Viewing profile — DeveloperErrata

Not quite, most of the recent work on modern RNNs has been addressing this exact limitation. For instance linear attention yields formulations that can be equivalently interpreted …

This was really educational to me, felt at the perfect level of abstraction to learn a lot about the specifics of LLM architecture without the difficulty of parsing the original pa…

Don't know how Grok is setup, but in earlier models the vision backbone was effectively a separate model that was trained to convert vision inputs into a tokenized output, where th…

Consider the difference between the requirements to simulate the universe and simulate a person's experience of the universe. As people in the universe, we wouldn't be able to tell…

Trueish - for orgs that can't use API models for regulatory or security reasons, or that just need really efficient high throughput models, setting up your own infra for long conte…

Increasingly so. Many other popular inference tools in this space also expose an OpenAI compatible API: VLLM, Llama.cpp, and LiteLLM all do.

Seems like this would (eventually) be big for VR applications. Especially if the avatar could be animated using sensors installed on the headset so that the expressions match the h…

Macbook Pros with M3 & integrated RAM & VRAM can do 70B models :)

I want to plug the Little Big Planet series of games, it's what got me into programming when I was young and I think it still has a lot of charm

I agree, a naive approach to approximate caching would probably not work for most use cases. I'm speculating here, but I wonder if you could use a two stage pipeline for cache retr…

Seems neat - I'm not sure if you do anything like this but one thing that would be useful with RAG apps (esp at big scales) is vector based search over cache contents. What I mean …

It's neat to see this getting attention. I've used similar techniques in production RAG systems that query over big collections of HTML docs. In our case the primary motivator was …

I love old school interactive fiction games (like Zork, etc) but find the strict syntax endlessly frustrating. I built this ChatGPT powered "middleman" to translate commands writte…