Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

ChatGPT vs. open source on harder tasks

github.com

Post reply on HN
Print view View original

61–70 of 70 posts

Re: ChatGPT vs. open source on harder tasks

#61

Post by jxy »

elromulous wrote: post #22

The other day when I saw the (allegedly) leaked copilot prompt, and now again, I can't help but feel some sense of empathy, as if towards a living thing. I have a pretty decent understanding of how the current generation of LLMs work, and I too don't think we've achieved consciousness. But the prompts just sound so much like something you'd tell a human, or something you'd tell a host in Westworld.

Speaking of which, HBO now has the perfect chance of riding this LLM hype train with a new season of Westworld, only if they hadn't cancelled it.

Re: ChatGPT vs. open source on harder tasks

#64

Post by hm-nah »

I think these guys could benefit from better prompts.

When I use chat prompting…

- system: sets the context for the bot

  - “You are…”
  - “Act like…”
  - “Pretend…”
- assistant: specifies the task to be performed

  - “Classify…”
  - “Extract entities…”
  - “Translate…”
- user: asks the question, adds examples

These guys were asking questions and giving examples in the assistant prompt. I feel like that messed up the LLMs responses.

I can’t wait to try Vicuña and MPT. I can’t quite figure out how to host them in Azure without an expensive VM. Maybe Azure DataBricks…?

Re: ChatGPT vs. open source on harder tasks

#66

Post by Qweiuu »

candiddevmike wrote: post #16
hackernewds wrote: post #13

Earlier quoted context omitted.

are we going to now invent a programming language that communicates with LLMs? I find that funny

I'm not an LLM, but I am a native English speaker and English is pretty awful for conveying information succinctly. The lengths you must go with prompts to ensure you're getting the right response is extremely similar to the lengths you go to when delegating something to someone or describing requirements to a project. I wonder if whatever language we end up using to "converse" with LLMs would have value within an or…

I'm normally the type of Google person with doing minus or using other tags.

I totally gave that up with chatgpt and the magic of it is that it understands it so so we'll.

Sometimes I also switch to German in the middle of a sentence or use very vague words to describe something if the word is missing in my head.

Re: ChatGPT vs. open source on harder tasks

#67

Post by boywitharupee »

thomasahle wrote: post #31
andy_xor_andrew wrote: post #27

Earlier quoted context omitted.

I think there will always be some element of non-determinism with model output, regardless of how explicitly you define your rules. I think regarding: "Make sure to use real numbers, not fractions." It would be simple using Guidance to create some kind of validation function, which guidance would invoke after it gets the response from the model. In this case you would check if the number is a real number or not. And…

You don't need non-determinism. If you know you are going to generate a number, just mask the output of the softmax layer to only decode number tokens. That's exactly what stuff like Guidance and Outlines ( https://twitter.com/remilouf/status/1653765371273330688 ) do.

How do you mask the output of the softmax layer? The link you referenced doesn't provide specific details.

Re: ChatGPT vs. open source on harder tasks

#68

Post by MacsHeadroom »

hm-nah wrote: post #64

I think these guys could benefit from better prompts. When I use chat prompting… - system: sets the context for the bot - “You are…” - “Act like…” - “Pretend…” - assistant: specifies the task to be performed - “Classify…” - “Extract entities…” - “Translate…” - user: asks the question, adds examples These guys were asking questions and giving examples in the assistant prompt. I feel like that messed up the LLMs respon…

You can run Vicuna at chatGPT speeds locally off of CPU. idk about MPT.

Re: ChatGPT vs. open source on harder tasks

#69

Post by marcotcr »

One of the authors here.

I deleted the notebook yesterday after realizing it was weird to have a disclaimer saying 'this is our personal opinion' on a github repo under 'Microsoft'. I moved the notebook to a gist here: - https://gist.github.com/marcotcr/64ca85bd0be724f6d8fb8f1b3d2...

I didn't know we were on hackernews, otherwise I would of course not have made it a broken link :)

This morning, we put the link back, without the takeaways with our personal opinion at the end (it's still on the gist and on the blog post https://medium.com/@marcotcr/exploring-chatgpt-vs-open-sourc... )

Re: ChatGPT vs. open source on harder tasks

#70

Post by ShamelessC »

throwawayadvsec wrote: post #57
ShamelessC wrote: post #36

Earlier quoted context omitted.

Text to image paints a far less clear image (no pun intended) of the failure of open source efforts.

text to image requires a lot less compute for training and has far less business applications also...porn will make people achieve anything they set their mind to

This is true.
Post reply on HN