I use GitHub Copilot very frequently for any programming I do.
I also use BingChat very often, I consider it to be a very underrated tool that people haven't fully explored. Of course, it's great for when you want your LLM queries augmented with search results. But BingChat can also view the current webpage, so for example you can pull up papers and ask BingChat questions about it. I've used it to help write abstracts for my papers. When I do this, BingChat literally searches up "how to write an abstract" which I found absolutely hilarious , it's like it's learning skills on the go as well. I didn't use the outputs directly, but it served as useful inspiration. I think BingChat uses a mix of models including GPT-4, all for free! Apparently more features are coming soon, including multimodal features.
Why do you think Bing chat has been under-utilized? I also don’t find myself reaching to it as often even though the few times I’ve used it I have been impressed.
I have noticed that Notion having a built-in AI assistant helps with writing because I hardly ever use something generated verbatim — so it’s easier to be in an interface that is editable.
Perplexity is also good for saving and sharing different queries.
Adobe's experimental Photoshop features have been a game-changer for me. We write a lot of stories on our blog profiling successful founders.
But a lot of them don't have high quality horizontal photos I can use as a blog header.
They've got great vertical photos. But getting horizontal that worked well with LI/Twitter preview was a huge drag. Now, I can just take their vertical photos, and use generative fill to extend the canvas out to horizontal.
Super easy, and very nice, high-quality output. It's wild.
- Perplexity ai. I tried to work with Bing but this isn't a tool to rely on, it straight out refuses to answer a question or it removes the answer midway. I discovered Perplexity AI, purchased pro (ChatGPT Pro doesn't accept any of my credit cards here), and it's also a part of my workflow now.
I've set up several models on Runpod and played around with them.
I generated my side projects logo with Stable Diffusion with an "anime art" style model and it got pretty good results. I generated about 20 logos from that then picked the best one.
Generally, Bard is far superior when it comes to querying the internet for raw information - ChatGPT excels at prose / written content that sounds more human and less robotic.
I also use BingChat very often, I consider it to be a very underrated tool that people haven't fully explored. Of course, it's great for when you want your LLM queries augmented with search results. But BingChat can also view the current webpage, so for example you can pull up papers and ask BingChat questions about it. I've used it to help write abstracts for my papers. When I do this, BingChat literally searches up "how to write an abstract" which I found absolutely hilarious , it's like it's learning skills on the go as well. I didn't use the outputs directly, but it served as useful inspiration. I think BingChat uses a mix of models including GPT-4, all for free! Apparently more features are coming soon, including multimodal features.