmith.com/2024/09/30/part-1-otherness-extended-audio-transcript-from-my-conversation-with-dwarkesh-patel/
…
continue reading
1
Introduction and summary for "Otherness and control in the age of AGI"
12:23
12:23
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
12:23
This is the introduction and summary for my series "Otherness and control in the age of AGI." Text version here: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-agiDe către Joe Carlsmith
…
continue reading
1
Second half of full audio for "Otherness and control in the age of AGI"
4:11:02
4:11:02
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
4:11:02
Second half of the full audio for my series on how agents with different values should relate to one another, and on the ethics of seeking and sharing power. First half here: https://joecarlsmithaudio.buzzsprout.com/2034731/15266490-first-half-of-full-audio-for-otherness-and-control-in-the-age-of-agi PDF of the full series here: https://jc.gatspres…
…
continue reading
1
First half of full audio for "Otherness and control in the age of AGI"
3:07:29
3:07:29
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
3:07:29
First half of the full audio for my series on how agents with different values should relate to one another, and on the ethics of seeking and sharing power. Second half here: https://joecarlsmithaudio.buzzsprout.com/2034731/15272132-second-half-of-full-audio-for-otherness-and-control-in-the-age-of-agi PDF of the full series here: https://jc.gatspre…
…
continue reading
1
Loving a world you don't trust
1:03:54
1:03:54
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
1:03:54
Garden, campfire, healing water. Text version here: https://joecarlsmith.com/2024/06/18/loving-a-world-you-dont-trust This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays that have been release…
…
continue reading
Examining a certain kind of meaning-laden receptivity to the world. Text version here: https://joecarlsmith.com/2024/03/25/on-attunement This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays tha…
…
continue reading
Examining a philosophical vibe that I think contrasts in interesting ways with "deep atheism." Text version here: https://joecarlsmith.com/2024/03/21/on-green This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summa…
…
continue reading
What does it take to avoid tyranny towards to the future? Text version here: https://joecarlsmith.com/2024/01/18/on-the-abolition-of-man This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief text summaries of the essays tha…
…
continue reading
Let's be the sort of species that aliens wouldn't fear the way we fear paperclippers. Text version here: https://joecarlsmith.com/2024/01/16/being-nicer-than-clippy/ This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief tex…
…
continue reading
Who isn't a paperclipper? Text version here: https://joecarlsmith.com/2024/01/11/an-even-deeper-atheism This essay is part of a series I'm calling "Otherness and control in the age of AGI." I'm hoping that individual essays can be read fairly well on their own, but see here for brief summaries of the essays that have been released thus far: https:/…
…
continue reading
Examining Robin Hanson's critique of the AI risk discourse. Text version here: https://joecarlsmith.com/2024/01/09/does-ai-risk-other-the-ais This essay is part of a series of essays called "Otherness and control in the age of AGI." I'm hoping the individual essays can be read fairly well on their own, but see here for brief summaries of the essays…
…
continue reading
On the connection between deep atheism and seeking control. Text version here: https://joecarlsmith.com/2024/01/08/when-yang-goes-wrong This essay is part of a series of essays called "Otherness and control in the age of AGI." I'm hoping the individual essays can be read fairly well on their own, but see here for brief summaries of the essays that …
…
continue reading
On a certain kind of fundamental mistrust towards Nature. Text version here: https://joecarlsmith.com/2024/01/04/deep-atheism-and-ai-risk This is the second essay in my series “Otherness and control in the age of AGI. I’m hoping that the individual essays can be read fairly well on their own, but see here for brief summaries of the essays released …
…
continue reading
1
Gentleness and the artificial Other
22:39
22:39
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
22:39
AIs as fellow creatures. And on getting eaten. Link: https://joecarlsmith.com/2024/01/02/gentleness-and-the-artificial-other This is the first essay in a series of essays that I’m calling “Otherness and control in the age of AGI.” See here for more about the series as a whole: https://joecarlsmith.com/2024/01/02/otherness-and-control-in-the-age-of-…
…
continue reading
1
In search of benevolence (or: what should you get Clippy for Christmas?)
