61–70 of 94 posts
I can’t help shake the feeling that something closer to code (or specific training?) and further from natural language should be being used to configure these models at this stage of development. I was _astounded_ by the ‘Sydney document’ being MS’s way of ‘configuring’ New Bing. Admittedly I have closer to a layperson’s understanding than an expert’s, but with some knowledge of how neural networks work, and having p…
If we're adjusting the way we speak to AIs, are we training them or are they training us?
Interesting. It's almost the exact same structure (although better organized) that I have built in my "AI Programmer" project (also in Node). Which by the way I hope to have a new release within a week or so. I am not mentioning the domain name again until I have the new release because it much, much better than the version I have up now. The core idea is that you need a certain structure in order to deal with the li…
>so you will need to truncate the beginning of the conversation at some point I wrote a little python script to keep track of a running conversation when I started playing with openai's completions API. I keep track of how many tokens the prompt is taking up, and when it gets too close to some configurable threshold, I then have a different prompt to tell the AI to summarize the conversation and any previous summary,…
Interesting, I just made myself something similar[1] because I found myself using the same prompts over and over again in either the OpenAI playground or in ChatGPT. The simple tool quickly provides builds up a form that either myself, or my staff can use. So far my pre-canned prompt forms are as follows[2]. [1] https://files.littlebird.com.au/Screen-Recording-2023-02-16-... [2] https://files.littlebird.com.au/Screen…
I'm just astounded by Microsoft's execution in both business and open source. It's such a stark contrast to the Ballmer era. They were a closed ecosystem. And now they invest so heavily in being open. It's amazing to see really. Hugely beneficial for the entire industry. Not everything that comes out of there is going to be gold but this is great.
I see a few comments about how the interface should be better. I would argue that the current interface is broad and can be adapted to a wide range of needs. The real value I see (and an area I've been exploring recently) is creating abstractions around prompt engineering. The idea is that at the moment, the better the prompt -> the more relevant the output. However businesses that act as proxies for chatgpt can take…
> It's as if chatgpt is the database, and prompt engineering systems are the query-optimizers. I've also been experimenting with this. Contact info in my profile if you want to reach me.
I can’t help shake the feeling that something closer to code (or specific training?) and further from natural language should be being used to configure these models at this stage of development. I was _astounded_ by the ‘Sydney document’ being MS’s way of ‘configuring’ New Bing. Admittedly I have closer to a layperson’s understanding than an expert’s, but with some knowledge of how neural networks work, and having p…
There’s no other way to program it. There no “code” to speak of. The only way to control it is to give certain phrases more or less importance. You do that with direct prompts or tons and tons of training data.
For example, you could imagine an LLM that as well as outputting probabilities for the next token, output the probability with which that token makes the response "offensive" or "helpful" or "playful". Then when it's time to use the model, you can slide some offensiveness and helpfulness parameters up and down depending on what the model is meant to do.
Perhaps this is a less powerful approach than training the generic model and telling it "Sydney is feeling particularly helpful today, and never espouses violence", but it's certainly an alternative. One problem is that experimenting with fundamentally different architectures for training GPT is very expensive, but experimenting using prompt engineering is relatively cheap.
I see a few comments about how the interface should be better. I would argue that the current interface is broad and can be adapted to a wide range of needs. The real value I see (and an area I've been exploring recently) is creating abstractions around prompt engineering. The idea is that at the moment, the better the prompt -> the more relevant the output. However businesses that act as proxies for chatgpt can take…
> It's as if chatgpt is the database, and prompt engineering systems are the query-optimizers. I've also been experimenting with this. Contact info in my profile if you want to reach me.