researcher VS tortoisegit

In this particular case (summarizing search results), it seems to work well. I think anchoring to known information helps avoid a lot of the issues (hallucinations, boring language, etc).

You can check out an open source demo I made if you want to play around with how search + GPT work - https://github.com/VikParuchuri/researcher .

I've had the exact same problem, and have experimented with Kagi, DDG, etc, to try to find better results.

ChatGPT, in my opinion, is great for "how do I code X" type questions, but isn't so good at the types of queries you mentioned, due to the lack of a search engine.

My weekend project was an open source combination of Google + GPT that returns pretty good results for these types of queries. You can check it out here - https://github.com/VikParuchuri/researcher

Example - the response to "what are the best current smartphones" is:

`...According to Search Result [2], the best phones have been thoroughly reviewed and tested, and include the Apple iPhone 14 and 14 Pro, the Pixel 7 Pro and the Samsung Galaxy S22 Ultra. Search Result [5] also states that there are strong options available at all price levels, so you don't have to spend a lot to get something great...`

This is very cool! It's nice to see other implementations outside of ChatGPT.

I noticed that it doesn't always cite sources, so I assume that some results are coming straight from an LLM, and some are web search + LLM.

If you're always looking for sources to be cited, I built a project this weekend that will summarize a topic and cite sources - https://github.com/VikParuchuri/researcher . It's definitely slower than this implementation, but it is self-hosted and hackable.

I don't think it's a huge lift to restrict a language model to "known" good facts from search results. And to have it cite sources.

I made a proof of concept this weekend - https://github.com/VikParuchuri/researcher . There are some issues, but it's very useful.

I built a side project recently to help with this. It searches Google, then feeds the relevant results from the pages into GPT-3 to get a summary. It seems to be accurate so far in my testing - https://github.com/VikParuchuri/researcher .

There is also a TortoiseGit that is based on TortoiseSVN

https://en.wikipedia.org/wiki/TortoiseGit

https://tortoisegit.org/

TortoiseGit sourcetree git kraken some times you need to compare to files you can do this with the notpad++ compare plugin or with Meld

Instead on my PC I use TortoiseGit. Most useful for the git log (as a graph), diff with previous versions,, filter files to commit by directory and ability to exclude files from the current commit, and most of all; ease of splitting a commit for each single file into parts by ability to "restore after commit" which allows you to edit a file before the commit and have it automatically restored to the pre-commit state afterwards.

If running TeXStudio in Windows, my personal preference is to keep the automatic check-in disabled and to use the manual one (File -> SVN/git -> Check in); this allows an individual commit message with the briefer abstract line, empty line, and the longer report. Perhaps it is less exhaustive then a proper git client (in Windows e.g., tortoise), yet TeXStudio' GUI and integrated version control allows to resolve many typical situations. The developers document as advanced use; heck, after some time, it becomes second nature. In case of missing git-related functionality, you still can opt for an other git GUI or for git from the command line independent of TeXStudio's choice.

> We now have a large selection of tools that allow you to visualize what's going on (I use git-kraken), as well as google for help on doing something that isn't in muscle memory.

Git Kraken is excellent, though Git has a page on various GUIs, many of which are free with no restrictions: https://git-scm.com/downloads/guis

Personally, on Windows I like SourceTree: https://www.sourcetreeapp.com/

Some that have worked with SVN back in the day like TortoiseGit: https://tortoisegit.org/

On *nix Git Cola seems to do the job for me: https://git-cola.github.io/

Then again, the most complex workflow I've worked with was Git Flow and I didn't need anything more advanced than that. Come to think of it, I don't really do rebases often either and mostly just take advantage of squashing commits through GitLab/Gitea and such, when needed.

But hey, that's also valid, using Git in a way where you get version control but mostly keep the technical details out of your way (though Git LFS and certain cases with particular line endings being needed does make you drop down occasionally).

The method to add the illustration to git, either from the command line, or via a GUI (for example TortoiseGit) should not have an influence how the image is managed by git itself. There is no "watermark" like stamp on the picture from which you later could tell if the picture, or the edit on the picture was committed from the CLI, or e.g., tortoise, either.

I started with TortoiseGit (coming from TortoiseSVN), then used SourceTree for a while (until Atlassian broke it. I hear it is better now), but I’ve settled in GitKraken for my work stuff where I need to maintain full histories while ping-ponging code features between many branches. I’ve heard great things about GitTower too.