hugozap

8gb

It is, it doesn't require any setup.

After installation:

> ollama run mistral:latest

I'm a happy user of Mistral on my Mac Air M1.

I've personally never been in a project where I've felt that the team was doing well thanks to scrum but in spite of it.

There will always be places with social revolts. Still a tiny tiny fraction of how it was in the past.

Watching news can distort your perspective very quickly.

Most people that retire don't turn into murderers or anarchists. I find very interesting how people tend to picture the worst possible scenarios, maybe a lot of Movies or TV influence?

I think that's a very limited view.

A lot of people that retire from their careers pursue other interests that fulfill their needs, maybe it will be the era of amateur artists everywhere. Others prefer to manually do tasks that can be automated.

Others could engage in cooperation with robots because humans will always have creative desires.

You can get far with htmx and any server template language. Common patterns are already encoded as html attributes.

Most framework devs don't have any incentive to stop adding features. What was a simple and elegant tool ends up trying to do much more and the additional complexity negates a lot of the benefits.

A dynamic routine that can run in a secure sandbox invoked from the host.

I think total disconnection on weekends cause more stress on Mondays and that's why most people hate them, you need a lot more cognitive effort to resume work.

I can already see AI Doomers predicting total catastrophe from this project.

The study group were mostly customer support agents. The nature of that work is very different from other knowledge workers so probably the results don't map to more creative fields.

I replaced my Obsidian workflow with a one big Google doc and it's been the best decision. No need to sync, offline support and reduced complexity.

I wonder if these improvements in memory alteration will make it possible to create micro models using an approach based on pruning non relevant connections but preserving the reasoning abilities of large models like GPT4.