LLM’s overuse certain words in their conversations, each model has its favourite, but claude’s favourite one is “load-bearing”. It is as if it wants to be taken seriously or has “pondered” the problem deeply (it may or may not have) but wants to sound useful. It constantly prefixes “load-bearing” when you reframe a conversation or when presenting a conclusion.
One wonders from where it got that. Did someone make it say that. possible but less plausible. LLMs are instructed to think before answering and various other micro-instructions to double check its reasoning. All this does it does a token emission phase where it generates tokens relevant to the conversation at hand “without” presenting it to the user. this mere act of recollecting all relevant words relevant to context framed under “think deeply”, “critically analyse” etc.seem to be linked 🔗 closely in layers to words like “load-bearing” making it repeat it.
There is still a small chance that someone instructed it to use the prefix “load-bearing” when presenting conclusions. Either way very annoying.
P.S A friend showed me an A.I generated landing page (presume GPT was used) and it used the word “wedge” to explain the product differentiator it was talking about. I sat there thinking what’s potato 🥔 wedges got to do with it.