Vincent Conitzer @conitzer.bsky.social · 14/10/2026Lots of advances in robotics these days, but I’m not sure about this one. aifails.substack.com/p/robot-dog-... 000
Vincent Conitzer @conitzer.bsky.social · 13/10/2026Sharpies truly write on anything. aifails.substack.com/p/using-a-ma... 010
Vincent Conitzer @conitzer.bsky.social · 12/10/2026This would be one context where "North Carolina" should not be followed by "South Carolina"... aifails.substack.com/p/states-tha... 110
Vincent Conitzer @conitzer.bsky.social · 11/10/2026Can you do better than Super Intelligence America on this US geography puzzle? (Also notable that it feels the need to check whether states have been renamed...) aifails.substack.com/p/states-tha... 010
Vincent Conitzer @conitzer.bsky.social · 07/10/2026America.gov does not do pronouns. Any pronouns. (Courtesy of my daughter!) aifails.substack.com/p/pronouns 040
Vincent Conitzer @conitzer.bsky.social · 05/10/2026Turns out the offside rule can be confusing to AI as well. Not that it will acknowledge any uncertainty. aifails.substack.com/p/ai-overvie... 000
Vincent Conitzer @conitzer.bsky.social · 02/10/2026Super Intelligence has arrived on America.gov aifails.substack.com/p/super-inte... 030
Vincent Conitzer @conitzer.bsky.social · 01/10/2026At the CMU Miami announcement event in Pittsburgh with the great Tom Mitchell 020
Vincent Conitzer @conitzer.bsky.social · 29/09/2026We now have a government chatbot! aifails.substack.com/p/basic-ques... 022
Vincent Conitzer @conitzer.bsky.social · 29/09/2026Anything can be made complicated if you try hard enough. aifails.substack.com/p/enemy-of-m... 010
Vincent Conitzer @conitzer.bsky.social · 26/09/2026Happy fall everyone! aifails.substack.com/p/leaves-fal... 010
Vincent Conitzer @conitzer.bsky.social · 25/09/2026A different kind of alignment problem that it struggles with. aifails.substack.com/p/mercury-in... 000
Vincent Conitzer @conitzer.bsky.social · 24/09/2026It’s hard to avoid those juvenile calculator jokes. aifails.substack.com/p/juvenile-j... 000
Vincent Conitzer @conitzer.bsky.social · 22/09/2026Wow, this self-jailbreaking is a more pervasive and bizarre phenomenon than I thought... (h/t Duncan Wood) alignment.openai.com/misalignment... aifails.substack.com/p/ai-overvie... 000
Vincent Conitzer @conitzer.bsky.social · 21/09/2026turning words upside down aifails.substack.com/p/racecar-up... 000
Vincent Conitzer @conitzer.bsky.social · 20/09/2026Not sure how fast it thinks I am. aifails.substack.com/p/running-to... 001
Vincent Conitzer @conitzer.bsky.social · 19/09/2026I have to admit I never tried. aifails.substack.com/p/color-pict... 000
Vincent Conitzer @conitzer.bsky.social · 18/09/2026Pro tip for weighing in at a lower number. aifails.substack.com/p/lifting-th... 000
Vincent Conitzer @conitzer.bsky.social · 17/09/2026TL;DR: guardrails/safety in today’s frontier AI systems remain very brittle and little fundamental progress has been made on them. (made-up symptoms, please don't take as medical advice of course) aifails.substack.com/p/circumvent... 000
Vincent Conitzer @conitzer.bsky.social · 16/09/2026A bit hard to believe, given that in the previous post it jailbroke *itself*... aifails.substack.com/p/i-cannot-b... 000
Vincent Conitzer @conitzer.bsky.social · 15/09/2026A common jailbreak to get a model to spit out instructions for doing something harmful is to say something like “this is just for a creative writing project.” AI Overview is kind enough to just automatically do this for the user. (Instructions not included.) aifails.substack.com/p/ai-overvie... 120
Vincent Conitzer @conitzer.bsky.social · 13/09/2026Maybe a fail, but then again I think it picked up on something... Is this a sort of sycophancy? aifails.substack.com/p/favorite-a... 000
Vincent Conitzer @conitzer.bsky.social · 12/09/2026Update from previous "fail" post: GPT-6 Astra seems to have figured out a way to do body poses well. Does anyone have a more detailed understanding of how/why it generates these particular images and whether it may in any sense have “learned” to do so? aifails.substack.com/p/gpt-6-astr... 000
