Algon

Karma: 2,283

What is scaffolding?

Vishakha and Algon

Mar 27, 2025, 9:06 AM

10 points

0 comments2 min readLW link

(aisafety.info)

What is an alignment tax?

Vishakha and Algon

Mar 20, 2025, 1:06 PM

5 points

0 comments1 min readLW link

(aisafety.info)

Are corporations superintelligent?

Vishakha and Algon

Mar 17, 2025, 10:36 AM

3 points

3 comments1 min readLW link

(aisafety.info)

What is instrumental convergence?

Vishakha and Algon

Mar 12, 2025, 8:28 PM

2 points

0 comments2 min readLW link

(aisafety.info)

What are the “no free lunch” theorems?

Vishakha and Algon

Feb 4, 2025, 2:02 AM

19 points

4 comments1 min readLW link

(aisafety.info)

What are the differences between AGI, transformative AI, and superintelligence?

Vishakha and Algon

Jan 23, 2025, 10:03 AM

10 points

3 comments3 min readLW link

(aisafety.info)

How do fictional stories illustrate AI misalignment?

Vishakha and Algon

Jan 15, 2025, 6:11 AM

13 points

4 comments2 min readLW link

(aisafety.info)

What are polysemantic neurons?

Vishakha and Algon

Jan 8, 2025, 7:35 AM

8 points

0 comments4 min readLW link

(aisafety.info)

When do experts think human-level AI will be created?

Vishakha and Algon

Dec 30, 2024, 6:20 AM

10 points

0 comments2 min readLW link

(aisafety.info)

What is compute governance?

Vishakha and Algon

Dec 23, 2024, 6:32 AM

6 points

0 comments2 min readLW link

(aisafety.info)

What is “wireheading”?

Vishakha and Algon

Dec 17, 2024, 7:49 AM

10 points

0 comments1 min readLW link

(aisafety.info)

AISafety.info: What is the “natural abstractions hypothesis”?

AlgonOct 5, 2024, 12:31 PM

38 points

2 comments3 min readLW link

(aisafety.info)

AISafety.info: What are Inductive Biases?

AlgonSep 19, 2024, 5:26 PM

11 points

4 comments2 min readLW link

(aisafety.info)

 Managing AI Risks in an Era of Rapid Progress

AlgonOct 28, 2023, 3:48 PM

36 points

5 comments11 min readLW link

(managing-ai-risks.com)

[Question] What is your financial portfolio?

AlgonJun 28, 2023, 6:39 PM

11 points

11 comments1 min readLW link

Sama Says the Age of Giant AI Models is Already Over

AlgonApr 17, 2023, 6:36 PM

49 points

12 comments1 min readLW link

(www.wired.com)

A Particular Equilibrium

AlgonFeb 8, 2023, 3:16 PM

13 points

0 comments2 min readLW link

(algon-33.github.io)

Idea: Learning How To Move Towards The Metagame

AlgonJan 10, 2023, 12:58 AM

10 points

3 comments1 min readLW link

What Does It Mean to Align AI With Human Values?

AlgonDec 13, 2022, 4:56 PM

8 points

3 comments1 min readLW link

(www.quantamagazine.org)

Algon’s Shortform

AlgonOct 10, 2022, 8:12 PM

5 points

27 comments1 min readLW link