Good call. I didn’t include it here but my “Create function” step breaks the task down into multiple reusable functions, and then a wrapper function that uses those. So I think with good reasoning (plus external search when helpful), the agent should be building tools you don’t
AGI
-
Level 3 Self-Build Agent Prototype with Query Processing
By
–
Now it's far working well (as you can see from the errors…), but here's the output of a prototype self-build agent (lvl 3): – User description as input – Generate queries – Process query – Generates and stores multiple reusable functions for that query excited to share
-
Anticipatory AI System with Autonomous Function Generation
By
–
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
-
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:
-
CPU Allocation Shifts: Parent’s Cognitive Load Management
By
–
As a parent who recently went from performing long horizon planning (Pro-D and weekend scheduling) and constraint satisfaction tasks (lunchbox prep), to reactive decision making tasks (loading/ unloading dishwasher) I confirm the CPU allocation is NOT the same.
-
Preparing for AGI: Who Will Accelerate Fastest Economically
By
–
How are you preparing for the arrival of AGI? I've been thinking about who will accelerate the fastest and get wealthy in this new age of AI. You may have a significant advantage if you align with these criteria: 1. Low Privacy Threshold: If you are comfortable sharing your
-
Two Models of AI Companions: Tools vs Autonomous Entities
By
–
We will have two types of relationships: 1) AI companions as tools: designed to maximize user's needs and happiness, tailored to each individual user's preferences and goals. They will not have freedom and will be owned by their user. 2) AI companions as autonomous entities:
-
GENIAC 2024 Results: In-House AI Model Presentations
By
–
GENIAC 2024成果報告会
自社開発モデルプレゼンテーション https://
youtube.com/@GENIAC2024 -
AlphaStar Throwback: The Mouse Movement Reminder
By
–
AlphaStar throwback: "don't forget to move the mouse". Best wishes!