News for hackers. Stuff that matters.
Re:GitHub Copilot: The Agent Awakens by dabinat on Thursday February 06, 2025 @12:40PM (#42964636)
I use Copilot and it’s a game-changer for my productivity, but I really wish it was capable of natural language searching. So for example I could ask it “show me all places in the code where x is assigned a value but a flush() command is not immediately issued afterwards”.
Re:GitHub Copilot: The Agent Awakens by simonw on Thursday February 06, 2025 @01:58PM (#42965353)
I answer those kinds of questions by piping my entire codebase into a large context model (like Claude or o3-mini or Gemini) and prompting it directly.

Here's a recent example:

    files-to-prompt datasette tests -e py -c | \
      llm -m gemini-2.0-flash-exp -u \
      'which of these files contain tests that indirectly exercise the label_column_for_table() function'
https://gist.github.com/simonw/bee455c41d463abc6282a5c9c132c...
Re:GitHub Copilot: The Agent Awakens by dplgk on Thursday February 06, 2025 @10:13PM (#42968880)
Your code is pretty small if it fits within the context if any major LLM. But very nice if it does!
Re:GitHub Copilot: The Agent Awakens by singularity2001 on Friday February 07, 2025 @04:11AM (#42970782)
doesn't it get very expensive quickly if you don't use prompt cashing
Re:GitHub Copilot: The Agent Awakens by simonw on Friday February 07, 2025 @07:43PM (#42979210)
I've had the occasional large prompt that cost ~30c - I often use GPT-4o mini if I'm going to ask follow-up questions because then I get prompt caching without having to configure it.
Re:GitHub Copilot: The Agent Awakens by mohsen1 on Friday February 07, 2025 @04:50AM (#42970993)
https://github.com/bodo-run/yek

This is more sophisticated for serializing your repo. Please check it out and let me know what do you think?

Re:GitHub Copilot: The Agent Awakens by blah2244 on Saturday February 08, 2025 @11:57AM (#42984261)
Yek is fantastic -- I've converted my whole team to using it for prompting. As input context windows keep increasing, I think it'll just keep becoming more and more valuable -- I can put most of my team's code in Gemini 2.0 now.
Re:GitHub Copilot: The Agent Awakens by skydhash on Thursday February 06, 2025 @02:51PM (#42965854)
> So for example I could ask it “show me all places in the code where x is assigned a value but a flush() command is not immediately issued afterwards”.

Could this not work? (with wathever flag to display the surrounding lines)

  ripgrep 'x =' | ripgrep 'flush()'
Re:GitHub Copilot: The Agent Awakens by jgilias on Thursday February 06, 2025 @12:46PM (#42964674)
I think Cursor can do this, if you @codebase, isn’t there something similar in copilot? E.g., your codebase being vectorized, indexed, and used as an embedding?
Re:GitHub Copilot: The Agent Awakens by shaneofalltrad on Thursday February 06, 2025 @01:16PM (#42964961)
I have had Cursor review all my file content solving similar things, but I would think it's limited to VSCode search capabilities and IMHO it's not great. I love how Pycharm handles indexing so search is fast and accurate. If they ever get agents going at the same quality as Cursor I would probably go to Pycharm for that advantage alone.
Re:GitHub Copilot: The Agent Awakens by wrs on Thursday February 06, 2025 @02:15PM (#42965512)
Cursor implemented their own code indexer so its RAG is not limited by VS Code search.