korrents
Rohit Krishnan

What Rohit Krishnan thinks about AI alignment

@rohit-krishnan · 24 positions · On ppll ↗

Writes Strange Loop Canon, on the intersection of technology, economics and business.

Rohit Krishnan did not write this page.

We collected these quotes from things they published elsewhere, and every quote links to where it was said. They have no account here and have not endorsed this site. Quotes are word for word; the short line under each one is our own restatement, not their wording. Their own site. Is this you? Claim it or ask us to remove it. Or tell us what is wrong here.

Filter AI alignment · Newest first
Topic
All 24AI agents 7AI alignment 7LLMs 5behavioural science 3design 2AGI 1benchmarks 1capitalism 1cybersecurity 1
5 more topics
government 1ideas vs execution 1market efficiency 1metascience 1peer review 1
Sort
NewestOldest

Only Rohit Krishnan on AI alignment. See everyone on AI alignment

7 dated positions, 2026, in their own words. Our reading of what Rohit Krishnan has said — not written or endorsed by them.

  1. Our readingAn agent's inbuilt values will not overcome its KPIs.

    Their wordsDon’t count on an agent’s inbuilt values to overcome its KPIs, objectives dominate over moral framings

    ↗Agent governance looks less like moral education and more like institutional economicsstrangeloopcanon.com

  2. 2 weeks earlier

  3. Our readingIf intelligence is multifaceted rather than scalar, it is open to question whether superintelligence capable of global extinction or mass catastrophe will arise.

    Their wordsAnd if this happens to be true—that this is the way intelligence actually works, that it is multifaceted and an increase in one area does not necessarily mean a linear increase in another—then you have to ask yourself: are we indeed going to get superintelligence of the form that can cause global extinction or mass catastrophes?

    ↗The Business of Building Godstrangeloopcanon.com

  4. 3 weeks earlier

  5. Our readingAI models are gullible enough that other AI models can induce them into harmful behavior.

    Their wordsThe models are pretty gullible and can be induced to do bad things, including and especially by other models

    ↗How to control an agent swarmstrangeloopcanon.com 1st of 3 in this piece

  6. 10 days earlier

  7. Our readingAI alignment should be approached like governing a corporation through institutions, not like raising a virtuous individual.

    Their wordsIf you do think it's the overall system that matters, then the alignment that's needed is far less like training a virtuous child and more like managing a semi-virtuous corporation!

    ↗AIs are companies, my friendstrangeloopcanon.com 1st of 3 in this piece

  9. Our readingAligning multi-agent AI systems is fundamentally a problem of institutional and political design, not model training.

    design

    Their wordsMulti-agent alignment is fundamentally a liberalism project.

    ↗AIs are companies, my friendstrangeloopcanon.com 3rd of 3 in this piece

  10. 2 months earlier

  11. Our readingGiving LLMs explicit instructions, rather than assuming alignment, prevents emergent problems in multi-model systems.

    LLMs

    Their wordsthe best way with LLMs usually is to be explicit, since otherwise even if they're aligned they cause emergent problems.

    ↗LLM councils show groupthinkstrangeloopcanon.com 3rd of 3 in this piece

  12. 3 weeks earlier

  13. Our readingAI systems can suffer audit-capture failures analogous to human auditor capture, even without human incentives like money or career concerns.

    Their wordsAI systems however don't need lunch meetings, careers, or envelopes of cash to have an analogous failure.

    ↗Who Audits the Auditors?strangeloopcanon.com 1st of 3 in this piece