this post was submitted on 25 Jul 2023
299 points (100.0% liked)
Technology
37737 readers
711 users here now
A nice place to discuss rumors, happenings, innovations, and challenges in the technology sphere. We also welcome discussions on the intersections of technology and society. If it’s technological news or discussion of technology, it probably belongs here.
Remember the overriding ethos on Beehaw: Be(e) Nice. Each user you encounter here is a person, and should be treated with kindness (even if they’re wrong, or use a Linux distro you don’t like). Personal attacks will not be tolerated.
Subcommunities on Beehaw:
This community's icon was made by Aaron Schneider, under the CC-BY-NC-SA 4.0 license.
founded 2 years ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I get that too drom Bard sometimes, but it is for specific queries. I think the key is working on the prompt until it gets it. Sometimes you need to start over with a new chat.
Bing does not work like ChatGPT despite having the same base, even in creative mode. No idea why. However I like creative mode when I don't just dont want to see links embedded. I also love taking advantage of free Dall-E.
Bard is great for anything that can be put into a list or chart, like comparisons. Literally put in a chart.
I am dissapointed in that I have not been able to get a single mathematic equation produced (like famous ones), but I know they can?
If you get the chance and willing to download a full ass browser, Opera has Aria, which is like the cleanest version of ChatGPT I have seen. Just the formatted answers with hyperlinks are worth it. It is good. It is hard to explain, but Aria mostly just works. It is closer to Bard in responses, and does what you want out of Bing without messing with convo styles.
Whatever prompts that Bing put for the convo style may be messing with the results.
All things said, I switch between them often, depending on my needs. It takes some time but I have built my intuition of which one will give the best response for the prompt, but I often just search the prompt in all of them.
Anyways, I hope you find more success using them!
Well, my understanding is that they actually can't. LLM's do "language" mostly based on what is called "next word prediction" so they basically look at the word and predict what the next most logical word would be. (Somewhat simplified). So numbers to them are not numbers but words, which is why they are fairly bad at them.
Pass, not sure what stake the chinese owners have these days but Opera is a bit too.... feature rich in everything.
I do like working with just chat.openai.com for simple stuff. It is great at helping my debug things in areas I don't quite have all the knowledge I'd like. For example, I had to work on a shell script earlier in bash. Something I don't do often and as an added bonus it needed to work on both macOS machines and the bash version shipped with "git bash" on windows. MacOS GNU utils already function slightly differently at times, but git bash on windows is entirely broken in some areas. Where yesterday I spend an hour trying to find something relevant based on my input and the error I got through google chatGPT just managed to point out the pain point right away.
And that is where I feel chatGPT (in this case anyway) does a great job, troubleshooting issues about things that are not necessarily bleeding edge. I just presented it with a clear problem and a bit of context and asked why that could be the case. It also got it wrong a few times, but that is fine, it did safe me a bunch of time in the end.
For sure that is a limitation of an LLM. I was hoping the capabilities of Google or Bing would overcome that with extended formatting.
I am ignorant of the ownership of Opera, so I will reserve judgement. I will say that the browser is great, despite its problem foundation.
That is an awesome usecase. ChatGPT lets you get niche and weird, which isnwhere it is most productive.
ChatGPT has the issue that it has no date beyond September 2021, which is not typically an issue.