The one that the other department tried, and which failed to meet expectations dramatically. Gave management a healthy dose of reality on “AI”.

LLMs are pretty good for language learning. I often ask ChatGPT to converse with me in Japanese or help me make a sentence sound more natural.

I use it to create funny shitpost copypasta-like outputs that I send to my friends in our personal group chats. Otherwise it’s fucking useless.

Those that I find the most useful are those that I (and likely many others) tend to take for granted.

For example, fuzzy logic may very well be used in electronics that involve temperature control - fridge, aircon, rice cooker, water heater - under the hood.

Another one is CSP (constraint-satisfaction problems) solvers which tend to be used in scheduling softwares. A possible use case is public transportation.

There are probably lots more AIs working behind the scenes that benefit everyone, but don’t get the coverage because they are just boring tech now. People may not even consider them AI!

I appreciate these AI for making my life so convenient.

I chat with llm’s to help me remember shit I already know, or to change the tone of stuff I write but thats about it.

The only thing that comes to mind is I wanted to make a shell script that moved every file in a directory to another directory, but one at a time, slowly, and I didn’t want to learn sh from scratch, so I asked an LLM for a script that would do it.

The script didn’t work, but I was able to figure out how to fix it better than write it from scratch.

I felt bad for the environment I was destroying, and I would never pay for this shit.

I tried Whisper+ voice-to-text this week.

Uses a downloaded 250MB model from Hugging-Face, and processes voice completely offline.

The accuracy is 100% for known words, so far.

For transcribing texts, messages and diary entries.

* I’d be interested to know if it has a large power drain per use.

I use ChatGPT every single day, and I find it both extremely useful and entertaining.

I mainly use it to help edit longer messages, bounce ideas around, and share random thoughts I know my friends wouldn’t be interested in. Honestly, it also has pretty much replaced Google for me.

I basically think of it as a friend who’s really knowledgeable across a wide range of topics, excellent at writing, and far more civil than most people I run into online - but who’s also a bit delusional at times and occasionally talks out of their ass, which is why I can’t ever fully trust it. That said, it’s still a great first stop when I’m trying to solve a problem.

I’ve been self-hosting my own AI stuff for a bit using Ollama. I use it to create images, design a tattoo, run a chatbot, write emails, write code and commit-messages, run a D&D game, explain concepts that I’m not familiar with, translate languages, etc.

I’ve been toying with different models, and I’m not sure that I have one that I would say is a goto. I am liking Ollama to be able to easily pull in and test new LLMs, as well as Stable-Diffusion for image generation/modification.

My CRM system at work has what called “Genius AI” integrated into it. When customer service reps receive calls that require site visits the AI auto fills the work ticket using the phone conversation adds in contact name and numbers and even puts a brief description of what service they require. The AI also transcribes our calls into text to be able to refer back to or get caught up on a job when someone is out sick. It wasnt Iife changing it wasnt forced but as a simple aid it makes life a bit easier.

I think I’ve found the one area where LLMs really excel: business books / self help literature. The real life examples in that genre are pretty awful and dragged out as it is, so you can’t really make it much worse, now can you? The information density is kept low to fluff up the page count, and oh boy, are LLMs good at that. So, if you want to become a self help guru, but can’t be bothered to write your own book about magical hotels, marriage advice, productivity tips and communication, LLMs can take care of that for you. Copilot has turned out to work well for projects like that.

If you raise the bar, you’re going to have to read and edit the text manually. You also need to keep track of what has already been mentioned elsewhere and avoid repeating them again, depending on the genre. In business books though, that’s not a problem at all.

BTW, if you wonder about the downvotes, it’s because [email protected] isn’t a safe space for AI related discussions. Consider posting somewhere else.

Supermaven code autocomplete in vscode is really nice

“AI” as in the hyped and since 5 years mainstream “Generative AI”: Jetbrains’ locally run code line completion. Sometimes faster than writing, if you have enough context.

Machine learning stuff that existed well before, but there was exactly 0 hype: Image tagging/face detection.

https://notebooklm.google.com/ is really handy for various things, you can throw a bunch of documents into it and then ask questions and chat interactively about their contents. I’ve got a notebook for a roleplaying campaign I’m running where I’ve thrown the various sourcebook PDFs, as well as the “setting bible” for my homebrew campaign, and even transcripts of the actual sessions. I can ask it what happened in previous episodes that I might have forgotten, or to come up with stats for whatever monster I might need off the cuff, or questions about how the rules work.

Copilot has been a fantastic programming buddy. For those going a little more in depth who don’t want to spring for a full blown GitHub Copilot subscription and Visual Studio integration, there’s https://voideditor.com/ - I’ve hooked it up to the free Gemini APIs and it works great, though it runs out of tokens pretty quickly if you use it heavily.