reggiepret

I think the prompt does add value, but its about wrapping the LLM + Prompt into a journey that works well for the intended use case. I think the most elegant implementation so far of this is: - notionai - blenderGPT

Both are embedded right where you need them, and they are tuned to provide great results. Another ChatGPT with a better prompt probably isn't much of a moat.

I think the idea behind agents is to have them a bit less constrained. If you can force input/output with better prompts that might help. Or if you can reduce the temperature of the underlying LLM generation, that could make it a bit more deterministic.

Or switch to using a chain.

this is a really great post. I thought I was blown away by the code interpreter, and you have shown some excellent ways it can be used. thanks!

this is great!!

The final cashflow amount of the house graph (in the example) ends in the negative, s this accurate?

I think this is a great idea.

How would day 1 look for the dev assistant? and how mature would a dev team need to be to incorporate someone with relatively low experience into their environment? psql drop db --prod?

A bullet journal to review previous day and overall goals.

A text based adventure game where people collaborate on: 1) Policy decisions 2) logistics planning 3) public health education to prevent the spread of a virus that has mysteriously arrived in a few city centers. Where the interactions are through a chat bot in your favourite texting platform.

Thanks! The_DaveG, this is great to hear! I hope we can help the smaller businesses to not lose out on these overdue invoices, and to never not send an invoice either! Cheers

Any comments or feedback would be greatly appreciated! Also, not sure if possible on HN, but send a message if you are keen to give the product a go! I will post to this thread when the bot is live (hopefully tomorrow)

Hi, definitely interested in this product!

Keen to use the CLI version.

do you have a sign up form?