81–90 of 139 posts
The methodology used here is a generic solution for distilling a non-generic corpus of utterances of , into a generic platitude machine.
I see that you are asking about "How to get a job at Google". I will help you with "How to get a job at Google". In order to solve the problem of "How to get a job at Google" please follow the following steps first:
- rewrite your resume in Google Docs
- reinstall Chrome
- apply to the job
Let me know if I can help further with "How to get a job at Google". I like using it, but I have to tune my prompts to make sure that they don't bullshit me before getting to the point.
could you do this for medical journal articles?
Earlier quoted context omitted.
I wish the results were reversed, so I could "well actually" your comment, but 'site:news.ycombinator.com "well actually"' gives ca. 4k results in Google and 'site:news.ycombinator.com "I think you'll find"' gives close to 17k results, so you appear to be right.
Well, "it turns out that" beats both, with about 26k results ;)
Am I correct in understanding that this doesn't actually generate answers based on HN, but instead finds semantically-near comments and sends them verbatim to GPT to summarize? Seems like a good enough hack, though I'd love a detailed writeup of how to actually specialize an existing LLM with additional training data (like HN).
The thing people don't realize is that right now there is a very large gap between the capabilities of a few models including OpenAI's most recent ones, and most of the other LLMs. So there are several options for actually training or fine-tuning with open models, but actually none of them have the language understanding and generation capabilities at the level of those new OpenAI models.
As far as I know.
Earlier quoted context omitted.
I wish the results were reversed, so I could "well actually" your comment, but 'site:news.ycombinator.com "well actually"' gives ca. 4k results in Google and 'site:news.ycombinator.com "I think you'll find"' gives close to 17k results, so you appear to be right.
Well, "it turns out that" beats both, with about 26k results ;)
I think this is false, but if you're reading quickly, it sounds cogent enough. As Sarah Constantin observed about GPT2 [0]:
> if you skim text, you miss obvious absurdities. The point is OpenAI HAS achieved the ability to pass the Turing test against humans on autopilot...The mental motion of “I didn’t really parse that paragraph, but sure, whatever, I’ll take the author’s word for it” is, in my introspective experience, absolutely identical to “I didn’t really parse that paragraph because it was bot-generated and didn’t make any sense so I couldn’t possibly have parsed it”, except that in the first case, I assume that the error lies with me rather than the text. This is not a safe assumption in a post-GPT2 world. Instead of “default to humility” (assume that when you don’t understand a passage, the passage is true and you’re just missing something) the ideal mental action in a world full of bots is “default to null” (if you don’t understand a passage, assume you’re in the same epistemic state as if you’d never read it at all.)
[0] https://www.skynettoday.com/editorials/humans-not-concentrat...
Am I correct in understanding that this doesn't actually generate answers based on HN, but instead finds semantically-near comments and sends them verbatim to GPT to summarize? Seems like a good enough hack, though I'd love a detailed writeup of how to actually specialize an existing LLM with additional training data (like HN).