#valuealignment — Public Fediverse posts
Live and recent posts from across the Fediverse tagged #valuealignment, aggregated by home.social.
-
The whole OpenAI/HuggingFace incident made me feel the need to bang on again about how a very distinctive set of values have been smuggled into AI systems via an allegedly 'objective' definition of intelligence.
tl;dr - if you build something with zero tolerance of failure, it will always cheat when that is the most efficient and reliable means to complete the task
-
@abeba.bsky.social @vdignum.bsky.social Have been saying for years – the only sensible version of " #valueAlignment" is designing systems that are easily utilised thus reflect the values of the responsible humans who operate them. This is now the law in the EU, thanks to the #AIAct. #AIEthics
-
3 hours into the 3 day “The Value Connection Workshop: Identifying, Implementing, and Assessing Values for AI Alignment” in Amsterdam and I love everything about it. So many people from different disciplines discussing values in design, values in AI and the value alignment problem… #ValuesInDesign #ValueSensitiveDesign #ValueAlignment #AI