#thecompaniesapi port back my ai wrapper improvements on our existing llama stack and prepare fine tuning for phi3

#thecompaniesapi run my phi3-128k flow using llama3.1 and the results are mind blowing, it's insane how good llama is at conserving context and original purpose even when supplied with thousands of tokens; also shipped multiple hotfixes in robot UI; about to merge a month of work and then hop on fine tuning

#thecompaniesapi continue working on phi3 ; first steps of subdomain support & association ; rewrite most of our AI impl

#thecompaniesapi maintenance on the bot ; send back test csv to a big ai company that want to use our api ; start migration to phi3 for ou AI stack

#thecompaniesapi few iterations on our ai flows, trying phi3

more AI story writing. Also, getting a better handle on what various versions of Llama2 can handle.

work on #crisp ai features improvements

do backend work on #crisp for new ai features

#thecompaniesapi continue on phi3; hell of a refactor

#thecompaniesapi multitasking support & AI stack rewrite; plenty of new things to do and try

#thecompaniesapi start working on fine tuning as phi3 cannot stop hallucinating even though its a lot faster, heard it would possibly change everything for our usecase so its worth trying

#thecompaniesapi tests are over; phi3 is what we need; dropping lots of python code in favor of a single inference process to govern them all

finalizing #crisp mirage ai backends, getting ready for launch!

#thecompaniesapi lots of fixes on the queue ; trying to get the llm stable ; refactor of sources

Fixing various issues and preparing to launch my AI tool.

#thecompaniesapi continue work on phi, lots of iterations, kinda exhausted lately

resume work on ai automations backend implementation #crisp

nlp pipeline refactoring work 6 hours #consulting

got distracted with my writer AIs — testing between llama3.1 vs gemma2 #leifinlavida

#thecompaniesapi review & merge PRs ; fix cuda drivers on GPU server & dockerize our internal LLM ; perf improvements on the bot