Posts on Artificial Intelligence
-
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 ]] -
[[ Read more ]] 路 15 minute read
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...
-
[[ Read more ]] 路 13 minute read
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...
-
[[ Read more ]] 路 6 minute read
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...
-
[[ Read more ]] 路 5 minute read
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...
-
[[ Read more ]] 路 17 minute read
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...
-
[[ Read more ]] 路 11 minute read
Build an Advanced RAG App: Query Rewriting
The new query now matches with the chunk of information I wanted to get my answer from, giving the LLM a better chance of answering a much better response for my question. Conclusion We have taken our first step out of basic RAG pipelines and into Advanced RAG. Query Rewriting i...
-
[[ Read more ]] 路 12 minute read
How to build a basic RAG app
Common problems and pitfalls As the title implies, this solution is a basic or na茂ve RAG implementation. It will empower your application to make the most out of the LLM it鈥檚 using and your data. But it won鈥檛 work for all cases. These are just some of the most common problems wi...
-
[[ Read more ]] 路 9 minute read
How to use LLMs: Summarize long documents
And that鈥檚 it! You now have a short summary of the most important points of a large document. But before you start processing your whole documentation, there are a few important notes you need to consider: This MapReduce method might not be less expensive than using an LLM with...