←back to thread

GitHub CEO: manual coding remains key despite AI boom

(www.techinasia.com)
358 points andrewstetsenko | 10 comments | 23 Jun 25 20:50 UTC | HN request time: 0.437s | source | bottom
Show context
taysix ◴[23 Jun 25 22:23 UTC] No.44360808[source]▶
I had a fun result the other day from Claude. I opened a script in Zed and asked it to "fix the error on line 71". Claude happily went and fixed the error on line 91....

1. There was no error on line 91, it did some inconsequential formatting on that line 2. More importantly, it just ignored the very specific line I told it to go to. It's like I was playing telephone with the LLM which felt so strange with text-based communication.

This was me trying to get better at using the LLM while coding and seeing if I could "one-shot" some very simple things. Of course me doing this _very_ tiny fix myself would have been faster. Just felt weird and reinforces this idea that the LLM isn't actually thinking at all.

replies(4): >>44360819 #>>44360879 #>>44360917 #>>44363593 #
1. toephu2 ◴[23 Jun 25 22:38 UTC] No.44360917[source]▶
Sounds like operator error to me.

You need to give LLMs context. Line number isn't good context.

replies(3): >>44361316 #>>44364260 #>>44365210 #
2. meepmorp ◴[23 Jun 25 23:34 UTC] No.44361316[source]▶
> Line number isn't good context.

a line number is plenty of context - it's directly translatable into a range of bytes/characters in the file

replies(2): >>44361838 #>>44362459 #
3. mediaman ◴[24 Jun 25 00:58 UTC] No.44361838[source]▶
It's a tool. It's not a human. A line number works great for humans. Today, they're terrible for LLMs.

I can choose to use a screwdriver to hammer in a nail and complain about how useless screwdrivers are. Or I can realize when and how to use it.

We (including marketing & execs) have made a huge mistake in anthropomorphizing these things, because then we stop treating them like tools that have specific use cases to be used in certain ways, and more like smart humans that don't need that.

Maybe one day they'll be there, but today they are screwdrivers. That doesn't make them useless.

replies(1): >>44363016 #
4. nprateem ◴[24 Jun 25 02:48 UTC] No.44362459[source]▶
...which LLMs don't use as they use tokens instead.
replies(1): >>44364266 #
5. skydhash ◴[24 Jun 25 05:13 UTC] No.44363016{3}[source]▶
Check the whole ecosystem around editors, grep tools, debuggers, linting and build tools. One common thing about all of this is line (and column) number so you can integrate them together if you want to automate stuff. Like jumping to errors (quickfix in vim,…), search all files and jump to the occurrences (grep mode in emacs,…), etc…
6. oneeyedpigeon ◴[24 Jun 25 09:18 UTC] No.44364260[source]▶
Of all the things I thought I'd read today, "Line number isn't good context" is more wild than I could possibly have imagined.
replies(1): >>44383060 #
7. oneeyedpigeon ◴[24 Jun 25 09:19 UTC] No.44364266{3}[source]▶
So do compilers, and they don't seem to have a problem with something as basic as line numbers.
8. rs186 ◴[24 Jun 25 12:00 UTC] No.44365210[source]▶
Imagine saying to another software engineer "you only gave me the line number, that's not enough context"
replies(1): >>44368575 #
9. 1718627440 ◴[24 Jun 25 17:26 UTC] No.44368575[source]▶
You need at least also the version and the filename.
10. ThunderSizzle ◴[26 Jun 25 00:19 UTC] No.44383060[source]▶
Line numbers are perfect for humans and programs reading files, but LLMs aren't really reading files.