korrents
Armin Ronacher

What Armin Ronacher thinks about AI alignment

@armin-ronacher · 30 positions · 1 change of mind · On ppll ↗

Creator of Flask and Jinja. Writes about software at lucumr.pocoo.org.

Armin Ronacher 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 30LLMs 6AI agents 5AI alignment 3coding agents 3chat interfaces 2developer tools 2Europe 2optimism 2AGI 1
20 more topics
AI writing 1America 1Anthropic 1China 1documentation 1infrastructure 1JavaScript 1market efficiency 1Microsoft 1neural networks 1Nix 1Omarchy 1open source 1permitting 1pruning 1scaling laws 1self-driving cars 1software quality 1taste 1war 1
Sort
NewestOldest

Only Armin Ronacher on AI alignment. See everyone on AI alignment

3 dated positions, 2023 to 2026, in their own words. Our reading of what Armin Ronacher has said — not written or endorsed by them.

3 positions so far — this page is not yet offered to search engines.

  1. Our readingMaking an agent somewhat durable is not very hard, but making an agent harness inherently durable without it becoming a mess is surprisingly hard.

    Their wordsIt’s not very hard to make an agent somewhat durable. It’s surprisingly hard to make an agent harness inherently durable and not turn into a crazy mess.

    ↗@mitsuhiko on Xx.com

  2. 3 weeks earlier

  3. Our readingAI is probably not going to cause an extinction event, and even without any slowdown humanity likely would not have much to worry about.

    Their wordsI don’t think AI is going to usher in an extinction event. In fact, even if nobody were to slow down, I really don’t think humanity would have much to worry about.

    ↗P(doom)lucumr.pocoo.org

  4. 4 years earlier

  5. Our readingWe do not control neural networks well enough to guarantee an AI will not harm humans, so we should be careful about what capabilities we give them.

    neural networks

    Their wordsThe biggest issue is probably that we don’t control neutral networks enough to be able to ensure AI doesn’t harm humans. We can’t even control AI to not reveal internal prompts.

    ↗I Think AI Would Kill my Wifelucumr.pocoo.org