Test out Phi, Mistral, Gemma and Llama for interpreting scraped text and find best #bkkrentmap

🤖 Created an Ollama + Llama 3.2 version of my job parser to compare to ChatGPT. It's not bad at all, but not as good as GPT4. #jobs

🤖 Updated some scripts to use Ollama's latest structured output with Llama 3.3 (latest) and fell back to Llama 3.2. I drop from >1 minute with 3.3 down to 2 to 7 seconds per request with 3.2. I can't see a difference in the results. For small projects 3.2 is the better path. #research

🤖 Tried out Llama 3.3 and the latest Ollama client for what feels like flawless local tool calling. #research

#thecompaniesapi working on llama3.1 with large context window, trying to improve some parts of our AI flow before merging it; now properly respects industries & naics constraints for current sample

#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 get my branch up to date with latest work from @LeCoupa and switch back to llama on critical parts ; also launch extraction of an exhaustive list of all our industries for a customer

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

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

tested llama model to scan newsletters #sponsorgap

Tried Nvidia's new Nemotron and holy shit.. I've never seen a LLM number list every letter of "strawberry" like that... while ChatGPT-4o, Claude Sonnet and Llama3.1 all fumbled #indiejourney

FINALLY! Made the canvas work. First time using a combo of Llama 3.1, Claude Sonnet 3.5 and ChatGPT, but the trickiest parts were mostly solved by Llama 3.1. Looks like Claude is better for coding with more conventions, not more uncommon stuff like canvas, while I'm pleasantly surprised Llama 3.1 can deliver on it! Now, what should I call this new project... #indiejourney

🤖 played with Aider and it mostly working with Ollama + Llama 3.1 #research

I used Claude 3.5 Project + Artifacts to help refactor most of the Ollama + Llama 3.1 #research project. I would call it a writing bot, but I'm not building it to automate writing. It's mostly a content wrapper around the Chat interface but it's good at generating code and building off of chat history.

🤖 more working with Ollama and Llama 3.1 and working on a story writer as a good enough demo. #research

check out Llama 3.1 #life

Try Llama3-8b for #TouristItinerary

read llama guard paper #aiplay

reading LLaMa paper #aiplay

trying to stream response from llama #autorepurposeai