Anomalous Tokens: a mysterious failure mode for GPT (lesswrong.com) 11 points by mquander 3y ago ↗ HN
[–] ttctciyf 3y ago ↗ This is fascinating!It would be a neat party trick to be able to elicit some of these non-sequitur responses from ChatGPT, but I guess there's no way to access the anomalous tokens in that particular case, short of hands-on access to the implementation? [–] Smaug123 3y ago ↗ ChatGPT displays many of the exact same failures! (But presumably deriving them without already knowing them would require access to the model, yes.)
[–] Smaug123 3y ago ↗ ChatGPT displays many of the exact same failures! (But presumably deriving them without already knowing them would require access to the model, yes.)
2 comments
[ 3.7 ms ] story [ 15.5 ms ] threadIt would be a neat party trick to be able to elicit some of these non-sequitur responses from ChatGPT, but I guess there's no way to access the anomalous tokens in that particular case, short of hands-on access to the implementation?