LESSWRONG
LW

Ramana Kumar
1482Ω50681990
Message
Dialogue
Subscribe

Posts

Sorted by New

Wikitag Contributions

Comments

Sorted by
Newest
No wikitag contributions to display.
(The) Lightcone is nothing without its people: LW + Lighthaven's big fundraiser
Ramana Kumar6mo51

Let me know when you can receive donations via a UK charity.

Reply
Is there any rigorous work on using anthropic uncertainty to prevent situational awareness / deception?
Answer by Ramana KumarSep 26, 2024Ω120

Vaguely related perhaps is the work on Decoupled Approval: https://arxiv.org/abs/2011.08827

Reply
Consent across power differentials
Ramana Kumar1yΩ120

Thanks for this! I think the categories of morality is a useful framework. I am very wary of the judgement that care-morality is appropriate for less capable subjects - basically because of paternalism.

Reply
Consent across power differentials
Ramana Kumar1yΩ230

Just to confirm that this is a great example and wasn't deliberately left out.

Reply
Without specific countermeasures, the easiest path to transformative AI likely leads to AI takeover
Ramana Kumar1yΩ8104Review for 2022 Review

I found this post to be a clear and reasonable-sounding articulation of one of the main arguments for there being catastrophic risk from AI development. It helped me with my own thinking to an extent. I think it has a lot of shareability value.

Reply
Systems that cannot be unsafe cannot be safe
Ramana Kumar2yΩ360

I agree with this post. However, I think it's common amongst ML enthusiasts to eschew specification and defer to statistics on everything. (Or datapoints trying to capture an "I know it when I see it" "specification".)

Reply
Why do we care about agency for alignment?
Answer by Ramana KumarApr 23, 2023Ω460

This is one of the answers: https://www.alignmentforum.org/posts/FWvzwCDRgcjb9sigb/why-agent-foundations-an-overly-abstract-explanation

Reply
Teleosemantics!
Ramana Kumar2yΩ120

The trick is that for some of the optimisations, a mind is not necessary. There is a sense perhaps in which the whole history of the universe (or life on earth, or evolution, or whatever is appropriate) will become implicated for some questions, though.

Reply
AI and Evolution
Ramana Kumar2yΩ352

I think https://www.alignmentforum.org/posts/TATWqHvxKEpL34yKz/intelligence-or-evolution is somewhat related in case you haven't seen it.

Reply
Load More
39Dialogue on What It Means For Something to Have A Function/Purpose
Ω
1y
Ω
5
50Consent across power differentials
Ω
1y
Ω
12
39Refining the Sharp Left Turn threat model, part 2: applying alignment techniques
Ω
3y
Ω
9
78Threat Model Literature Review
Ω
3y
Ω
4
127Clarifying AI X-risk
Ω
3y
Ω
24
61Autonomy as taking responsibility for reference maintenance
Ω
3y
Ω
3
86Refining the Sharp Left Turn threat model, part 1: claims and mechanisms
Ω
3y
Ω
4
133Will Capabilities Generalise More?
Ω
3y
Ω
39
21ELK contest submission: route understanding through the human ontology
Ω
3y
Ω
2
38P₂B: Plan to P₂B Better
Ω
4y
Ω
17
Load More