What is the difference between an AI chatbot and a non-AI chatbot in this context?
“AI” = Stuff like ChatGPT that use Large Language Models (LLM)
“Non-AI” = Bots that don’t use LLMs.
So without hardcoded I/O choice options à la 20 Questions, how is the latter supposed to function?
In this case, a simple chatbot like she interacted with falls under AI. AI companies have marketed AI as synonymous with genAI and especially transformer models like GPTs. However, AI as a field is split into two types: machine learning and non-machine-learning (traditional algorithms).
Where the latter starts gets kind of fuzzy, but think algorithms with hard-coded rules like traditional chess engines, video game NPCs, and simple rules-based chatbots. There’s no training data; a human is sitting down and manually programming the AI’s response to every input.
By an AI chatbot, she’d be referring to something like a large language model (LLM) – usually a GPT. That’s specifically a generative pretrained transformer – a type of transformer which is a deep learning model which is a subset of machine learning which is a type of AI (you don’t really need to know exactly what that means right now). By not needing hard-coded rules and instead being a highly parallelized and massive model trained on a gargantuan corpus of text data, it’ll be vastly better at its job of mimicking human behavior than a simple chatbot in 99.9% of cases.
TL;DR: What she’s seeing here technically is AI, just a very primitive form of an entirely different type that’s apparently super shitty at its job.
Is CleverBot still around, and as stupid as always?
Cleverbot is still around, but he’s got nothing on SmarterChild.
https://computerhistory.org/blog/smarterchild-a-chatbot-buddy-from-2001/
Oh, SmarterChild. Now that brings me back. I remember there being a slew of chatbots that followed it. I didn’t know what Radiohead was at the time, I learned about the band from them, and thought it odd they had their own chatbot.
Funny enough, Slackbot (or at least the current incarnation of it) is definitely based on an LLM. Although I suspect this screenshot is older, because when the current Slackbot gives bad responses it does so a lot more verbosely.
I’ve found it to usually work better than most AI, actually, at least if you ask it stuff like “which slack threads do I need to follow up on?” or other stuff it can work out based on your slack activity.
All chatbots are AI, from ELIZA to GPT4. Did you mean LLM-based, maybe?
Technically you can call a chain of three if/else conditions an AI but come on, you KNOW that’s not what we mean.
Best bot.
Slack does have AI features now, mostly focused around summarization. I found the features pretty useless and turned them off (as much as they allow you to, at least). It’s not very often that I don’t care to know the whole context of messages I receive at work. And I do have channels that I usually just skim or ignore that the summaries weren’t super helpful for. It strips out way too much of the conversation.
Similarly, I really dislike the Apple Intelligence summarization features. It drove me to finally turn off Apple Intelligence on all my devices. Do people find summarization useful? Genuinely curious for use cases.
HELLO?
I would ignore this poor slack (and general communication) etiquette myself.