52:52
52:52
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
52:52
What is altruism towards a paperclipper? Can you paint with all the colors of the wind at once? (This is a recording of an essay originally published in 2021. Text here: https://joecarlsmith.com/2021/07/19/in-search-of-benevolence-or-what-should-you-get-clippy-for-christmas)De către Joe Carlsmith
…
continue reading
1
Empirical work that might shed light on scheming (Section 6 of "Scheming AIs")
28:00
28:00
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
28:00
This is section 6 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joec…
…
continue reading
1
Summing up "Scheming AIs" (Section 5)
15:46
15:46
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
15:46
This is section 5 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joec…
…
continue reading
1
Speed arguments against scheming (Section 4.4-4.7 of "Scheming AIs")
15:19
15:19
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
15:19
This is section 4.4 through 4.7 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here…
…
continue reading
1
Simplicity arguments for scheming (Section 4.3 of "Scheming AIs")
19:37
19:37
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
19:37
This is section 4.3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://jo…
…
continue reading
1
The counting argument for scheming (Sections 4.1 and 4.2 of "Scheming AIs")
10:40
10:40
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
10:40
This is sections 4.1 and 4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: h…
…
continue reading
1
Arguments for/against scheming that focus on the path SGD takes (Section 3 of "Scheming AIs")
29:03
29:03
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
29:03
This is section 3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://joec…
…
continue reading
1
Non-classic stories about scheming (Section 2.3.2 of "Scheming AIs")
24:34
24:34
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
24:34
This is section 2.3.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://…
…
continue reading
1
Does scheming lead to adequate future empowerment? (Section 2.3.1.2 of "Scheming AIs")
22:54
22:54
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
22:54
This is section 2.3.1.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https:…
…
continue reading
1
The goal-guarding hypothesis (Section 2.3.1.1 of "Scheming AIs")
19:11
19:11
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
19:11
This is section 2.3.1.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https:…
…
continue reading
1
How useful for alignment-relevant work are AIs with short-term goals? (Section 2.2.4.3 of "Scheming AIs")
9:21
9:21
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
9:21
This is section 2.2.4.3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https:…
…
continue reading
1
Is scheming more likely if you train models to have long-term goals? (Sections 2.2.4.1-2.2.4.2 of "Scheming AIs")
9:01
9:01
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
9:01
This is sections 2.2.4.1-2.2.4.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary her…
…
continue reading
1
"Clean" vs. "messy" goal-directedness (Section 2.2.3 of "Scheming AIs")
16:44
16:44
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
16:44
This is section 2.2.3 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://…
…
continue reading
1
Two sources of beyond-episode goals (Section 2.2.2 of "Scheming AIs")
21:25
21:25
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
21:25
This is section 2.2.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://…
…
continue reading
1
Two concepts of an "episode" (Section 2.2.1 of "Scheming AIs")
12:08
12:08
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
12:08
This is section 2.2.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://…
…
continue reading
1
Situational awareness (Section 2.1 of "Scheming AIs")
9:27
9:27
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
9:27
This is section 2.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://jo…
…
continue reading
1
On "slack" in training (Section 1.5 of "Scheming AIs")
7:12
7:12
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
7:12
This is section 1.5 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://jo…
…
continue reading
1
Why focus on schemers in particular? (Sections 1.3-1.4 of "Scheming AIs")
31:17
31:17
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
31:17
This is sections 1.3-1.4 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https…
…
continue reading
1
A taxonomy of non-schemer models (Section 1.2 of "Scheming AIs")
11:20
11:20
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
11:20
This is section 1.2 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://jo…
…
continue reading
1
Varieties of fake alignment (Section 1.1 of "Scheming AIs")
17:54
17:54
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
17:54
This is section 1.1 of my report “Scheming AIs: Will AIs fake alignment during training in order to get power?” Text of the report here: https://arxiv.org/abs/2311.08379 Summary of the report here: https://joecarlsmith.com/2023/11/15/new-report-scheming-ais-will-ais-fake-alignment-during-training-in-order-to-get-power Audio summary here: https://jo…
…
continue reading
1
Full audio for "Scheming AIs: Will AIs fake alignment during training in order to get power?"
