Back
Similar todos
continued on my ahrefs DR reverse engineering. Around 10h investment, old model: correlation: 89%, new model: correlation 69% 😭
reverse engineering ahrefs DR model- part 137
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
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%
trying to find a better data science model for backlink analysis - spent around 16h for a promising new version - which turns out is worse than before 🙁
reverse engineering ahrefs DR dimension - it's somehow logarithmic, but how exactly?
Bump aiexperiments.co from Ahref score of 81% to 99% 
#aiexperiments
Full refacto of AI predictions and credit management 
#melies
👨💻 re-create the "is the car damaged?" from kaggle | train the model on 64 picture and accuracy of the model is 92% 🤯
tested succesfully keyphrase-extraction-kbir-inspec ai model via huggingface on newsletters to identify key words 
#sponsorgap
train a model to see if I can detect accuracy in reviews based on a context. 
#beassured
predictive analysis #consulting
Improving SIC classifier model some more. Finally getting somewhere! Precision & Recall at 70% now 
#branddev
cross 200k on replicate with my model used in 
#audiogest 
#spectropic
