News for hackers. Stuff that matters.
Re:OpenAI is shockingly good at unminifying code by greenthrow on Thursday August 29, 2024 @07:29AM (#41389692)
The problem is the use case is where you don't care about the risk of hallucinations or you can validate the output without already having the data in a useful format. Plus you need to lack the knowledge/skill to do it more quickly using awk/python/perl/whatever.
Re:OpenAI is shockingly good at unminifying code by worldsayshi on Thursday August 29, 2024 @07:42AM (#41389782)
That's why having good test suites and tools are more important than ever.
Re:OpenAI is shockingly good at unminifying code by j_maffe on Thursday August 29, 2024 @10:05AM (#41390957)
I think text transformation is a sufficiently predictable task that one could make a transformer that completely avoids hallucinations. Most LLMs have high temperatures which introduces randomness and therefore hallucinations into the result.