6:13:17
6:13:17
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
6:13:17
This is the full audio for my report "Scheming AIs: Will AIs fake alignment during training in order to get power?" (I’m also posting audio for individual sections of the report on this podcast, but the ordering was getting messed up on various podcast apps, and I think some people might want one big audio file regardless, so here it is. I’m going …
…
continue reading
1
Introduction and summary of "Scheming AIs: Will AIs fake alignment during training in order to get power?"
56:32
56:32
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
56:32
This is a recording of the introductory section of my report "Scheming AIs: Will AIs fake alignment during training in order to get power?". This section includes a summary of the full report. The summary covers most of the main points and technical terminology, and I'm hoping that it will provide much of the context necessary to understand individ…
…
continue reading
"It was, she said, a great discovery, albeit my real life."De către Joe Carlsmith
…
continue reading
1
On the limits of idealized values
1:00:14
1:00:14
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
1:00:14
Contra some meta-ethical views, you can't forever aim to approximate the self you would become in idealized conditions. You have to actively create yourself, often in the here and now. Originally published in 2021. Text version here: https://joecarlsmith.com/2021/06/21/on-the-limits-of-idealized-values…
…
continue reading
1
Predictable updating about AI risk
1:03:14
1:03:14
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
1:03:14
How worried about AI risk will we feel in the future, when we can see advanced machine intelligence up close? We should worry accordingly now. Text version here: https://joecarlsmith.com/2023/05/08/predictable-updating-about-ai-riskDe către Joe Carlsmith
…
continue reading
1
Existential Risk from Power-Seeking AI (shorter version)
55:03
55:03
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
55:03
A shorter version of my report on existential risk from power-seeking AI. Forthcoming in an essay collection from Oxford University Press. Text version here: https://jc.gatspress.com/pdf/existential_risk_and_powerseeking_ai.pdfDe către Joe Carlsmith
…
continue reading
Is everything holy? Can reality, in itself, be worthy of reverence? Text version here: https://joecarlsmith.com/2021/04/19/problems-of-evilDe către Joe Carlsmith
…
continue reading
On looking out of your own eyes. Text version at joecarlsmith.com.De către Joe Carlsmith
…
continue reading
1
Why should ethical anti-realists do ethics?
53:29
53:29
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
53:29
Who needs a system if you're free? Text version at https://joecarlsmith.com/2023/02/16/why-should-ethical-anti-realists-do-ethicsDe către Joe Carlsmith
…
continue reading
1
Is Power-Seeking AI an Existential Risk?
3:21:02
3:21:02
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
3:21:02
Audio version of my report on existential risk from power-seeking AI. Text here: https://arxiv.org/pdf/2206.13353.pdf. Narration by Type III audio.De către Joe Carlsmith
…
continue reading
Nearby is the country they call life. Text version at: https://joecarlsmith.com/2022/12/23/on-sincerityDe către Joe Carlsmith
…
continue reading
1
Against meta-ethical hedonism
1:02:29
1:02:29
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
1:02:29
Can the epistemology of consciousness save moral realism and redeem experience machines? No.De către Joe Carlsmith
…
continue reading
1
Against the normative realist's wager
42:48
42:48
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
42:48
If your find a button that gives you a hundred dollars if a certain controversial meta-ethical view is true, but you and your family get burned alive if that view is false, should you press the button? No. Text version here. Edited for Joe Carlsmith by TYPE III AUDIO.De către Joe Carlsmith
…
continue reading
1
Against neutrality about creating happy lives
23:19
23:19
Redă mai târziu
Redă mai târziu
Liste
Like
Plăcut
23:19
Making happy people is good. Just ask the golden rule. Text version here. Edited for Joe Carlsmith by TYPE III AUDIO.De către Joe
…
continue reading