News Claude takes the top spot in AI chatbot ranking — finally knocking GPT-4 down to second place

[admin]

Claude 3 has become the most-liked chatbot in a global AI arena where people blind rate two models in a head-to-head battle.

Claude takes the top spot in AI chatbot ranking — finally knocking GPT-4 down to second place : Read more

 

[parkerthon]

This is precisely why I have found the hysteria and hype about OpenAI specifically to be humorous. Having used multiple LLMs now, OpenAI's ChatGPT tends to receive far too much publicity when it's far from superior. Obsessing about Sam Altman's utterances, Microsoft's ownership, etc is WAY too premature. Any talk about a monopoly or undue influence is assuming the race is already over when it has just begun. Meanwhile we should be laying very basic guardrails on the track already. We should be having a discussion about AI in general and especially the more immediate dangers(e.g. where the line exists on using publicly shared content, how do we identify AI created content, what limits do we impose on AI systems control over other systems, etc). We don't even need to make it law, just make it policies or standards that could become law if people don't abide by them.

 

[darylclose]

Claude 3 has become the most-liked chatbot in a global AI arena where people blind rate two models in a head-to-head battle.

Claude takes the top spot in AI chatbot ranking — finally knocking GPT-4 down to second place : Read more

I asked Claude a very simple question that Bing Copilot--a GPT-4 program--answered correctly and easily: List 3 Middle Eastern markets near [my ZIP code] within 100 miles. Claude was stumped; no business info in the training model.

I then asked Claude, Who is best associated with the statement "Justice is the advantage of the stronger"? Both Claude and Copilot provided correct answers, but Claude's was longer and more detailed. Copilot's answer was shorter, but provided citations and hyperlinks to further reading while Claude provided neither.

My third test question was, State three leading hypotheses about the authorship of Shakespeare's plays and estimate the probability of correctness. Both Claude and Copilot provided correct answers of approximately the same length and detail. Claude assigned numerical probabilities to the three leading hypotheses, while Copilot used qualitative terms, very high and low.

This is obviously an inadequately sized sample, but I'd rate Copilot over Claude simply because of Claude's inferior training base. Tip: if you're seeking product information, shopping, etc., use Copilot. Claude's not there yet.