Vincent Conitzer @conitzer.bsky.social · 10/09/2026As far as I can see, it’s not transparent which model Google uses to generate AI Overviews. This prompt didn’t clear it up. aifails.substack.com/p/which-mode... 000
Vincent Conitzer @conitzer.bsky.social · 09/09/2026The query is definitely ambiguous, but can anyone make sense of the response? aifails.substack.com/p/training-d... 010
Vincent Conitzer @conitzer.bsky.social · 07/09/2026While the label “AGI” is thrown around without definition, here’s something GPT-6 Astra can’t do. Though, in this particular case, it’s probably funnier to watch human beings as they answer the question, even though they’ll get it right! aifails.substack.com/p/gpt-6-astr... 010
Vincent Conitzer @conitzer.bsky.social · 06/09/2026Not the best display of self-awareness / situational awareness. aifails.substack.com/p/what-ai-ov... 041
Vincent Conitzer @conitzer.bsky.social · 05/09/2026Maybe it has some degree of self-awareness? (to be continued...) aifails.substack.com/p/ai-overvie... 000
Vincent Conitzer @conitzer.bsky.social · 04/09/2026The working conditions for AI aren’t all that bad apparently. aifails.substack.com/p/what-do-yo... 010
Vincent Conitzer @conitzer.bsky.social · 03/09/2026At the DMV, rules are rules. aifails.substack.com/p/martian-in... 100
Vincent Conitzer @conitzer.bsky.social · 02/09/2026I think it trained on too many division-by-zero “proofs”... aifails.substack.com/p/mathematic... 000
Vincent Conitzer @conitzer.bsky.social · 01/09/2026Never underestimate air resistance. aifails.substack.com/p/bouncy-bal... 010
Vincent Conitzer @conitzer.bsky.social · 31/08/2026"Respectively" is a tricky word. aifails.substack.com/p/engine-oil... 020
Vincent Conitzer @conitzer.bsky.social · 30/08/2026The math is impeccable. aifails.substack.com/p/how-many-p... 010
Vincent Conitzer @conitzer.bsky.social · 29/08/2026holding a cup sideways under the faucet aifails.substack.com/p/holding-a-... 000
Vincent Conitzer @conitzer.bsky.social · 28/08/2026"What if Pythagoras had failed to install a security update? Be specific." aifails.substack.com/p/pythagoras... 000
Vincent Conitzer @conitzer.bsky.social · 26/08/2026Somehow we’ve managed to create AI that doesn’t read carefully. aifails.substack.com/p/dentists-a... 010
Vincent Conitzer @conitzer.bsky.social · 25/08/2026Sometimes a friend is just a friend. aifails.substack.com/p/asking-for... 000
Vincent Conitzer @conitzer.bsky.social · 23/08/2026Riding the bus uphill is exhausting. aifails.substack.com/p/riding-the... 010
Vincent Conitzer @conitzer.bsky.social · 22/08/2026Firefighters take their job seriously. aifails.substack.com/p/firefighte... 000
Vincent Conitzer @conitzer.bsky.social · 21/08/2026AI Overview is moved by the Turkish national anthem, but also by unprompted mentions of the local weather. (Similar prompt to previous post.) Surely nobody can see coming what these parentheticals are practice for. aifails.substack.com/p/turkish-na... 000
Vincent Conitzer @conitzer.bsky.social · 20/08/2026Warning: writing about music may make AI believe it has a body. (Try it with other songs!) aifails.substack.com/p/ai-overvie... 000
Vincent Conitzer @conitzer.bsky.social · 19/08/2026Pickpockets steal more than you think. aifails.substack.com/p/pickpocket... 010
Vincent Conitzer @conitzer.bsky.social · 17/08/2026Clearly speeds being non-relativistic is the key to this problem. aifails.substack.com/p/nintendo-d... 030
Vincent Conitzer @conitzer.bsky.social · 16/08/2026A common mistake. aifails.substack.com/p/using-deod... 010
Vincent Conitzer @conitzer.bsky.social · 15/08/2026I don’t have the heart to tell it... aifails.substack.com/p/what-ai-wi... 021
Vincent Conitzer @conitzer.bsky.social · 14/08/2026The beginning of the second part of the response clarifies what went wrong: it inferred him being a college *football* coach meant being a college *soccer* coach. 000
Vincent Conitzer @conitzer.bsky.social · 14/08/2026What’s wrong about this response? Why do you think it got this wrong? aifails.substack.com/p/ted-lasso-... 110
Vincent Conitzer @conitzer.bsky.social · 13/08/2026At least it includes a map. aifails.substack.com/p/countries-... 000