Why not
922 karma · joined October 26, 2014
Although Central European Time (https://cet.httpclock.com) will be valid too, as well as a few other time zones (for maximum coverage it uses 12 hour time format)
And yes I understand an empty response the majority of the time is perhaps a little confusing, and from the logs it looks as if most visitors are receiving such a response, so while I wished to keep it as "pure" as possible I probably should add a simple "about" page.
4 can be an absolute demonic hallucinating machine.
From my own experience XML tags are incredibly powerful — particularly for very large system prompts, with some markdown in there too.
It has full knowledge of your entire codebase rather than being limited to currently open files (I assume embeddings with RAG) and will index documentation (or any other URL).
I find it especially useful for things like Swift/SwiftUI APIs given how quickly they can evolve, not to mention copilot’s other limitations when it comes to languages beyond JS/TS, Python, etc
Edit: I wrote this after reading some comments. The article is interesting and not an attack on its author.
https://twitter.com/RemitNotPaucity/status/15623190045631733...
https://twitter.com/wavefunk_/status/1562468847483244546
https://twitter.com/remi_molettee/status/1562440354955395084
https://twitter.com/pharmapsychotic/status/15625200064741007...
https://twitter.com/TomLikesRobots/status/156243596942050509...
E.g., distilling large amounts of text into short summaries while retaining substance is effectively the opposite of this, and is a use case GPT3 has been applied to successfully/commercially.
Absolutely. From a surface-level read it may sound sensible but it all falls apart very easily.
The lines of reasoning for each attempted rebuttal are practically non sequiturs.
Out of curiosity, I’d be interested in seeing some attempts using prompts intended to induce CoT reasoning (“let’s think step-by-step“ etc.)
Could you elaborate a little more on what you're asking? Perhaps an example?
I feel as if any use case like this, — particularly if it crosses into interpersonal relationships and disagreement — risks being incredibly dangerous as far as reinforcing your own biases.
It should go without saying that to even consider this, you should have a solid grasp of the fundamentals of these LLMs, their limitations and inherent biases, and their tendency to unconditionally agree with you regardless of your position – particularly in a dialog-style format.
One clearly problematic use case would be asking about an interpersonal conflict where there exists an established societal and cultural power imbalance.
E.g., describing a disagreement between a man and a woman and asking for insight into that conversation would be incredibly flawed, no matter how objectively it were depicted.
This isn't an attack on you nor am I claiming you're doing anything at this level, but taken to the extreme it’s something I can easily imagine someone doing after reading your post.
I’d really just like people to be cautious. After all, this is the same language model that told me a social media post contains hate speech due to “negative sentiment towards a protected class (racists)”.