I’m a technical kinda guy, doing technical kinda stuff.

  • 0 Posts
  • 37 Comments
Joined 2 years ago
cake
Cake day: September 27th, 2023

help-circle





  • It straight made up a powershell module, and method call. Completely made up, non existent.

    Counterpoint 1:

    I gave Copilot a couple of XML files that described a map and a route, and told it to make a program in C# that could create artificial maps and routes using those as a guideline.

    After about 20 minutes of back and forth, mainly me describing what I wanted in the map (eg walls that were +/- 3m from the routes, points in the routes should be 1m apart, etc) it spat out a program that could successfully build xml files that worked in the real-world device that needed them.

    Counterpoint 2: I gave Copilot a python program that I’d written about 8 years ago that connected to a Mikrotik router using its vendor specific API and compiled some data to push out to websocket clients that connected. I told it to make a C# equivalent that could be installed and run as a windows service, and it created something that worked on the very first pass using third party .NET libraries for Mikrotik API access.

    Counterpoint 3: I had a SQL query in a PowerShell script that took some reporting data from a database and mangled it heavily to get shift-by-shift reports. Again I asked it to take the query and business logic from the script and create a command line C# application that could populate a new table with the shift report data. It created something that worked immediately and fixed a corner case in the query that was causing me some grumbles as well.

    These were things that I’ve done in the past month. Each one would have taken a week for me to do myself, and with some general discussion with this particular LLM each one took about an hour instead, with it giving me a complete zipped up project folder with multiple source files that I could just open in Visual Studio and press “build” to get what I want.

    In all these cases however, I was well versed in the area it was working in, and I knew how to phrase things precisely enough that it could generate something useful. It did try and tack on a lot of not-particularly-useful things, particularly options for the command line reporting program.

    And I HATE the oh-so-agreeable tone it takes with everything. I’m not “absolutely right” when I correct it or steer it along a different path. I don’t really want all this extra stuff that it’s so happy to tack on, “it won’t take a minute”.

    I want the LLM to tell me that’s an awful idea, or that it can’t do it. A constant yes-man agreeing with everything I say doesn’t help me get shit done.




  • It’s really more about the overall flavor of the spreadsheet than how “right” any individual field is.

    Just like the Xerox copier/scanners that helpfully kept scanned images small by reusing parts of the image elsewhere. Like, all these 6s on your scanned invoices can totally be replaced with 8s. There’s just a tiny degradation in the overall image, it shouldn’t be a problem!

    Xerox should have just called it AI compression and people would have been throwing money at them.


  • It looks like your drive is going offline randomly, or at least, when it warms up a little. All the IO errors look like various subsystems trying to write to something that’s not there anymore, which is why there’s nothing visible in the logs when you look later.

    Could be the drive, could be the drive controller on the motherboard, could be just that your nvme drive just needs to be taken out of its slot and reseated, could be something weird in your BIOS setup that’s causing mayhem (bus timings, etc).

    Personally I’d reseat your drive in its slot first and go from there.





  • These kind of “manual” a/c units normally have a little sticker or a caution in the manual to “wait 5 minutes before restarting”.

    People can easily trigger this kind of thing just by turning the thermostat back and forth, so there is usually a thermal cutout on the compressor to keep them mostly safe.

    You can usually hear it when it activates, there will be a hum from the stalled compressor for a few seconds and then a little click, and then the compressor won’t start for a minute or two.


  • This kind of reliability is huge for prosthetic limbs, fitness trackers, and robotic arms, where precision and durability are non-negotiable.

    Thanks, AI slop! Sensors that have been durability tested for a few hundred cycles will be perfect for prosthetic devices that can do that in half a day of office work, or fitness trackers that can do that in five minutes, or in robotic arms that can perform that kind of movement in 60 seconds! I’m going to use them in my next safety critical robotics project for sure!