I’m on the fence.
I’ve used Perplexity to take a javascript fragment, identify the language it was written in and describe what it’s doing. I then asked it to refactor it into something a human could understand. It nailed both of these, even the variable names were meaningful (the original ones were just single letters). I then asked it to port it to C and use SDL, which it did a pretty good job of.
I also used it to “untangle” some really gnarly mathy Javascript and port it to C so I could better understand it. That is still a work in progress and I don’t know enough math to know if it’s doing a good job or not, but it’ll give me some ability to work with the codebase.
I’ve also used it to create some nice helper python scripts like pulling all repositories from a github user account or using YouTube’s API to pull the video title and author data if given a URL. It also wrote the skeleton of some Python scripts which interact with a RESTful API. These kinds of things it excelled at.
My most recent success was using it to decode DTMF in a .WAV file, then create a new .WAV file using the DTMF start/end times to create cue points to visually show me what it saw and where. This was a mixed bag: I started out with Python, it used FFT (which was the obvious but wrong choice), then I had it implement a Goertzel filter which it did flawlessly. It even ported over to C without any real trouble. Where it utterly failed was with the WAV file creation/cue points. Part of this is because cue points are rather poorly described in any RIFF documentation, the python wrapper for the C wave processing library was incomplete and even then, various audio editors wanting the cue data in different ways, but this didn’t stop the LLM from lying through its damn teeth about not only knowing how to implement it, but assure me that the slop it created functioned as expected.
I’ve found that it tends to come apart at the seams with longer sessions. When its answers start being nonsensical I sometimes get a bit of benefit from starting over without all the work leading up to that point. LLMs are really good at churning out basic frameworks which aren’t exactly difficult but can be tedious. I then take this skeleton and start hanging the meat on it, occasionally getting help from the LLM but usually that’s the stuff I need to think about and implement. I find that this is where LLMs really struggle, and I waste more time trying to explain what I want to the LLM than if I just wrote it myself.
A couple things I’ve been working on
First, I spun up a larger VPS to consolidate two smaller ones. This time I dockerized almost everything. Still a docker newb, but karakeep, redmine, mbin, lemmy (still deciding which I want), davical. Asterisk and postfix/dovecot are probably gonna stay on the vps root. I’m using zfs and compression. Interestingly, the postgres database that everything is using seems to get better compression than the mail spool.
A couple weeks ago I picked up a NetApp 7 bay disk shelf for $30. It uses fibre channel (AT-FCX) controllers and I’ve never used that before. I grabbed a $7 FC HBA (QLE2560), a 2m cable and an m2-to-PCIe adapter meant for an eGPU. The idea is to see if I can’t get the RK3588 board I’m playing with to see it. I did something similar with a $50 Dell 12 drive bay and my old C6100.