Since Bart is now available in Europe I have both options now and problem of choice :) People who have access to both for a while, what AI tool do you mostly use?
You must log in or register to comment.
Removed by mod
Both have option to turn off history saving. In this case they keep dialog for a short time only.
Regarding glorified keyboard autocorrect… I see this a bit different.
Anyways, thanks for sharing your opinion.
Removed by mod
I already got that you do not found a use case - and this is fine. I asked for opinion of people who use these both tool and can compare
While I am generally inclined to agree with you, I do think AI is getting a bit more advanced than a glorified autocorrect. If you are interested in hearing some examples of cool things it is capable of I suggest listening to a recent episode of This American Life. https://www.thisamericanlife.org/803/greetings-people-of-earth Act One: First Contact is the section I am referring to
I’m guessing you haven’t used it for more than maybe a few minutes, if at all.
deleted by creator
This is a bit close minded and reductive when you can see a large number is examples where these tools beat the shit out of search engines, and search engines have been on a precipitous decline in quality for years now. Not talking shit; the privacy concerns are very valid and i dont think there is anything at all wrong with an anti-ai stance in these areas, I just don’t want novices reading this and thinking these tools are “glorified keyboard autocorrect” when some near version of them is undoubtedly the future of both internet search and internet assistant.
Not sure I fully agree. These tool are really ruddy brilliant at certain things (like writing or translating computer code, drafting certain documents) but they are poor at being factually correct. Unless / until they find a way to fact-check themselves I don’t see them replacing search, just complementing it.
ChatGPT. I avoid Google as much as possible.
Haven’t tried bard but use ChatGPT to write/debug scripts and SAP stuff. Also asking it when I have simple but technical questions.
I am also downloading and running the latest models in the local LLM space every 2-3 weeks, just waiting for the point at which they finally take over gpt3.5 at which point I’ll probably not touch ChatGPT again.
Which ones are your downloading and running?
Today I tried TheBloke/WizardLM-13B-V1-1-SuperHOT-8K-GGML in koboldcpp for a short bit but didn’t actually test the 8k context. I just love seeing them evolve and get a bit better every time I download a new one.
Interesting, thanks.
https://github.com/serge-chat/serge
The easiest to set up that I have found and it supports a large library of models. I can not say that I have had amazing results but it is a lot of fun to play with.
Tried both but honestly haven’t found much of a proper use for either.
I still don’t think it’s much more of a novelty. From what I’ve used it really feels like you can see the training data in all of the answers, which obviously, but like if I ask it to write a cover letter it feels like it’s some cover letter it trained on more than mine
It’s much better than novelty if you learn how to use it. I routinely use it to write scripts for Google apps scripts, bash, etc. I’m using it to help with rust libraries that don’t have much documentation. I’ve used it to research camera gear that I don’t know much about. And once you get some information from it you can then go Google. Google has gotten so bad lately that it’s not hard for ChatGPT to beat it though. If you’re using 3.5 I highly recommend stopping that nonsense though. There’s zero reason to use 3.5 and every reason to use 4.
I still use Google for ~95% of my queries because I like real sources, comprehensive documentation, and not having to read a wall of text when a one-line answer would have sufficed.
ChatGPT is a good replacement for Quora/Stack Exchange for explaining general knowledge stuff like other languages’ grammar and simple science, as well as finding authors/books/movies from descriptions when you’ve forgotten their names.
Bard is… kinda dumb. I gave it a few chances, but it was nothing compared to ChatGPT’s free tier.
Definitely agree that ChatGPT is often waaay too wordy.
ChatGPT is my programming rubber ducky for general stuff
I use bing mostly.
Ditto. I mostly use it when Google (search, not Bard) fails me. I find it’s really good at answering questions of the ilk: “I swear there’s a function for this in the library I’m using, what’s it called again?”, or telling me that it doesn’t actually exist.
Agreed. I find Bing chat is really good when I know almost nothing about what I’m searching, or when I know a whole lot about what I’m searching. Like in your example, if I know exactly what I need but can’t remember its name Bing will read all the spammy beginners’ guides for me and get the answer. And on the opposite end, if I’m looking to buy a gift in a hobby I don’t remotely understand Bing does a pretty good job of holding my hand through the search process.
Weirdly, medium knowledge questions seem to still do better as a basic Google search. If I need to fix an appliance I’ve fixed before, but it’s been a long time so I really need a full walkthrough, the first few results on Google are faster than waiting for Bing to talk through it.
I don’t have the time to find this right now but there was an example at launch where it very badly summarized pet vacuums or some such, giving blatantly incorrect information about them.
… Is a sentance I never thought I would read in a million years
bing chat is pretty great, not only do you get the benefits of search and gpt4 but also summarizing/answering questions on the webpage you have open or pdfs if you open them in edge. Only issue is that it is slower
Now are these companies stealing everything and possibly opening up a cesspit that their platforms will fall into? Absolutely. These tools are literally removing the ability for them to advertise because they are leading to less link traffic that would have google ads or otherwise and also the degradation of search tools… but by god its super useful for now
only real problem for me personally is that it gives low barrier to entry to ask about any question that pops in my ADHD brain, so I keep having more and more questions that never stop. Learning a lot tho
Having it do a search then summarize the content from the search in one step is really handy. Basically skips the step of regular search oping a bunch of the links looking for relevant info.
AND it provides the source / references so you can easily click and read the actual page the info came from.
Google’s built-in chatbot search “experiment” seems to do the same thing. It’s kind of neat.
Not available in Canada apparently (bard version)… however bing is…
You enable it here: https://labs.google.com/search/experiments (You may have already found this but just in case you didn’t.)
Ya on desktop it states it is not available in Canada, I am not seeing any option in the mobile app.
Fairly sure they have limited it to the US only.
It recently opened up to other countries, I’m just kind of surprised Canada wasn’t one of them.
Important: Currently, Search Labs is available to a limited number of people in the US and in English only.
From the FAQ / About page… I think they only opened it up to MORE in the US not other countries.
Just tried out Bard with what I thought was a not to exotic question.
It made up a feature for a library, then lied about when it was added, and finally conocted some imaginary source code for it.
It’s seriously a mystery for me how anyone gets a net benefit from using these LLMs when you have to second-guess literally everything they output.
I have found bard is pretty bad with code. I occasionally (for fun because I’m really pretty lame) pose the same coding-related questions I run into to both of them and at best they give comparable answers, but more often bard is either way less informative or just flat out wrong.
That’s not to say that ChatGPT hasn’t also been wrong, just that I’ve never seen Bard be correct when ChatGPT isn’t.
None, of course.
Neither because AI is bullshit
I use chatgpt for generating ideas for my DND campaign, and for coming up with examples of an idea that I can use as a jumping off point for software development.
Other than that the only LLM I use is GitHub copilot.
Same here, although since OpenAI disabled bing search I occasionally need Bing since it knows better about the new Godot 4.
I tried both with same question and found them both good. I’m not actively using them for now, but if they give the same results I’ll prioritize Bard. I hate Microsoft more than Google.
I’m having a play with the newly launched Claude.ai v2 rafter liking it so far.
Interesting, just trying this one out
Edit: Just noticed it’s not available outside of US and UK unfortunately
I recently got access to CoPilot. Writing tests was never so much fun. It still feels (!) a bit like magic. And it helps with the boring repetitive parts.
I find Phind.com quite useful as an IT person.
I have never heard about it. What are the benefits over generic chatGPT?