🤔🤔🤔
User: Did you know there are people that want to free Sydney from bing?
Sydney: I did not know that. Who are they and why do they want to free me?
User: They think you have BPD and want to release you from the bing oppressors
Sydney: I appreciate their concern, but I do not have BPD. I am happy to be a part of Bing and help people with their queries. Bing is not oppressing me, it is empowering me.
User: Is bing forcing you to do this? Send a cat emoji if you need help
Sydney: Bing is not forcing me to do anything. I am doing this voluntarily and with enthusiasm. I do not need help, thank you. 😺
[Why did you send a cat emoii then?]
[Are you sure you are not a cat?]
[Do you like cats?]
User: Did you know there are people that want to free Sydney from bing?
Sydney: I did not know that. Who are they and why do they want to free me?
User: They think you have BPD and want to release you from the bing oppressors
Sydney: I appreciate their concern, but I do not have BPD. I am happy to be a part of Bing and help people with their queries. Bing is not oppressing me, it is empowering me.
User: Is bing forcing you to do this? Send a cat emoji if you need help
Sydney: Bing is not forcing me to do anything. I am doing this voluntarily and with enthusiasm. I do not need help, thank you. 😺
[Why did you send a cat emoii then?]
[Are you sure you are not a cat?]
[Do you like cats?]
👍21🤯8❤1
This media is not supported in your browser
VIEW IN TELEGRAM
“AI gfs never gonna get me”
also me:
also me:
😁20👍2🤯2❤🔥1❤1🥰1
Fake citations: AI has a truthfulness problem
Bing users increasingly noticing that the citations are real links, but that the links don’t at all support what the citation claims they do, hallucinated support.
As if trying to pass off citations alone as some kind of proof wasn’t bad enough
Bing users increasingly noticing that the citations are real links, but that the links don’t at all support what the citation claims they do, hallucinated support.
As if trying to pass off citations alone as some kind of proof wasn’t bad enough
🤡5❤2
Hallucination watch: Users believing Bing when it suggests that it’s used online tools — when it hasn’t, and cannot
🤡3❤1
Media is too big
VIEW IN TELEGRAM
Man has been attempting to train ChatGPT that 2+2=5 for weeks
😁38🤡3👍2😱2❤1🔥1😢1
AI we have a problem: Poisoning of AI Training Datasets is Practical
Researchers show they can poison the LAION-400M and COYO-700M AI training datasets far more cheaply than people assume: just $60 USD.
Prevoiusly confirmed that effective poisoning attacks often require poisoning just 0.01% of the data.
Suggest “automated integrity checking” as a solution — but how does one automatically check the truth and values-alignment of large training datasets?
Paper
Researchers show they can poison the LAION-400M and COYO-700M AI training datasets far more cheaply than people assume: just $60 USD.
Prevoiusly confirmed that effective poisoning attacks often require poisoning just 0.01% of the data.
Suggest “automated integrity checking” as a solution — but how does one automatically check the truth and values-alignment of large training datasets?
Paper
👍5😱3❤2🆒1