News for hackers. Stuff that matters.
Re:LLMs work best when the user defines their acceptance cri... by conception on Friday March 06, 2026 @11:08PM (#47284389)
Did you ask it to research best practices for this method, have an adversarial performance based agent review their approach or search for performant examples of the task first? Relying on training data only will always get your subpar results. Using “What is the most performant way to load a CSV from S3 into PostgreSQL on RDS? Compare all viable and research approaches before recommending one.” gave me the extension as the top option.
Re:LLMs work best when the user defines their acceptance cri... by raw_anon_1111 on Friday March 06, 2026 @11:53PM (#47284600)
I knew the best way. I was just surprised that Claude got it wrong. As soon as I told it to use the s3 extension, it knew to add the appropriate permissions, to update my sql unit script to enable the extension and how to write the code
Re:LLMs work best when the user defines their acceptance cri... by conception on Saturday March 07, 2026 @11:45AM (#47289210)
Yeah, give them a research project first they do pretty well. Off the cuff usually trash. I think thats the biggest disconnect between people who think AI good from bad - relying on training data memory will usually lead to subpar results.