Recent Posts
-
馃敆 [Link] Circuit Tracing: Revealing Computational Graphs in Language Models
A group of Anthropic-affiliated scientists has released a paper where they study how human concepts are represented across Claude 3.5 Haiku's neurons and how these features interact to produce model outputs.
This is a specially difficult task since these concepts are not contained within a single neuron. Neurons are
polysemantic
, meaning that they encode multiple unrelated concepts in its representation. To make matters worse,superposition
makes it so the representation of features are built from a combination of multiple neurons, not just one.In this paper, the researches build a Local Replacement Model, where they replace the neural network's components with a simpler, interpretable function that mimics its behavior. Also, for each prompt, they show many Attribution Graph that help visualize how the model processes information and how the features smeared across the model's neurons influence its outputs.
Also check out the companion paper: On the Biology of a Large Language Model. In this paper the researchers also use interactive Attribution Graphs to study how models can think ahead of time to perform complex text generations that require the model to think through many steps to answer.
[[ Visit external link ]] -
How to Write a Good index.html File
Every web developer has been there: you're starting a new project and staring at an empty file called index.html. You try to remember, which tags were meant to go in the <head> again? Which are the meta tags that are best practice and which ones are deprecated? Recently, I ...
-
馃毀 [Project] HTML Starter Template
A comprehensive index.html template (with comments) to get quickly up and running when starting a new web site.
-
馃敆 [Link] Claude Think Tool
The Anthropic team has discovered an interesting approach to LLM thinking capabilities. Instead of making the model think deeply before answering or taking an action, they experimented with giving the model a think tool. The think tool does nothing but register a thought in the state. However, it does allow the model to decide when it's appropriate to stop and think more carefully about the current state and the best approach to move forward.
The thinking done using the think tool will not be as deep and it will be more focused on newly obtained information. Therefore, the think tool is specially useful when the model has to carefully analyze the outputs of complex tools and act on them thoughtfully.
[[ Visit external link ]] -
馃敆 [Quote] 馃敪 The Einstein AI model
These benchmarks test if AI models can find the right answers to a set of questions we already know the answer to. However, real scientific breakthroughs will come not from answering known questions, but from asking challenging new questions and questioning common conceptions and previous ideas. - Thomas Wolf
Interesting reflection from Thomas from HuggingFace. Current LLMs have limited potential to make breakthroughs since they cannot "think out-of-the-box" from their training data. We might be able to give the LLMs the ability to explore outside their known world by mechanisms like reinforcement learning + live environment feedback, or other mechanisms that we haven't thought about yet. Still, significant breakthroughs will be hard for LLMs since the real breakthroughs that make a huge impact are usually very far away from established knowledge - very far from the AI model's current probability space.
[[ Visit external link ]] -
About the Dead Internet Theory and AI
The Dead Internet Theory is a thought that has gained a lot of traction recently. I have to admit, the first time it was explained to me, I felt an eerie realization. Like I had already been experiencing it, but I hadn't paid too much attention to it. The first moment, I felt sc...
-
The Rise Of Reasoner Models: Scaling Test-Time Compute
A new kind of LLM has recently been popping out everywhere: Reasoner models. Kickstarted by OpenAI's o1 and o3, these models are a bit different from the rest. These models particularly shine when dealing with mathematical problems and coding challenges, where success depends on...
-
AI in 2024: Year in Review and Predictions for 2025
The past year has been transformative for artificial intelligence, marked by breakthrough innovations, emerging regulations, and a shift toward practical AI tools that enhance productivity. As we look ahead to 2025, let's review the major developments of 2024 and explore what th...
-
Is the EU Falling Behind in the AI Race?
The recent announcement that Meta's Llama 3.2 Vision models won't be available in the European Union has reignited discussions about the impact of EU regulations on AI innovation and accessibility. This development joins a growing list of AI technologies from major tech companie...
-
Build an Advanced RAG App: Query Routing
Conclusion In conclusion, Query Routing is a great step towards a more advanced RAG application. It allows to set up a base for a more complex system, where our app can better plan how to best answer questions. Also, Query Routing can be the glue that ties together other advance...