Sublime

An inspiration engine for ideas

AllPeopleCollectionsArticlesAudioBooksFilesHighlightsImagesLinksNotesTextTweetsVideosSocial

Thumbnail of www-x-com-yacinemtb-status-1896416935874847106-eed081117d584e8f

POV you're interviewing to become an ML researcher at an AGI lab https://t.co/of3SUc2Nva

Thumbnail of www-x-com-yacinemtb-status-1668096776505643011-2456a77d61f74b13

I put up my node / llama.cpp / whisper.cpp talk engine up on gh, if you want to play around with it! Still early days, but I hope to talk to my computer soon https://t.co/VyzxBUCDDJ https://t.co/067oW8aRHM

kache

x.com

22365_3_Prompt Engineering_v7 (1)

The content covers prompt engineering for large language models, including techniques, output configurations, and best practices to optimize prompts for various tasks while enhancing model performance and response accuracy.

Link

Training great LLMs entirely from ground zero in the wilderness as a startup — Yi Tay

Yi Tay yitay.net

Things I’d prioritize learning if I was to study to become a ML engineer again: 1. Version control 2. SQL + NoSQL 3. Python 4. Pandas/Dask 5. Data structures 6. Prob & stats 7. ML algos 8. Parallel... See more

Chip Huyen x.com

Thumbnail of www-x-com-austen-status-1858974535326069138-c807ed80298b419d

Hot damn https://t.co/vmQ6v53vYG

Austen Allred

x.com

If you waste days every month fixing broken crawlers check out Bytebot's new launch. https://t.co/Lyac3I1pOd Most people don't know this but I paid for my first year of college building ad hoc web crawlers and selling data. The #1 issue I had was website changes, multiply that by every website and I had massive profit... See more

jason liu x.com

How to talk to machines

Carly Ayres carly.substack.com

Every major AI lab is hiring people who can: – ship eval pipelines – scale training infra – write interpretable logs MLE ≠ "fine-tune a llama" It’s how to make reasoning reliable at scale. Get in. It’s day 1.

Adi Polak x.com