The comments are not showing up for me now, but when they were still showing for anonymous users, there was a link to https://commoncrawl.org. I've been sort of worried about letting agents hit websites, I wonder if a fetch_url agent tool could be made to look in common crawl first before hitting the web for it?
In the context of the title of the hn submission, I read “RAG Context” as “the retrieved content injected into the context window” .... "read" read /rε d/ not /riːd/
> So when an agent does "cat file.txt" that's RAG to you?
"Standard ML is a functional programming language, in the sense that the
full power of mathematical functions is present." From a Pdf linked on the repo (I didn't know what Standard ML was, I was hoping for a mark up language)
You could also produce special purpose applications this way, say to provide access to the online library catalog, or a run a gopher client for use in a public terminal lab. Telnetting to a unix account running some sort of restricted shell was how these often worked.
A sibling comment I can't reply to asks if you can do with with unix permissions.
These were really intended for anonymous guest access, or at least often used for this purpose. You couldn't do the same things with the file permissions systems at the time.
When I was an undergraduate biology student in 1991 a suitemate told me I should go to some desk in some building over by Muir and get an account on the VAX. There were strange rooms all over campus that were open 24/7 and were loaded with green and amber screen terminals with integrated keyboards. Lots of sessions for CS lectures were held in these rooms and there was always interesting notes on the white boards (most rooms still had black boards or green boards, but think the chalk was too dusty so these rooms usually had the white boards.
Once I saw an instruction that was circled with an arrow pointing to is that said:
man man
man -k -or- apropos
and that was how I learned about computers.
I just typed `man man` in a terminal on my Mac, and luckily its still there.
I do think it pays to be nice to the model. When the context window is running out I like to ask "please summarize what went well and what didn't work in this session. How could the user be more helpful?"
When I was about 4 years old, this was the first movie I saw in a theater, it was a double feature with fantasia. Next time I remember going to a theater when my parents took me and a friend out of kindergarten to see Star Wars on opening day.
I wholeheartedly agree with these, and I think point 1 is a real danger.
An ai system can't lie, and it can't deliberately ignore your directions. The current frontier class does not have a model of the world or their action -- they live in a world of words. Scolding them or arguing with them has no point other than to scramble the context window.
I do think zoomorphizing them might be useful. These poor little buggers, living as ghosts in the machine, are pretty confused sometimes, but their motives are purely autoregressive.
I agree that anthropomorphizing is a real risk with LLMs, but what about zoomorphizing? Can feel bad for LLMs without attributing them human emotions/motivations/reasoning?
When ATMs first came out, they were mostly still only at the branch because they were big machines. I remember in the late 70s/early 80s, if you got a steady check (like social security or a paycheck from a steady job) you could cash them at the liquor store. The liquor store would even run my Dad a tab, and he would pay it off when he cashed the check. On paydays he would not be the only one doing that, they must have had to get a lot of cash on hand.
[ my public key: https://keybase.io/tingle; my proof: https://keybase.io/tingle/sigs/sUg3nhBMyAmDusnRiGy2z6Fgzxj9Woonpb5oRwQSxzg ]