I am currently making a fair amount of my living helping out CEOs like this. The quick-sand that LLMs let non-engineers build overtime is pretty remarkable.
A project usually starts with a list of basic looking cosmetic bugs that the stakeholder is having a hard time getting Claude to fix. Literally every bug unearths a heap of other bugs or architectural problems.
As an example yesterday I was looking at a basic, “record XYZ not appearing on list view” bug. Turned out that Claude had built the list view (which should have been backed by thousands of records) to only ever load the first 100, and then do all organization, counts, sorting and filtering on the frontend on that dataset.
Also found a query that was taking ~18 seconds to query 1 record from a set of ~60.
Plucking strings is usually synthesized using Karplus-Strong synthesis which is a very short delay line loop with a low pass filter. The delay gets excited with a short burst of noise. The length of the delay line tunes the string.
Karplus-Strong can be extended in ways to simulate different types of plucking, acoustic pickup at bridge, or electric pickup at any point along tbe string, and plucked at any point along the string. Body resonance can be simulated etc. It's a pretty fun synth technique to play with. Amazing to take beyond simulating conventional instruments.
A project usually starts with a list of basic looking cosmetic bugs that the stakeholder is having a hard time getting Claude to fix. Literally every bug unearths a heap of other bugs or architectural problems.
As an example yesterday I was looking at a basic, “record XYZ not appearing on list view” bug. Turned out that Claude had built the list view (which should have been backed by thousands of records) to only ever load the first 100, and then do all organization, counts, sorting and filtering on the frontend on that dataset.
Also found a query that was taking ~18 seconds to query 1 record from a set of ~60.