we've officially reached AGI

Tool use, in which an LLM is given functions it can request to call for gathering information, taking action, or manipulating data, is a key design pattern of AI agentic workflows. You may be familiar with LLM-based systems that can perform a web search or execute code. Some of the large, consumer-facing LLMs already incorporate these features. But tool use goes well beyond these examples. If you prompt an online LLM-based chat system, “What is the best coffee maker according to reviewers?”, it might decide to carry out a web search and download one or more web pages to gain context. Early on, LLM developers realized that relying only on a pre-trained transformer to generate output tokens is limiting, and that giving an LLM a tool for web search lets it do much more. With such a tool, an LLM is either fine-tuned or prompted (perhaps with few-shot prompting) to generate a special string like {tool: web-search, query: "coffee maker reviews"} to request calling a search engine. (The exact format of the string depends on the implementation.) A post-processing step then looks for strings like these, calls the web search function with the relevant parameters when it finds one, and passes the result back to the LLM as additional input context for further processing. Similarly, if you ask, “If I invest $100 at compound 7% interest for 12 years, what do I have at the end?”, rather than trying to generate the answer directly using a transformer network — which is unlikely to result in the right answer — the LLM might use a code execution tool to run a Python command to compute 100 * (1+0.07)**12 to get the right answer. The LLM might generate a string like this: {tool: python-interpreter, code: "100 * (1+0.07)**12"}. But tool use in agentic workflows now goes much further. Developers are using functions to search different sources (web, Wikipedia, arXiv, etc.), to interface with productivity tools (send email, read/write calendar entries, etc.), generate or interpret images, and much more. We can prompt an LLM using context that gives detailed descriptions of many functions. These descriptions might include a text description of what the function does plus details of what arguments the function expects. And we’d expect the LLM to automatically choose the right function to call to do a job. Further, systems are being built in which the LLM has access to hundreds of tools. In such settings, there might be too many functions at your disposal to put all of them into the LLM context, so you might use heuristics to pick the most relevant subset to include in the LLM context at the current step of processing. This technique, which is described in the Gorilla paper cited below, is reminiscent of how, if there is too much text to include as context, retrieval augmented generation (RAG) systems offer heuristics for picking a subset of the text to include. Early in the history of LLMs, before widespread availability of large multimodal models (LMMs) like LLaVa, GPT-4V, and Gemini, LLMs could not process images directly, so a lot of work on tool use was carried out by the computer vision community. At that time, the only way for an LLM-based system to manipulate an image was by calling a function to, say, carry out object recognition or some other function on it. Since then, practices for tool use have exploded. GPT-4’s function calling capability, released in the middle of last year, was a significant step toward general-purpose tool use. Since then, more and more LLMs are being developed to similarly be facile with tool use. If you’re interested in learning more about tool use, I recommend: - Gorilla: Large Language Model Connected with Massive APIs, Patil et al. (2023) - MM-REACT: Prompting ChatGPT for Multimodal Reasoning and Action, Yang et al. (2023) - Efficient Tool Use with Chain-of-Abstraction Reasoning, Gao et al. (2024) Both Tool Use and Reflection, which I posted about last week, are design patterns that I can get to work fairly reliably on my applications — both are capabilities well worth learning about. In the future, I’ll describe the Planning and Multi-agent collaboration design patterns. They allow AI agents to do much more but are less mature, less predictable — albeit very exciting — technologies. [Original text: ]

Those who thought it was free money are now discovering that they have to pay for it retrospectively.

On the left is GPT-3.5. On the right is GPT-4. If you think the answer on the left indicates that GPT-3.5 does not have a world-model.... Then you have to agree that the answer on the right indicates GPT-4 does.