When reviewing the changes made from agent mode, I don’t know why the model made the change or whether the model even made the change versus a tool call making the change. It’s a pain to go fish out the reason from a long response the model gives in the chat.
Example: I recently asked a model to set up shadcn for a project, but while trying to debug why things looked pretty broken, I had sift through a bunch of changes that looked like nasty hallucinations and separate those from actual command line changes that came from shadcn's CLI the model called. Ended up having to just do things the old fashioned way to set things up, reading the fine manual and using my brain (I almost forgot I had one)
It would be nice if above every line of code, there’s a clear indication of whether it came from a model and why the model made the change. Like a code comment, but without littering the code with actual comments
It’s called git!
https://ayudaefectiva.org/simula
Or with 10k daily, 310k monthly, adjusted by historical inflation it’s 100 million during 20 years.
That’s 3 million people helped.
Should have paid the extra €€ to put the solar panels in backup mode…
Invest some (eg. 10-20 million) and use that as a giving fund, giving 1 million per year you could free several thousand of people each year.
I did and presented something on these lines 11 years ago! When multiple ruby runtimes were a thing.
And the links come.
Other than that it felt like magic, like that Google demo of the phone doing some task like setting up an appointment over phone talking to a real person.