2,417 karma · joined May 10, 2014
We’re in such a “you’re either with us or against us” phase of politics that a discussion with the “other team” is difficult.
Combine that with people adopting political viewpoints as a big part of their personality and any disagreement is seen as a personal attack.
https://us.macmillan.com/books/9780374615369/wheretheaxeisbu...
Then I get it to go through each section of the todo list and check each item off as it completes it. Generally results in completed tasks that stay on track but also means that I can stop half way through and go back to the tasks without having to prompt from the start again.
Gemini seems to now advise you when you’re telling it to do something that may not make sense - first time I’ve really seen a non-Yes Man LLM. It’s more like a Yes-but-are-you-sure man.
I've stopped using agent unless its for a POC where I just want to test an assumption. Applying each step takes a bit more time but means less rogue behaviour and better long term results IME.
Give me Tailwind standardised utility classes over having to search through the codebase to find what a dev 6 years ago called a CSS class.
https://wagtail.org/ is a solid CMS
Can you expand on what the LLM work here is and it’s purpose?
> 3. Hypothetical answer generation from a query using an LLM, and then using that hypothetical answer to query for embeddings works really well.
Interesting idea, going to add to our experiments. Thanks.
Having been through the year long build of a similar app for another health condition here’s some thoughts focusing on the GenAI side of things:
- What’s the source of the responses? Is this a RAG system or straight-to-LLM?? We have an ever-growing huge repo of domain expert written content which is the source for our RAG system. It’s far easier to control potential misinformation with a well set up RAG and some tight prompting/guardrails.
- What verification do you have that the responses are correct? We have a group of 50 highly experienced experts in the field who constantly vet the responses to our synthetic set questions and it was eye opening how often our “looks good to me” analysis was off at the beginning.
- The main reason for this questions was that your responses are going to be wrong sometimes, what legal protection do you have? Disclaimers, terms of use at absolute minimum. Who is liable if the answer is wrong? Just presume someone is going to be very upset if your response gives them bunk info.
Either way - great work.