Matt Wynne

If, like me, you are sick and tired of reading dense sentences packed with jargon, written by robots, I offer you a choice: 1) close the laptop and go outside to touch some grass 2) download my fine skill github.com/mattwynne/sk... 3) continue to suffer, like a fool

Don't hate the AI. Hate the capitalism.

Don't hate the AI. Hate the capitalism.

Don't hate the AI. Hate the capitalism.

Non-profits and government agencies who can’t afford the tokens and get stuck with shitty software, left further and further behind.

Don't hate the AI. Hate the capitalism.

LLMs not only amplify social injustice through the inherent bias of the material they were trained on, they also move even more wealth and power towards an ever smaller number of people who can access and harness this technology.

Don't hate the AI. Hate the capitalism.

But I think being angry with the technology itself is missing the mark.

Don't hate the AI. Hate the capitalism.

I know a lot of people in the software engineering community right now who are, at best, begrudgingly accepting that LLMs are here to stay and, at worst, very angry about the whole thing.

I've decided I quite like the factory metaphor for hands-off/augmented coding using LLMs.

Anthropomorphizing them is problematic in many ways. So a metaphor where I literally refer to the LLMs as "machines" working in an "assembly line" is vastly preferable to one where I talk about agents or hallucinations.

I've decided I quite like the factory metaphor for hands-off/augmented coding using LLMs.

One of the thinking errors that it's so easy to get drawn into when working with LLMs is that they're somehow sentient. It's just not true. They're machines.

Are you trying different models? What do you find are their strengths and weaknesses?

I've also seen comparisons of the images generated by the different models, and the GPTs seem way ahead of the game there.

Are you trying different models? What do you find are their strengths and weaknesses?

Even when configured for "concise" output it still talks a lot, in comparison to the GPT models which are much more focussed on the facts.

Are you trying different models? What do you find are their strengths and weaknesses?

AI summaries are lame. A summary of a book is not the same thing as learning it. Let's be honest, you never read the summary of a meeting you missed unless you absolutely have to.

They’re boring. Reading is not the same as learning. The interesting thing about an agent is that it can be a study partner. It can ask you questions, listen while you explain it back, and show you where you have misunderstood.

E is for Escape Velocity When I had the chance to hang out with Justin McCarthy earlier this year, one big idea I got from him was the idea of escape velocity.

The danger of course is that they do sloppy work, and you end up doing unpleasant labour cleaning up their mess. But it doesn't have to be this way. You can learn to get great results from models, by giving them the right context and harnessing them with validation loops.

E is for Escape Velocity When I had the chance to hang out with Justin McCarthy earlier this year, one big idea I got from him was the idea of escape velocity.

This was based on his mantra, to constantly ask yourself: > Why am I doing this? (implied: the model should be doing this instead) The basic idea is that labour is gravity, and the more you can get agents to work for you, the lighter you become.