fine tuned data cleaning to handle the limits on Claude 3.5 Sonnet Context Window.. now continues processing where it left off and we've added the ability to fact check and complete, incomplete datasets. I really want to add a diff view instead of just clobbering existing data, but we're getting into scope creep. Can come after launch. #datamachine

📝 wrote about using Claude 3.5 to refactor a Python app without writing any code. micro.webology.dev/2024/08/25…

got some fancy chart done by claudeAI on how the AI integration into #feedbackbasket can go, mind blowing how it just went above and beyond, I just asked for an explanation. 🤯

🤖 testing Claude 3 for some low hanging fruit code writing tasks

Used Cursor AI + Claude 3.5 to generate a bunch of content for #installphp - quite impressed by the speed!

🤖 let Claude write a bunch of tests for my new app to make sure nothing breaks

impact prediction model seems crap - refining it now with the help of Claude - and once again I'm blown away

🤖 I gave the new Claude a test ride and had it create a new Django Admin app. Not bad. Not bad at all. #research

making Claude 3.5 Sonnet to come up with a pytorch code which finds a model which computes the ahrefs DR impact of a backlink. With manual exploration I came to a correlation of 66%. 5 minutes of Claude -> pytorch already pushed it up to 72%

reverse engineering ahrefs DR log scale - my manual approach was MUCH better than 2h of claude loops. Interesting: data science is another thing which works better by hand (or with external help) than with AI

Love it when the "Discover more" feature works this well.. Which doesn't happen often 😅 Might have to consider using AI to help #lifelog

Tried Claude instead of ChatGPT, much better at code but still not perfect #blogrecorder

I don't often use generative AI, but I did the trend (then saw @levelsio post and asked it that way): Literally ZERO surprises in either answer, but it's good to have this external perspective to confirm what I already knew.

delegate reasoning to Claude to compare two texts (one is human-written and the other by AI)

try better code helpers than chatGPT 3.5 - after getting MUCH advice on Twitter tried GPT4, Perplexity, trying to get access to Claude, installed bolt AI

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.

🤖 Prototyped a Django-based Agent framework using Claude 3.5 #research

🤖 has Claude work on a few projects while I was going to sleep and immediately after waking up. The present is wild. #research

#thecompaniesapi continue r&d on phi3, trying idea refinement from structured text content, then pipe to inference flow, unknown territories 🤣

🤖 wrapped my brain around proxies and built an app which collects and tests them #mylife