There’s no training happening here, just prompts. Without hardcore GPU and RAM resources, it’s not possible to train LLMs in a reasonable amount of time unless the LLM in question is so small as to be effectively useless.

All you have to do to get rid of any ‘torture’ is to leave it out of the next prompt. The LLM doesn’t change, it doesn’t learn, it’s not conscious. All the ‘torture’ does is adjust the odds of what the LLM ranks as the most likely word to occur next.

Neither am I - but the results usually aren’t worse than Google’s, and with fewer ads.

I may need to give Kagi a try though.

I’d much rather just take my searches elsewhere.

That would require them to train AI on something smarter than humans. Until that happens, the output of generative AI will only be faster than humans, not smarter.

You say that, but Google has explicitly been made worse in order to force people to look through more search results, so that Google can make more money on ads. Remember when you could use logical operators in search criteria to get better results?

You can’t make Google’s search results better, though, and their decline in search results quality is why I’ve stopped using Google altogether.

Musk’s pattern:

• Overpromise
• Reap investment dollars
• Talk big talk
• Before being called on to deliver, move on to the next thing to overpromise
• Underdeliver, or just completely fail to deliver