undefined
@NefariousCelt @dragonfrog @cstross @ViennaMike
95% agree. I'm currently working an LLM project that is interfacing with something a touch more than home automation. Aside from fine tuning the model and putting constraints on the output (think https://github.com/dottxt-ai/outlines), you can use existing approved software as validation of llm output.
All of this requires in-depth knowlege, patience and exaustive testing.
@ludicity @dragonfrog @cstross @ViennaMike
I'm kinda betting on this, but it doesn't mean the next couple of years won't be painful.
Those are my bread and butter
@dragonfrog @cstross @ViennaMike
I more or less agree. I'm just not looking forward to the backlash those of us in the machine learning space will face (I'm in computer vision/medical).
There is some real utility under the hood, but goddamn.
The pushback from higher utility bills and GenAI diarrhea is justified, and a huge black eye for practical use.