I guess it was not only my social media stream that was flooded with GPT4 news in the last few days. The results are impressive but not surprising to me. A combination of events, which are more important from my point of view, didn’t get that much attention: The LLM LLaMA runs on a Raspberry Pi, and Stanford students fine-tuned the model for $100.
Current State and Future Plans for RDF-Ext
This year, RDF-Ext will turn ten years old. In this blog post, I will give a brief overview of recent updates, show the current plans, and explain how you can help improve RDF-Ext.
Implementing a 15x faster JavaScript SHACL Engine
One of my projects encountered a performance problem with the available SHACL engines. Besides, I needed to know which triples had been processed (coverage/fragments), so I implemented a new SHACL engine in JavaScript from scratch.
Man beats machine at Go - What about LLM detection?
In my last blog post, I wrote about how to detect LLM output, with the conclusion that machine-learning approaches are not the solution. Today I want to show how the recent news “Man beats machine at Go in human victory over AI” is related to that topic.
To detect or not to detect LLM output
Recently the question of whether and how text generated by large language models (LLM) can be distinguished from human text showed up in the W3C Semantic Web mailing list. A solution that seems obvious at first glance would be to use the same technology for this purpose. There are already some tools that do exactly that. This blog post lists some of them. But that’s not a long-term solution. Let me explain why:
SPARQL Named Query
Once your SPARQL queries get bigger, you may stumble over the problem that you have duplicate parts of the query or have to deal with performance impacts. Federated queries are affected by some more constraints. The SPARQL Named Query proposal allows the explicit reuse of sub-queries. This blog post will describe the problem in more detail, how the SPARQL Named Query can solve it, and how you can try it already.
Score RDF/JS terms
The RDF community does a pretty good job writing code around specifications. But there could be more generic code that supports people testing or implementing algorithms for RDF graph data. There are many tiny libraries on my local machine which fit into that gap, just lacking better documentation or code coverage. @rdfjs/score is one of them, which finally got a small readme file and was added as an experimental feature to rdf-ext.
Videos and Series of 2020
Maybe some of you watched more videos than the years before. I guess this will be the case in 2021 as well. That’s why I wrote down this summary of my favorites of 2020.
Vielleicht hat der ein oder andere im letzten Jahr ein paar Videos mehr angeschaut als in vorherigen Jahren. Weil es in 2021 vielleicht auch noch ganz gute Chancen gibt Videos zu schauen, habe ich die für mich wichtigsten Videos und Serien aus 2020 hier kurz zusammengefasst.
ReSpeaker Core v2.0 Case
Finally I fixed some small issues in my first design for the case for the ReSpeaker Core v2.0 board. Now you can download it at Thingiverse and print your own!
