Yeah her comment that basically saying bullshit like this almost SOLEY to justify layoffs is pretty deprived is right on the money
fruitycoder
I think you can point to a file instead too
I will say, the Le Chat provider is pretty decent. You really can use it more natural language. "Rewrite it with a better rhyme scheme" "remove the last line" and it just got it.
Why no local option though? Why no anonmysing option?
Edit: There is a right click option which does make this officially actually useful for me now (summarize this!).
Other models do have RAG options and Mist real supports making agents with specified documentation too to at least fine tune too (not as good as full grounding though IMHO)
I was disappointed there was no local option...
For real. Dude seems to think people can jack around and do nothing in office
Tbh sounds yet another "if we lived in another society this would be great" how much money is spent trying to measure, manage and control people doing the actual work?
Honestly though make an opensource version of this and run in it within the team, make the results public to the team and it's a great tool to motivate coworkers and make sure they are working without needing a manager (as often at least) to assign KPIs and get status reports.
Never got why small government guys would support it where I lived. It's just the government stepping in to limit the union on behalf of big corporations
Energy independence is one of my favorite reasons for it. Getting actually invest and own my power generation vs being stuck in a subscription with a corporation who is subject to geopolitical movements on where, how and when they can buy their fuel.
Crazy to see right winger, pepper types sometimes (not all of them) get sucked into being a liberal thing lol. Like is it a liberal thing to want to own my house or car too? What a weird thing to think
Awesome! Servo as an embedded solution is a great choice imho! Glad to see them start their to build into the full browser
At DefCon this year a dude had a robot that used different LLMs for different pieces including a movement one that out put specific API structured output.
Maybe something like that to take complex output and turn them into lower latency smaller outputs
To discover and adhere to an objectively moral life.
I will say I worked one job where we had to submit network changes which was supposed to be checked by 5 different network engineers and then implemented.
Those 5 people would take a couple months just to fuck up my requests every gd time.