News for hackers. Stuff that matters.
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by throwaway2037 on Monday May 26, 2025 @06:02AM (#44095791)
Before I started using advanced IDEs that could navigate project structures very quickly, it was normal to have a relatively poor visibility -- call it "fog of war/code". In a 500,000 line C++ project (I have seen a few in my career), as a junior dev, I might only understand a few thousand lines from a few files I have studied. And, I had very little idea of the overall architecture. I see LLMs here as a big opportunity. I assume that most huge software projects developed by non-tech companies look pretty similar -- organic, and poorly documented and tested.
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by markus_zhang on Monday May 26, 2025 @06:33AM (#44095981)
What do you think about software such as source insight that gives developers an eagle eye of view of the project?
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by throwaway2037 on Monday May 26, 2025 @12:58PM (#44099214)
You raise a good point. I had a former teammate who swore by Source Insight. To repeat myself, I wrote: <<Before I started using advanced IDEs that could navigate project structures very quickly>>. So, I was really talking about my life before I started using advanced IDEs. It was so hard to get a good grasp of a project and navigate quickly.
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by markus_zhang on Tuesday May 27, 2025 @07:01AM (#44105725)
This makes sense.
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by guappa on Monday May 26, 2025 @09:30AM (#44097274)
That's what documentation is for. If you don't have that, AI won't figure it out either.
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by jrochkind1 on Monday May 26, 2025 @11:01PM (#44103599)
I'm not sure that's true?
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by guappa on Tuesday May 27, 2025 @02:19AM (#44104369)
Such a project is way too large for AI to process as a whole. So yes it's true.
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by throwaway2037 on Tuesday May 27, 2025 @04:37AM (#44105038)
I have a question: Many people have spoken about their experience of using LLMs to summarise long, complex PDFs. I am so ignorant on this matter. What is so different about reading a long PDF vs reading a large source base? Or can a modern LLM handle, say, 100 pages, but 10,000 pages is way too much? What happens to an LLM that tries to read 10,000 pages and summarise it? Is the summary rubbish?
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by guappa on Tuesday May 27, 2025 @05:35AM (#44105343)
It can't handle large contexts, so the way they often do it is file by file, which loses the overall context.
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by randomjoe2 on Wednesday May 28, 2025 @05:17PM (#44120761)
Lots of models CAN handle large contexts, gemini 2.5 pro their latest model can take 1 million tokens of context
Re:At Amazon, Some Coders Say Their Jobs Have Begun to Resem... by srazzaque on Wednesday May 28, 2025 @08:09AM (#44115109)
Get the LLM to read and summarise N pages at a time, and store the outputs. Then, you concatenate those outputs into one "super summary" and use _that_ as context.

Theres some fidelity loss but it works for text, because there's quite often so much redundancy.

However, I'm not sure this technique could work on code.