Wasn't me but I think the principle is straightforward. When you get an answer that wasn't what you want and you might respond, "no, I want the answer to be shorter and in German", instead start a new chat, copy-paste the original prompt, and add "Please respond in German and limit the answer to half a page." (or just edit the prompt if your UI allows it)
Depending on how much you know about LLMs, this might seem wasteful but it is in fact more efficient and will save you money if you pay by the token.
In most tools there is no need to cut-n-paste, just click small edit icon next to the prompt, edit and resubmit. Boom, old answer is discarded, new answer is generated.
I feel quite comfortable in Excel - used various tools like Power Pivot, Power Query, OLEDB, created my own functions, Python within Excel, etc. - but Airtable felt so confusing and limiting. Other former colleagues also struggled with Airtable; maybe it was not explained to us correctly.
I only started working on it on Saturday, so nothing very useful yet. It's at https://www.askhuxley.com/ and I want to focus on making something really useful instead of on monetization, so you'll have to bring your own API key, but I'd love it if you wanted to bounce some ideas and use cases off each other. I know what things are useful to me, but I don't know what's useful to other people, and I'd love to get new ideas.
Feel free to email me (email in profile) if you'd like to try it out. Right now it only does weather and Google Calendar, but adding new integrations is easy and the interesting thing is the fact that it can learn from you, and will behave like a PA would, while also being proactive and messaging you without you having to message it first.
I did make a prototype a while ago, which I integrated with a hardware device, and that was extremely useful, being able to do things by me teaching it. For example, it only had access to my calendar and its memories, but I told it (in chat) to check for and notify me of conflicts before adding an event, and told it the usual times of some events, so then I'd say "I'm playing D&D on Thursday" and it would reply with "you can't, you have an appointment at 8PM". This sounds simple for a human, but the LLM had to already know what time D&D was, that it's something I can't do during appointments, and that I wanted to be informed of conflicts, which are all things that I didn't have to program, but just instructed the LLM to do.
* Evading corporate IT: I do not recommend doing this.
* Normal[0] remote access to a machine: Yeah, running a remote desktop in software on the machine[1] is almost always going to be easier, cheaper, more performant, and more flexible than anything you tack on externally.
[0] Where "normal" remote access means it doesn't need to work when the machine is kernel panicked or in the firmware setup screens.
[1] The machine itself can be whatever you want. It can be an always-on desktop, but it can also be a laptop that sits in the corner and that only boots up when you poke it with a Wake-on-LAN packet, or a VM on an ESXi cluster, or a (carefully secured) Hetzner Cloud VM. That part is dealer's choice depending on your needs.
