Kaustubh Sule
@kaustubh
Investment Manager, Amateur writer, fitness enthusiast
Kaustubh Sule
@kaustubh
Investment Manager, Amateur writer, fitness enthusiast
What generalists are
Generalists are usually curious people who like to hop around from domain to domain. They enjoy figuring things out, especially in areas that are uncertain or new. They’re good at solving problems that domain experts struggle with, because they’re able to bring bits of knowledge from diverse fields together.
As Nat notes, because
... See more.modelthinking
He reframes what it means to be a generalist—not just someone with shallow knowledge across multiple domains, but a curious, adaptable problem-solver who thrives in environments where rules are unclear and patterns aren't obvious. In an allocation economy, the winners won't be those who know all the answers, but those who know which questions to as
... See more.modelthinking
#4—Prompting is a finicky art, but a worthy investment While it would be great if the three techniques I’ve shared so far immediately transform your prompts, there's a decent chance they will fall flat for your use case. My guess is that they will even become irrelevant as models become smarter and more cost-effective over time. My point in sharing
... See more#3—Be methodical about the examples you provide The staple of any few-shot prompt is its examples. I had strict screening criteria for the examples that were added to my contrarian, punchy, tweet Spiral. The only tweets that were allowed were those that: did not exceed the single-tweet word count (i.e., were not a thread or long post) had over 100,
... See more#2—Show-based telling > tell-based telling Showing your LLM examples of what it is you’re trying to create is the principle of showing vs. telling—a key tenet of storytelling the world over (and something Geroge Lucas certainly understood). But I’ve found that showing is also an excellent way to approach any telling that you need to do. In accor
... See more#1—Less is often more when it comes to instructions For whatever reason, the presence of certain words can skew LLMs into unexpected behaviors. Additional instructions will often go ignored until you remove the offending words or instructions. Recent research shows that a less-is-more approach seems to work for LLMs on a pretty profound level. For
... See moreThis resonates with Jeff BEzos philosophy that ultimate form of alignment is no communication. this creates autonomy and independence
Overcoming few-shot friction There is one problem I’ve noticed with example-based prompting: Most creators and businesses aren’t using it. I think this is because you have to overcome three major inconveniences before you start to take advantage of few-shot prompting on a consistent basis: Upfront effort: A few-shot prompt is only as good as the ex
... See moreOne reason that helps to explain why Lucas’s scrappy team was able to snatch victory from the jaws of defeat is because they were in total alignment. Prior to the shoot, Lucas sat them down and had them watch four films that embodied his desired vibe for Star Wars: 2001, Silent Running, Once Upon a Time In the West, and Satyricon. Armed with these
... See moreSame as prompting in AI
However, if the strategy is a long–short dollar-neutral strategy (i.e., the portfolio holds long and short positions with equal capital), then 10 percent is quite a good return, because then the benchmark of comparison is not the market index, but a riskless asset such as the yield of the three-month US Treasury bill (which at the time of this writ
... See more.implementation .market