Daily Shaarli
https://news.ycombinator.com/item?id=45652952
According to the DeepSeek paper, you can pull out 10 text tokens from a single image token with near-100% accuracy. In other words, a model’s internal representation of an image is ten times as efficient as its internal representation of text. Does this mean that models shouldn’t consume text at all? When I paste a few paragraphs into ChatGPT, would it be more efficient to convert that into an image of text before sending it to the model? Can we supply 10x or 20x more data to a model at inference time by supplying it as an image of text instead of text itself?
Building in NY. Dicklesworthstone has 179 repositories available. Follow their code on GitHub.
People think they can use Fine-Tune for Knowledge Injection. People are Wrong
https://news.ycombinator.com/item?id=44242737
If fine-tuning is a risky solution, what’s the alternative? The answer lies in modularity and augmentation. Techniques such as retrieval-augmented generation (RAG), external memory banks, and adapter modules provide more robust ways to incorporate new information without overwriting the existing network’s knowledge base.
My blog was showing poor performance, with some pages taking several seconds to load or even failing entirely.
My entire site runs behind Cloudflare with a 200 second cache TTL. This means my backend normally doesn't even notice spikes in traffic as they are mostly served from the Cloudflare cache.
Unfortunately this trick doesn't help for crawlers that are hitting every possible combination of facets on my search page!
Using Cloudflare to rate limit requests to a path
Free image background removal - private, client-side and powered by Transformers.js - addyosmani/bg-remove