Hacker News new | past | comments | ask | show | jobs | submit login

For me that's the biggest takeaway.. whilst chatGPT seems to be stuck at a specific date, Bard is updating extremely quickly.

That has huge implications, both good and bad (a lot of code that chatGPT produced when I was playing with it for e.g. sveltekit is outdated)




I wonder if it's actually being updated quickly. I think it'd be much easier to train it to use google's search index as a tool in a way hidden from the user. For example regarding the shutdown date of itself it might have googled "google bard shutdown" to find and misunderstand the HN comment cited in the twitter thread.


Seems like it would be trivial to replace "As an AI language model who hasn't been updated since x date" with "$ESCAPE_SEQUENCE search_query: $TERM" and rerun the question with the hidden prefix "Given that the google results for $TERM are $RESULTS"...


So it will spew the latest lies that have been posted online then I guess, if it's using internet comment forums as sources?


Just like humans. Singularity is knocking.


dang.


The same goes for Bing AI, it's better to compare Bard to Sydney than to ChatGPT.




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: