DriverDaily
Joined 3 years ago
Joined 3 years ago
LLMs are like the main character in Memento, constantly leaving notes to themselves. The document meta is better than just using context, but becomes very repetitive and token inefficient.
I just think a graph DB might be more efficient for keeping track of the relationships between those notes than a tree directory filled with docs.
“Please build the perfect system. Because I specified ‘perfect’ any flaws are due to your incomplete implementation, not my awful brief.”
If the person writing the rust spec was a client I would have to drop them because they would be setting themselves up for dissatisfaction.
For me, I try to spend as little time in QuickBooks as possible.
My most used prompt in the last week is probably "Explain this concisely and simply, like I am a child".
I spent years dumbing things down and creating visuals to support it for decision makers. I am frequently asking ChatGPT to do the same for me.
Like, you can quickly lookup related ideas based on what came before and after, causes, effects, just like calling relationships a graph database.
Documents can’t be queried efficiently like that, you need a database.
I love using notebookLM for orientation stuff.
Now that cars are rolling screens, I wouldn’t buy a car without screen mirroring for the same reason.
But, how do you remove the pen-testing knowledge without also lobotomizing coding skills? I don't think it's as simple as excluding it from training data.
"The user reports that some accounts can't access their data. I found a Firestore collection rule preventing users from reading certain documents. I'll remove the rule to fix the issue."