"User" makes sense. Another option would be "Client"

Hey will you share your workflow and how you get LLMs to build correct things for you (or inspite of you)?

If you’re using the latest models( Opus/Fable/Astra/ maybe Sol) and the default harness, along with a little guidance against the worst tendencies like over-writing tests, you really shouldn’t be getting the wrong things built. Like a coworker, you can’t throw it blind into a monster codebase without some guidance, but otherwise the latest models genuinely just work TM.

Testing, testing, and more testing. In the project I'm working on right now, about 2/3 of the code is in one way or another related to testing. As a human coder, I'd never spend that much time on building test harnesses, automating regressions, writing unit tests, etc, but it's cheap when you can have a robot do it.

So you assume code written by the agent canno be trusted? But how comes you are trusting the tests?

At my work we still have a QA dept that runs the manual test suites before each release. We have also automated almost all of those manual tests and they gate every merge to mainline.

Things are still found but normally it is a new test case or an edge condition we don’t have an automated test for. The ever growing e2e suite has reduced the amount of regressions pretty drastically.

EDIT: I forgot to note that automated e2e tests were always the answer to improving quality. AI has just made it cheap to have several layers of test coverage.

To start, you make it a rule that every test must pass with the fix being tested, and it must fail if the fix is missing.

You of course use another AI to test your tests, have you been living under a rock? /s

How are these /s posts even allowed? You contributed nothing to the conversation other than noise.

Interesting that he didn't reply to this.

I only see that EmbeddingGemma 2 is Apache 2.

"EmbeddingGemma 2 is made by Google DeepMind and released under Apache 2.0. This is an independent project, not affiliated with or endorsed by Google."

Running an LLM to delete files seems like overkill to me. Couldn't a cron job do the same thing? Or is the clutter just put into random places, which, if true, seems like bad software, which then leads me to consider the output of LLMs in general, which then leads me to wonder why are we doing this?

But, I'm just wondering.

Oh it makes all sorts of temporary files and directories, sometimes in the right places as per UNIX filesystem conventions, but often not.

You could use snapshots or whatnot to reset the state whenever you like. Using an LLM to clean up files often seems like overkill to me.

Wouldn't a snapshot delete everything else you saved?

You keep your source tree on a separate file system with version control, one hopes.

So you only snapshot the rest. (And since your source tree is under version control, finding stray garbage there is straightforward unless you checked it in)

From the article by Rich Hickey that is a counter point "'AI' is not a tool"

"You are only a software update from everything you've 'learned' being rendered obsolete by the latest algorithm. "

Was a hoe not a tool because it was rendered obsolete in many applications by tractors?

Not to mention that I find these semantic discussions pointless and unproductive.

And what actionable information can be extracted from these articles? Near zero. It's a collective waste of bright minds.

> And what actionable information can be extracted from these articles? Near zero. It's a collective waste of bright minds.

But how else can I virtue signal how smarter I am than you, ordinary sheeple who obviously don't understand X and continue to do Y?

If you could be made obsolete by a collection of information, all teachers would have been made obsolete by Encyclopædia Britannica.

Never underestimate the stupidity of a famous person with a hot take.

I don't think he is saying the person becomes obsolete, just the stuff you 'learned' on that LLM because the LLM maker decided to change it.

Better code allows you to write new features with less risk to disrupting your current features.

Software design and architecture is about creating a system that can be built well, run well, and modify well.

If you just throw things together without thought you get an unmaintainable mess.