Today I started work on a crew of LLM agents that will search the internet and YouTube for reviews about products.
For example, if I was planning to buy a pair of noise cancelling headphones, I would search YouTube for product reviews. With AI agents, I can automate this process to produce a synthesis of several reviews and output a simple summary.
I’ll see if this actually works well and share demo results here.
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