191–197 of 197 posts
Earlier quoted context omitted.
whats the intuition for 2/3 of RAM?
Because there’s always some overhead during inference plus you don’t want to fill all your available RAM because you risk swapping to disk which will make everything slow to a crawl.
UX Fail. The first time I clicked the link, I thought it was just another chatbot and exited--I'm so overexposed to them. Then I realized I'd exited without giving it a fair chance, so I opened it again, and looked at the prompt. Ironic I'm being presented with a prompting question. Pondered on it for a while, decided I don't know (or at this point care) what it is and exited a second time.
Thats a U issue not a UX issue.
Earlier quoted context omitted.
Just tried and got the same odd response. Maybe "what is this" or is a common phrase searched for that leads to Google Lens? No matter what, Perplexity is now the worst of the worst. They were early with the ability to upload documents but the utter failure of Perplexity to be useful is proving what I have been saying for a year now, (1) LLMs are not "AI" any more than a spell checker is and (2) LLMs are not really u…
While I understand what you are trying to say with your analogy I think it shows a misunderstanding of how they work. If you meant a very good autocomplete then yes that's exactly what they are. However, predicting the next word in an autocomplete can be naive or rather involved. > not really useful for anything other than a VERY good spell checker. Try GitHub code pilot. Try asking it to summarize something you know…
People keep trying to apply them as autocompleters... that doesn't mean they're good at it.
I think the following would be a worthy challenge to an AI: (entire prompt follows) My NFSv4.2 server occasionally prints this and then some `[nfsd]` processes hang. They cannot be killed and the clients that made a request to them will also hang. Processes that were using that NFS mount will become zombies if we try to SIGKILL them ``` Dec 16 16:16:05 host-00 kernel: receive_cb_reply: Got unrecognized reply: calldir…
Mixtral had something in that vicinity: Disable NFSv4.2 features: Although you mentioned that your mounts are read-only, it's still possible that some NFSv4.2 features might be causing issues. You can try disabling some of these features by adding the following options to your NFS mount command: vers=4.1,minorversion=1,proto=tcp,sec=sys This will force the client to use NFSv4.1 with TCP and system authentication.
Earlier quoted context omitted.
I am not sure how you may have gone about it but I was able to get this script, from ChatGPT4: #!/bin/bash # Script to convert git diff output to a searchable format # Check if a git repository if [ ! -d .git ]; then echo "This directory is not a git repository." exit 1 fi # Filename for the output output_file="git_diff_searchable.txt" # Empty the output file or create it if it doesn't exist > "$output_file" # Proces…
However, I did do some prompt "engineering" alongside using your literal request. I definitely should make it clear that I didn't only use your request verbatim but I augmented it a bit with some additional prompting cues.
What it usually fails at (maybe 4 can do it, I only use 3.5) is that the output should have one line per line-number, so nothing like 9-15 but 9,10,11,12 etc. I made this very explicit, I gave also examples on how the output should look like. Nothing helped.
Also, I explicitly set it should work under macOS but there were many syntax errors or uses of grep that are incompatible with macOS. So maybe part of it would have worked with linux, not sure. If you can maybe reformat, I could check
Earlier quoted context omitted.
Just tried and got the same odd response. Maybe "what is this" or is a common phrase searched for that leads to Google Lens? No matter what, Perplexity is now the worst of the worst. They were early with the ability to upload documents but the utter failure of Perplexity to be useful is proving what I have been saying for a year now, (1) LLMs are not "AI" any more than a spell checker is and (2) LLMs are not really u…
While I believe the impact of LLMs is often overstated, I'd like to hear what you really mean that they are not AI any more than spell checker. Arguably an LLM is significantly closer to AI than a spell checker.
As to why an LLM is not AI? People are wrongfully "afraid" that an LLM is somehow make "bad" information too easily available to people. Like how to rob a bank or make a bomb. The confusion is in thinking that an LLM can output something that it had not seen in training and supposedly all the training data is available elsewhere. Now, "data leaking" is a serious issue with LLMs but that has nothing to do with "AI".
An LLM is a good auto-complete, which is a good spell checker, which is a good search algorithm. I don't see how we ever get from context search and retrieval to "AI".