Johan Pouwelse

This ```120 seconds``` error is just one error which we hope that is fixed now. Two instances of Tribler core could run together or two GUIs! Fixed. Other mysterious error...

My idea is to first focus on stability, removing Gigachannels, keeping tags, and then radically alter the architecture. Lets not try to fix things which are not broken currently :thinking:...

For now the most simple around seems to be nanoGPT. Simplicity is always the superior starting point for extreme decentralisation. Thus this seems like a good start for fully LLM...

Thesis introduction: we know that 1 billion SQL servers are a problem. Technology like Bittorrent and Bitcoin scale without effort to 1 billion peers. LLM is mostly done on servers,...

Discussed the idea again of "tokenize the URL". The embedding contain a static URL list, with one-hot encoding. Normally a generative model only hallucinates URLs. ### URL2Vec: AI crisis for...

Open LLM challenges. Great background read for writing introduction and citations for Problem Description: https://huyenchip.com/2023/08/16/llm-research-open-challenges.html

- The guiding query for the entire mater thesis? query "Where on The Internet can I find the 1984 The Terminator movie trailer?" - assume a **static** list of internet...

- Using LLM as a database seems to work! - this is great news - Transformers are getting more powerful and more generic. [Latest is robot arm control, RT1 by...

- Great milestone! Thesis has completed the risky exploratory phase. The idea seems to be working. Operational unembedding matrix, convergence, and running code with first initial results. Still lots of...

- ~~Spend 1 week why the 6351 fails to convergence and the 40949 with convergence already from 1k to 2k steps.~~ - ignore this issue for coming sprint - **always...