HN user
LLMs are at their best when you have an expectation for their output. I generally know the shape of the correct response and that allows me to evaluate it's output on it's "vibes", rather than line by line. If there's no expectation then I have to take everything at face value and now I'm at the mercy of the machine.
Yeah I try to keep it away from overlapping it's work as much as possible. Using plan mode in claude or just telling codex to build a plan, that is structured in a parallelized way for multiple agents usually helps delegate tasks to be handled at the same time. Typically: app code, infra, and data layer are the main three, but obviously depends on the project.
If I ever find my self just waiting, then it always gives me an opportunity to respond to messages, emails, or update tickets. Won't be long now until the agents are doing that as well...
Checks out, that’s definitely a CTO’s perspective.
Banning phones is a waste of time, the children will find a way. We need to embrace phones and teach responsible use along with holding content providers accountable. A war on phones will be as effective as the war on drugs.
Tough crowd in these comments. I think this is a beautiful project and it applications to AI are very interesting.
Finetuning should never be the first step; it's slow, expensive, and indeterminant. Until you are maxing out that context window, you can just keep layering in more information into the prompt.
Pinecone makes it super easy to get up and running with RAG asap. Those prices are ridiculous though and any project with legitimate scale will move on to a more affordable solution.
I'm no die hard apple fan, but you would think I was if you heard me talking about my 16" m1 pro. It's an absolute beast, battery for days, and I've never heard the fan spin up once. It would take a lot for me to even give another machine a chance.
It’s ironic you say: “we are playing with fire.” Playing with fire is, in large part, literally how humans have come to dominate this planet. Why stop now?