You could do that indeed, but the performance would be abysmal. For this kind of use-case, it would be a LOT better to use a small pre-trained model and either fine-tune it on your materials, or use some kind of RAG workflow (possibly both).
> it would be a LOT better to use a small pre-trained model and either fine-tune it on your materials, or use some kind of RAG workflow (possibly both).
I noticed NewRelic has a chat feature that does this sort of thing, it's scoped very narrowly down to their website and analytics DSL language, and generates charts/data from their db. I've always wondered how they did that (specifically in terms of set up the training/RAG + guardrails). It's super useful.
You might be able to figure that out just by asking it - see if you can get it to spit out a copy of the system prompt or tell you what tools it has access to.
The most likely way of building that would be to equip it with a "search_docs" tool that lets it look up relevant information for your query. No need to train an extra model at all if you do that.
I don't think this is about education, but I suspect rather something more akin to "intellectual revenge". Let me explain : In my experience, people who are into conspiracy theories are usually people who have been intellectually marginalised or disparaged during their life. It's not about being stupid - I think that's besides the point - but it's about being called and made feel stupid, literally or metaphorically.
People don't want to believe they are stupid, and they especially don't want to believe the people (or institutions) who call them stupid are superior to them. So they find a way out, by believing something that not only makes them feel important (they know but other people don't), but also superior to those who ostracised them in the first place.
I've been thinking about this for a while, but somehow never came across any similar ideas anywhere, anybody got references (or comments) ?
There is also a component of this which is (some) people needing a simple explanation for problems and injustices and preferably one where _someone else_ (individual or group) is to blame.
Yeah, that psychoanalysis makes sense, but why would there suddenly be so many people that supposedly had traumatic experiences in being judged stupid?
ASA is very prone to warping, and thus needs an enclosure to keep ambient temp high enough while printing. You might be able to print small parts in ASA with a non-enclosed bedslinger like this, but you will run in trouble for bigger parts.
I print ASA all the time on my Prusa MK3S. It's the filament I use the most. The printer is not encased, though it's also not in a draughty environment.
I rarely have a warped part, and I've printed from tiny parts to some that would take most of the bed and 10-30cm tall.
Keeping the bed clean is usually enough. For trickier parts I add a brim. I always use a release agent (I prefer a thin layer of talcum powder but glue and others work as well), otherwise it sticks badly and I've damaged more than a couple PEI sheets trying to get them off.
