Level 3: Anticipatory A system that generates synthetic queries based on its understanding of the user, where each query is fed into the system 2 need-based system – which generates required functions as necessary. The result is a system that can autonomously generate functions
@yoheinakajima
-
AI-Powered Function Generation: Request-Based Tool Creation
By
–
Level 1: Request-based Users can request to have functions generated by an AI, and when they query the system, the new function is available as an option for the AI to use. *There's lots that goes into this "Create Function Tool", but let's keep the chart simple (eg.
-
Dynamic Function Generation for AI Query Processing
By
–
Level 2: Need-based When a user submits a query, the AI first decides if an existing function works, and if not, will generate a new reusable function, generate parameters based on the original user input, and execute the new function to handle the query.
-
Level 0: AI Access to Function Libraries and Tools
By
–
Before we start, this is Level 0. A library of functions built by human developers that the AI has access to. The agent is not building its own functions.* *tools, skills, api calls, are all just functions
-
Three Levels of Self-Building Autonomous Agents
By
–
A helpful autonomous agent has access to all the tools you need – and nothing more. But we all have different needs, changing all the time, so… what we need is a self-building autonomous agent. Here, I'll describe the 3 levels of self-building autonomous agents:
-
Function Dependencies Graph with Code Management and Versioning
By
–
function dependencies displayed as a graph with ability to see details, read and update code, see logs, execute the function, and see versions (auto-generated) pic.twitter.com/OcbrK0BSZs
— Yohei (@yoheinakajima) 26 septembre 2024function dependencies displayed as a graph with ability to see details, read and update code, see logs, execute the function, and see versions (auto-generated)
-
Next Level Debugging Techniques and Methods
By
–
this is some next level debugging if i may say so myself
-
AI Agent Companies Funding Trends Analysis 2026
By
–
amount raised per year by AI companies with the word "agent/agents" in their description (source @crunchbase – which i know is not full coverage but still helpful for seeing trends)
-
Vector LoRA technique test and evaluation results
By
–
Oooh I do like this vector LoRA! (my usual test )
-
New Multimodal Model with Visual Feedback Features Released
By
–
oooh pretty cool new multimodal model you can play with today. some unique features like visual feedback as part of the response (eg dots showing when it counts things)
— Yohei (@yoheinakajima) 25 septembre 2024
though on the site I only see option to upload media and ask questions, no the demo I see in video https://t.co/bjvl8mblh0oooh pretty cool new multimodal model you can play with today. some unique features like visual feedback as part of the response (eg dots showing when it counts things) though on the site I only see option to upload media and ask questions, no the demo I see in video