Show HN: GPT Repo Loader – load entire code repos into GPT prompts

Re:Show HN: GPT Repo Loader – load entire code repos into GP... by ozfive on Friday March 17, 2023 @01:17AM (#35193438)

Here is what GPT-4 says about it. "As an AI language model, I can understand and work with various text encoding schemes and compression algorithms. However, to work with a raw bytestream, you would need to provide specific details about the encoding and compression used.

To teach me to understand a particular binary encoding and compressed text format, you should provide the following information:

The binary encoding used (e.g., ASCII, UTF-8, UTF-16, etc.). The compression algorithm employed (e.g., gzip, Lempel-Ziv-Welch (LZW), Huffman coding, etc.). Once you provide these details, I can help you process the raw bytestream and decompress the text. However, keep in mind that my primary focus is on natural language understanding and generation, and I might not be as efficient at handling compressed data as a dedicated compression/decompression tool."

[ Parent | on HN ]

Re:Show HN: GPT Repo Loader – load entire code repos into GP... by tablatom on Friday March 17, 2023 @04:30AM (#35194596)

When GPT gives an answer like that, is it actually a meaningful description of its capabilities? Does it have that kind of self-awareness? Or is it just a plausible answer based on the training corpus?

Genuine question.

[ Parent | on HN ]

Re:Show HN: GPT Repo Loader – load entire code repos into GP... by Olphs on Friday March 17, 2023 @07:56AM (#35195848)

My guess is that the training data includes things specifically about the GPT itself and its capabilities, so it would be somewhat correct. But it's also known to just make shit up when it feels like it, so you can't 100% trust it, same as with all other prompts/responses.

[ Parent | on HN ]