| > What does frequency bias have to do with the objective fact that hundreds of people reported This isn't hard to understand "Model is nerfed" claim hits social media Someone else sees it, frequency bias makes them think their model is also nerfed, and they amplify the claim Now it spreads, like a virus, even if the model never changed Social dynamics like this are well understood psychologically > If the LLM used to be able to achieve set goals and no longer could, it is already a sign of the distribution shift. The more likely explanation is that you're looking at older LLMs with rose tinted glasses, and misremembering what it could achieve Otherwise you could measure the token shift and see the better tps and latency Your own evals would trend down But no one, not one person, has presented empirical evidence of being served a quant. Just vibes. |
Did you really just claim that people are so gullible that it was social media or whatever that made them believe their LLM could no longer achieve the tasks it yesterday could, and not the actual FACT of LLM not being able to do it that they, you know, verified before complaining online? I guess if you gaslight everything like that, then indeed no matter what the facts are, you will never be convinced in anything.
You see, because of outlandish claims and reasoning (or rather lack of) like that, everyone sees that you are an Anthropic shill.