AI agents have quickly evolved from obscure technical experiments to mainstream buzz. In the last 18 months, new automation capabilities have captured the imagination of entrepreneurs and established organizations alike. While it’s possible that we’re in another AI bubble, the early adopters of AI agents are reporting impressive
Last week I attended the Algorithmic Innovation & Entrepreneurship Summit on Open Problems for AI. That’s a bit of a mouthful but in essence, it was a 2-day conference covering the challenges and opportunities for AI over the next 5 years. Day 1 was focussed on algorithms and AI
An undeniable killer use case for large language models is code generation. It’s already helping software developers write code up to twice as fast and with more delight. As LLM models improve with each release, they can write better software and handle more complex architectures at a fraction of
AI agents have been getting a lot of attention but they can be expensive to run. This is because they use a lot of tokens and make multiple calls to LLMs. Some AI developers have beat performance benchmarks by using exceptionally expensive agentic runs. However, this is unrealistic because in
I switched one of my AI agents projects from GPT-4o to the new Claude 3.5 Sonnet model. The agents now run with a cost that’s roughly 85% cheaper and the final results arrive about 15% faster. To upgrade my AI agents project, all I had to do was
On the way home today I was listening this podcast — “Lessons from a Year of Building with LLMs“. The biggest takeaway? While everyone has been building lots of experimental projects with LLMs and often shipping to production scrappy builds of seemingly impressive demos (I’m guilty of this!), few people
AI Agents are a mixed bag. I tried this morning to get a group of CrewAI agents to complete some Youtube summaries and they kept failing or going off the rails. My deterministic version which I hard coded works significantly better than leaving things to a group of autonomous agents.
There’s an article in the Wall Street Journal I came across today with the headline below. The article ends with a quote from a Google Cloud Chief Evangelist, Richard Seroter: “If you don’t have your data house in order, AI is going to be less valuable than it
Claude AI is really good at coding. In one shot, I asked it to create streamlit app that I can use to chat to my PDFs with a local, offline, large language model. The first attempt had a roughly working version and with just 2 more follow-on prompts and refinement,
Just 18 months ago, OpenAI released GPT-3.5 Turbo which had double the input token context window of its predecessor, GPT-3. We went from 2048 tokens to 4096 tokens and that felt like a significant leap. But today, we are enjoying context windows of 128,000 tokens with GPT4o. How
A couple of experiments today: I completed a simple tutorial that helps you build a RAG app using local models. I also installed and tested https://openwebui.com/. This is a really cool open source project that gives you a ChatGPT-style interface to use with large language models that run
I’ve just finished listening to this podcast with the founders of https://www.factory.ai/. Their startup automates away the drudgery bits of work in software engineering. That includes writing tests, debugging, documentation, and migrations. I found the views of the founders compelling. For example, they don’t think
Tech
I finally have a Youtube video summarizer working! I’ve deployed the app with Streamlit.io. On the backend I’m using the Gemini 1.5 Flash LLM because it’s cheap and fast! The summaries are “chained” together using Langchain. A 20 minute video can be summarized in around
Tech
I’ve been testing out the new Claude LLM and it’s better at coding than GPT4o. I might actually start using it more given how fast and effective it is. You can see the benchmarks below that Anthropic provided. They probably have some bias as they are self-published but
Tech
Today I got a Youtube summarizer script working! I can input a Youtube URL and I get useful summary of the video using the Langchain “refine” documents chain. I really like this because iterates over portions of text and it refines the summary until something more thorough is generated. I’
Tech
This evening I experimented with Langchain’s summarisation frameworks. This is something LLMs are great at natively, but with Langchain, you can use even more sophisticated summarisation techniques. Here’s a GPT-generated summary of these techniques based on the Langchain documentation: From ChatGPT4o: 1. Stuff Method * Concept: Simply concatenate all
Tech
Given the note I wrote yesterday about the need to be “programmatically” lazy, I’m rewriting my Youtube reviewer system. I’m building it initially without agents, and I’ll only add an agentic layer in areas that are more unstructured. I’m not yet sure what areas will have
Tech
The temptation with any new powerful tool is to apply it in more places than is necessary. What’s that saying…”to a man with a hammer, every problem is a nail”? The same appears to be happening with large language model frameworks and AI agent frameworks. I’ve experienced
Tech
One of the pioneers of how large language models are trained and fine-tuned, Jeremy Howard, has a great article here on “What policy makers need to know about AI (and what goes wrong if they don’t)”. The article is actually very accessible to everyday readers. Here’s an excerpt
Tech
I tested out a few AI agents today with the goal of optimising on cost, but they remain expensive to run if you have tasks that involve multi-step reasoning with chunky bits of content. One group of tasks that I gave to GPT4o cost $0.15 and took 2 minutes
Tech
OpenAI launched a feature called “function calling” last year, but it’s a feature I haven’t used and didn’t understand until today. Part of my misunderstanding was because the feature is poorly named. It made me (and many other more technical people) expect that the capability means an
Tech
I have a 7 billion parameter large language model running locally on my Macbook thanks to Ollama! This is great when travelling and there’s no Wifi to access ChatGPT or other large language models. What I can run on my Macbook today is not as powerful as GPT4o but
Tech
The Plateau of Generative AI? There are many people in Generative AI circles who believe that we can get to God-like AI by training models on increasingly larger swaths of data. Their view is that if we can train gargantuan models on all of the world’s data, we’ll
Tech
I did two things today. First, I got a Youtube summarizer to work. I followed a simple tutorial here. I will create an agent tool out of this, and also try and build a RAG process around it. Second, I watched this lecture on “The Future of AI from the