Have you tried using non-LLM based methods? Like starting with something rules-based and working through a layered multi-model setup?
That’s what we’ve been using for document extraction where accuracy needs precision (capital markets documents, medical assessments). We had a go at pure LLM with medical documents but the output was poor and felt like it would take substantial investment to create something more robust.
Yes - 100%. That's why I have a Slack where I invite friends and other people hacking away. Planning on setting up more remote social stuff to beat the 'loneliness' factor. Happy to send you an invite if you want. We're friendly.
Interesting. During my time there, I found the scene to be decently vibrant. It's definitely not SF but there are quite a few events and get-togethers happening around.
I was actually going to comment on the same fact about professionalism growing into English football. Back when the Premier League era began compared to now is just a whole different level as what most players have been saying on SkySports. You see players playing in their mid and late 30s.
I was also going to hypothesize that players are significantly mentally equipped to cope with away pressures and their tactical shape stays more consistent regardless of being home or away.
This is really cool and I can see a ton of opportunities to leverage this in the enterprise. Using the scanner, does it scan what's on the marketplace as opposed to what's already installed?
I think someone had already mentioned that it would be useful to have this as an extension to scan existing installed extensions but would there be a way to scan just prior to extension installation?
I was actually thinking of setting up some coaching sessions / workshops. If you're interested, I'd love to connect with you just to get a understanding of folks would be looking for and put together a program of some sort. In exchange, I'd be happy to share my experiences and exchange ideas on improving soft skills.
I've worked as a software engineer and as a consultant and went from engineering to business back to engineering again.
That’s what we’ve been using for document extraction where accuracy needs precision (capital markets documents, medical assessments). We had a go at pure LLM with medical documents but the output was poor and felt like it would take substantial investment to create something more robust.