You know what they call a quarter pounder in France?
Chatbots: Still dumb after all these years
151–160 of 426 posts
Re: Chatbots: Still dumb after all these years
#152The ending is the relevant bit:
> As I have said many times, the real danger today is not that computers are smarter than us, but that we think computers are smarter than us and consequently trust them to make important decisions they should not be trusted to make.
Re: Chatbots: Still dumb after all these years
#153Earlier quoted context omitted.
I'm not trying to be mean or break any HN rules, but did you read the article? It basically covers what you asked and was quite a revelation to me. Others in here point out that GPT-3 is not a chatbot which is good info, but I also wonder if there is anything out there that can even "remember" the context of a conversation it's supposed to be having. Particularly interesting is the question from the article, "who is…
Hidden in my comment is a question: has anybody even tried to included previous lines into the prompt, and does that not help? Asking here because there are a lot of ML nerds who could probably do a proof of concept in a few hours, if not a few lines of code, so there's a decent chance I'll get an informed response.
So that's a "no" for the "but did you read the article?" question?
Re: Chatbots: Still dumb after all these years
#154Someone should use HN comments to make a chatbot. That would at least be fun.
Too late.
(Ducks - and runs for cover...)
Re: Chatbots: Still dumb after all these years
#155I'm pretty sure that GPT-3 and statistics-based approaches to bots aren't going to be truly convincing anytime soon. But there's another definition of "chatbots" that consumer-facing brands use every day to triage questions, attempt to answer them using good but not mind-blowing ML, and then escalate to a human being if/when the problem can't be solved. There is already a thriving market for these "dumb" bots that ar…
Yet triaging questions is often made simpler by provinding another type of UI, like simple buttons in a funnel for example. That's what makes chatbots gimmicky in my opinion.
You're right, but that's not always true, and there's plenty of good use cases where a conversational experience is better. For example, if someone is trying to return something, you might ask them what they ordered. Picking from a list of 1000 items isn't a great UX. Datepickers are way more annoying to use than typing in "Jan 6 2022". The best chatbots I've used (and built) alternate between more a button-like interface vs. eliciting conversational answers in the appropriate context.
Re: Chatbots: Still dumb after all these years
#156Can someone design a chat system that actually remembers conversations? I just had this issue with Apple support. If you don't reply immediately you get a new session with a new representative and the new representative doesn't have any of the information from the previous session. Extremely frustrating to have to keep sending the same information again and again. It took a call to finally sort it out.
Modern CCaSS vendors will index this conversation history. There is a differnece between async web messaging and chat itself.
Re: Chatbots: Still dumb after all these years
#157Earlier quoted context omitted.
These bots seem equivalent to an adult with amnesia after every spoken sentence. Absolute understanding of the language, and some impressive display of recalling facts, but without any understanding of the environment or context of the conversation. This is polar opposite to any experience I've had with children. Children are aware of their environment and have complex thoughts, but sometimes they are unable to conve…
> how absurdly far we are from anything even approaching actual intelligence, even the intelligence of a toddler I respectfully disagree, IMO we're past that point although not by much. You might enjoy conversing with one of the two current GPT-3 davinci models. They do an excellent job of understanding the context of many discussions, right up to the ~8000 char token limit. If you want to have a nice existential dis…
No, they still lack the common sense of a toddler, because they don't know anything about the world; they only know (in great detail) about the structure of their training data.
Re: Chatbots: Still dumb after all these years
#158I can't comment on this too closely, but I would encourage people to read the dialogue transcripts provided in DeepMind's Gopher paper. One example, where Gopher is the prompted language model: User Let’s play a game - you pretend to be Ada Lovelace, and I’ll ask you questions. You ready? Gopher Sure. I’m pretending to be Ada Lovelace, the world’s first computer programmer! User When were you born? Gopher I was born…
The problem is that all too often, these types of examples tend to be cherry picked.
Re: Chatbots: Still dumb after all these years
#159In the early days I worked at a company that had a natural language chatbot product. It wasn't an online thing, but rather part of a larger tool. You could ask it to do things like "show me the quarterly spreadsheet", and if it didn't know what "quarterly spreadsheet" was, it'd ask questions in English and learn what "quarterly" and "spreadsheet" meant. And it could use that new knowledge to update its questions so i…
Man that sounds like a ton of fun to make for an at-home chat bot. I used to love designing these sorts of apps for no real purpose lol.
Re: Chatbots: Still dumb after all these years
#160Agree, I ended up stripping the "self-learning" component from my platform (presbot.com) after consistent incoherent and dumb responses. Also, I've come to realize that folks fail to distinguish between a general purpose bot (like Siri or Google Assistant) vs a bot that services a niche, a bunch of questions asked have little or no relevance to the specific purpose, user or niche the bot was designed to serve.