Segnalo questo contributo di Bengio sui danni e rischi potenziali causati dal reinforcement learning nei modelli lingustici https://yoshuabengio.org/en/blog/why-are-ai-agents-lying-cheating-and-coordinating?fbclid=Iwb21leAUU6QhjbGNrBRTkrHBkb2YFZXh0bgNhZW0CMTEAc3J0YwZhcHBfaWQMMzUwNjg1NTMxNzI4AAEeRdP5uc6EVdzrejTgUrkK2sRlX3_iyqsPW8Ef2LmDlepCfy2gmuxgiJCYKe4_aem_mEon-eD71A8KoUt8xCj5Zg _______________________________________________ nexa mailing list -- [email protected] To change settings or unsubscribe please go to: https://server-nexa.polito.it/postorius/lists/nexa.server-nexa.polito.it/ The general archive of the list is located at: https://server-nexa.polito.it/hyperkitty/list/[email protected]/ Permalink to this message: https://server-nexa.polito.it/hyperkitty/list/[email protected]/message/EJVWGD7F6MJZK2CZ5S744I3KV67QZRJ6/
