Post #2442629
2026-01-17 21:44 UTC
@NefariousCelt@mastodon.scot @dragonfrog@mastodon.sdf.org @cstross@wandering.shop @ViennaMike@mastodon.social
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.
Replies (1)
-
@NefariousCelt@mastodon.scot 2026-01-17 22:03
@ThePowerNap@mefi.social @dragonfrog@mastodon.sdf.org @cstross@wandering.shop @ViennaMike@mastodon.social I suspect I am coming from a very risk averse standpoint. The “summarise this” is what scares me with LLM marketing. I have been burned by poor software requirement specifications. Language simplification can do that in multiple sectors. But yeah mapping natural language to a fixed set of goals, that’s fine. Trust AI with my life, no. Sudden random steering inputs WTAF stelantis.