Hacker News Reader

Comment by latemedium | Hacker News Reader

My experience is starkly different. Today I used LLMs to:

1. Write python code for a new type of loss function I was considering

2. Perform lots of annoying CSV munging ("split this CSV into 4 equal parts", "convert paths in this column into absolute paths", "combine these and then split into 4 distinct subsets based on this field.." - they're great for that)

3. Expedite some basic shell operations like "generate softlinks for 100 randomly selected files in this directory"

4. Generate some summary plots of the data in the files I was working with

5. Not to mention extensive use in Cursor & GH Copilot

The tool (Claude 3.7 mostly, integrated with my shell so it can execute shell commands and run python locally) worked great in all cases. Yes I could've done most of it myself, but I personally hate CSV munging and bulk file manipulations and its super nice to delegate that stuff to an LLM agent

edit: formatting

View on HN

These seem like fine use cases: trivial boilerplate stuff you’d otherwise have to search for and then munge to fit your exact need. An LLM can often do both steps for you. If it doesn’t work, you’ll know immediately and you can probably figure out whether it’s a quick fix or if the LLM is completely off-base.

That’s fair but it’s totally different use cases than the linked post discusses.

The click baited title is “I genuinely don’t understand how some people are still bullish about LLM”.

I guess the author can understand now?

When something was impossible only 3 years ago, barely worked 2 years ago, but works well now, there are very good reasons to be bullish, I suppose?

The hypes cut both way.

> When something was impossible only 3 years ago, barely worked 2 years ago, but works well now

Are you talking of what exactly? What are you stating works well now and did not years ago? Claude as a milestone of code writing?

Also in that case, if there are current apparent successes coming from a realm of tentative responses, we would need proof that the unreliable has become reliable. The observer will say "they were tentative before, they often look tentative now, why should we think they will pass the threshold to a radical change".

How did you integrate Claude into your shell

Claude Code is available directly from Anthropic, but you have to request an invite as it's in "Research Preview"

There are third party tools that do the same, though

I hacked something together a while back - a hotkey toggles between standard terminal mode and LLM mode. LLM mode interacts with Claude, and has functions / tool calls to run shell commands, python code, web search, clipboard, and a few other things. For routine data science tasks it's been super useful. Claude 3.7 was a big step forward because it will often examine files before it begins manipulating them and double-checks that things were done correctly afterwards (without prompting!). For me this works a lot better than other shell-integration solutions like Warp

I wrote my own tool for that a while back as an LLM plugin, so I can do this:

    llm cmd extract first frame of movie.mp4 as a jpeg using ffmpeg

I use that all the time, it works really well (defaulting to GPT-4o-mini because it's so cheap, but it works with Claude too): https://simonwillison.net/2024/Mar/26/llm-cmd/

Reply on news.ycombinator.com