irasigman

Murphy’s Law says if something can happen then given enough time or trials it will happen.

Agent swarms solve for number of trials so it becomes more so about what “can” go wrong.

How do you weight the value of semantic layers when all of the labs are chasing shell usage benchmarks like TerminalBench?

Aside from the enterprise stuff like consistent metrics I’m not convinced semantic layers improve agent performance. Case in point is Snowflake Analyst has been routing 90%+ of queries to traditional SQL as opposed to their own semantic SQL dialect.

A semantic layer is a concept from 2018 in the BI world. Metadata is one thing but semantic layer implies an abstraction from physical data with lossy translations.

It’s a shame that Arvix (and once thoughtful places like Kaggle) are used for self-promotion.

I get people want to work at an AI lab but slopping it in public in this manner is counterproductive to the original intended purpose of these places.

Meanwhile revenue is up 12% YoY to 6.4B in latest earnings.

Prefer evidence from the eyes over noise from the ears.

I think you mean 8 out of 20. Fewer than half.

Hello all, using an ideas first approach and an AI agent with access to a novel backtesting language, this blog post details the hunt for institutional buyers building positions in NVDA either for themselves or on behalf of their clients. Happy whale hunting.