Google released their first public model to compete with ChatGPT and the results are . . . underwhelming, but the implications are anything but. The stakes are extraordinary and far-reaching (no, I’m not talking about thinking machines!) If Google, Microsoft, and Amazon cannot align their generative AI models with existing productivity tools aka ‘talking to your data,’ then we may have front-row seats to one of the largest tech meltdowns since the dot com bubble twenty-five years ago. That doesn’t just have implications for tech companies—the ripple effect from the fallout could cause massive disruption to the economy.
Claude is probably the best at this point, but based on the recent paper that Anthropic released, you need to carefully construct your prompts with clear instructions, even giving it directed pathways to what you feel are your most relevant quotes.
Hey, Marc,
Let's say I am using a LLM to find good quotes to insert to an existing draft I am writing.
What would be your suggested pathway for the best results?
Asking for a friend!
Claude is probably the best at this point, but based on the recent paper that Anthropic released, you need to carefully construct your prompts with clear instructions, even giving it directed pathways to what you feel are your most relevant quotes.
Yes, that seems to be the rule with everything LLM related.
This is a really great summary, thanks for diving into this.