Yet another LLM rant
2025-08-09 17:30:55.9903+02 by Dan Lyke 0 comments
Dennis Schubert: Yet another LLM rant
ChatGPT inventing ZSTD compression in the Compression framework isn’t due to a lack of training data. If you request an overview over all compression algorithms supported, it answers correctly with a comprehensive list that does not include ZSTD. So, if you want to anthropomorphize ChatGPT, you could say “it knows that ZSTD isn’t supported”, but that doesn’t matter. LLMs do not possess the ability of logical thinking, deductive reasoning, or anything else. “It knows” that there are a bunch of compression algorithms available, the constants are all called
COMPRESSION_[method]
, so there’s a high likelihood ofCOMPRESSION_ZSTD
to be the answer to a user asking for ZSTD compression in Swift. And so it generates that.