All of that is just one agent/thread. People coalesce into organizations so they can specialize and parallelize work towards shared goals. Imo this is likely to happen to AutoGPTs and for the same reasons, strung into AutoOrgs, with AutoCEO, AutoCFO, AutoICs, etc.
INNOVATION
-
GPT Calls as Thoughts: Building Agents with Reflection and Memory
By
–
1 GPT call is a bit like 1 thought. Stringing them together in loops creates agents that can perceive, think, and act, their goals defined in English in prompts. For feedback / learning, one path is to have a "reflect" phase that evaluates outcomes, saves rollouts to memory,
-
Is AI Really Recursively Self-Improving Its Own Code?
By
–
Is it really recursively self-improving? So not just generating code, but also modifying its own code?
-
AutoGPTs: The Next Frontier of Prompt Engineering and AI Systems
By
–
Next frontier of prompt engineering imo: "AutoGPTs" . 1 GPT call is just like 1 instruction on a computer. They can be strung together into programs. Use prompt to define I/O device and tool specs, define the cognitive loop, page data in and out of context window, .run(). https://t.co/EKy84pa5bB
— Andrej Karpathy (@karpathy) 2 avril 2023Next frontier of prompt engineering imo: "AutoGPTs" . 1 GPT call is just like 1 instruction on a computer. They can be strung together into programs. Use prompt to define I/O device and tool specs, define the cognitive loop, page data in and out of context window, .run().
-
Agent AI Corrects Generated Programs Using Test Feedback
By
–
By patching you mean how the agent corrects the generated program? We get the feedback from the tests and feed it back to LLM, to make an intelligent decision on what needs to get fixed.
-
AI Development Acceleration: Major Changes Ahead for Software Engineering
By
–
Take this from @Steve_Yegge (
https://
about.sourcegraph.com/blog/cheating-
is-all-you-need
…) and add this from @simonw (
https://
simonwillison.net/2023/Mar/27/ai
-enhanced-development/
…) and this from @peternixey (
https://
x.com/peternixey/sta
tus/1640002493630369792?s=20
…) and it's clear that something big is going to happen, and probably faster than we'd like, to AI and software development -
AI Requires New Startup Building Paradigm and Approach
By
–
I don’t agree! I think AI as a paradigm to build tech and products is very different than traditional software and requires an update on how we build and suggest to build startups
-
Lean Startup Methodology for AI: Building Differentiation Beyond PMF
By
–
We need the equivalent of the “lean startup” book/movement by @ericries but for AI. Very different paradigm IMO to build startups. For ex, it’s easier to get to wow effect/illusion of pmf but harder to differentiate/retention/stay up to date on cutting edge. Who’s working on it?
-
GoodAI Autonomous Agents Design Test Programs Autonomously
By
–
In GoodAI, we are working on autonomous agents powered by LLMs. This is one of those projects where the agent gets an initial goal (to build a program) and then autonomously designs tests, runs them, and proposes corrections until the program works. Another use case for
-
BMW Transforms into Robot in 30 Seconds
By
–
All it takes is 30 seconds (just 30 seconds!) for this BMW🚘 to become a transformer! This is amazing.pic.twitter.com/XTrG2c0U5b #Robot #IoT #AI #Sundayvibes @BMW #SundayMorning #selfdriving #SmartCity #İstanbul
— Sean Gardner (@2morrowknight) 2 avril 2023All it takes is 30 seconds (just 30 seconds!) for this BMW to become a transformer! This is amazing. #Robot #IoT #AI #Sundayvibes @BMW #SundayMorning #selfdriving #SmartCity #İstanbul