Replying to @TheMiamiApe
Got one of these too: Bottom row, 2nd from right :) Nov 2021 was my 2nd NFT.NYC and so peak NFT ! Crazy times.
Replying to @poolsideai
@poolsideai Laguna S2.1 oQ6e in oMLX. surprisingly fast and capable model otherwise - seems to not "get the hint" that my Postgres tables are case sensitive. looping with 20x the same error. - lower case vs pascalCase tool looping issues need to be solved somehow.
Replying to @DailyTurkic
Historically accurate Helen of Troy:
Cloud AI is convenient. Local AI is control.
I joined “Was KI kann” to talk about local AI, data privacy, and why digital sovereignty matters.
Listen here: youtube.com/watch?v=ljUpT3eO…
#AI #LocalAI #DigitalSovereignty
Somebody train the models what "ACs" are when talking about validating tasks. Acceptance Criteria. It's the things that need to work to close issues.
This is what my "Dark Software Factory" output looks like. Parallel worktrees. High-capacity orchestrations. multi-turn review/fix iterative looping. Cheap writing, expensive validation. Unit + End2End integration tests of progress and features. How does yours look like?
Replying to @jundotkim @antirez
check out github.com/apetersson/omlx/t… the day when we can use DS4 as an engine within oMLX - is today. Running at exact same speeds as DS4 proper on my M1 Ultra 128GB. Looking for feedback before i draft a proper PR.









