31–40 of 46 posts
Just use CALDAV; it's designed for making calendar entries automatically via email. I'm not hip with the fashion for putting an LLM into everything. I think it's lazy.
IDK about "lazy", but it's certainly an extremely expensive solution.
I am working on GabrielAI, which is a tool to filter and autodraft reply for Gmail and outlook and of course it uses LLM under the hood. https://getgabrielai.com In cases like this the author could just set up a filter like: "If the email contains a task for me" (or some variation) Then add a Gmail label to it. In this way the author will immediately find all the actionable emails for him in a specific folder, much f…
A bit classless, but do you mind if I reach out to you about your experience building GabrielAI?
I am working on GabrielAI, which is a tool to filter and autodraft reply for Gmail and outlook and of course it uses LLM under the hood. https://getgabrielai.com In cases like this the author could just set up a filter like: "If the email contains a task for me" (or some variation) Then add a Gmail label to it. In this way the author will immediately find all the actionable emails for him in a specific folder, much f…
author here. This definitely sounds all good. I'll be trying out your app. Funnily enough, when we were building this, friend pitched the idea you're doing (seems fantastic) on GabrielAI so we will be signing up for the beta. A bit classless, but do you mind if I reach out to you about your experience building GabrielAI?
Feel free to use the email address on the GabrielAI website!
I'd be happy to chat about it!
Earlier quoted context omitted.
author here. This definitely sounds all good. I'll be trying out your app. Funnily enough, when we were building this, friend pitched the idea you're doing (seems fantastic) on GabrielAI so we will be signing up for the beta. A bit classless, but do you mind if I reach out to you about your experience building GabrielAI?
I definitely don't mind! Feel free to use the email address on the GabrielAI website! I'd be happy to chat about it!
Earlier quoted context omitted.
I definitely don't mind! Feel free to use the email address on the GabrielAI website! I'd be happy to chat about it!
Sounds good. can't find an email on your homepage, but I sent one to the email on your privacy policy page. Might land in the spambox. Looking forward to it.
I must make the email in the homepage more prominent
I'm looking at the AppScript site. Is this like PowerAutomate, but for G Suite products? Also I don't know why, looking at the site makes me think it's a candidate that Google is going to kill off without warning: https://www.google.com/script/start/
It stands out that it doesn't follow the Design System of many other Google products - wonder if that means it has its own fiefdom.
And it has had significant updates as well. The newer runtime is based on V8 using some clever way to isolate the code. Previously they used Mozilla Rhino as the runtime because it was easier to sandbox, but it was also very frustrating to work with.
Now the DX is much better with more recent and performant executions and a better UI.
If I sound like a sucker it's because I am and building with Apps Script is fun even with its limitations.
While Power Platform in comparison might be 100x more powerful for all I care and I still wouldn't touch it with a 10ft pole. Most frustrating experience I ever had.
"Setting up LLMs to output structured data is incredibly hard." resonated strongly with my experience working in similar one-off projects. I've almost always implemented some level of fuzzy-matching to validate and convert the LLM output back into my expected structured format. I've also noticed that the LLMs are much better at writing code than structured JSON (no real surprise given the popularity of code assistant…
"Setting up LLMs to output structured data is incredibly hard." resonated strongly with my experience working in similar one-off projects. I've almost always implemented some level of fuzzy-matching to validate and convert the LLM output back into my expected structured format. I've also noticed that the LLMs are much better at writing code than structured JSON (no real surprise given the popularity of code assistant…
I have a 7000 token prompt that generates JSON chugging away in production and at scale I'm seeing ~1 in 4000 generations require a re-generation, and even that could probably be killed with some basic "healing" code.
OSS are prone to outputting garbage in my experience, but OP mentions ChatGPT:
How are you running into issues if you simply prefill the response with ```json and set ``` as your stop token?
Also, are people also just not trying to parse the opening and closing bracket and treating it as broken if there's a preamble? The prefill gets rid of the preamble, but if you're not willing/able to prefill, how hard is getting JSON out of a string?