Search: “yohei-nakajima--x”

@Replit longer form video on Active Graph [7 min 22 sec] - flip the agent architecture - 1970s blackboard system - rollback, fork, diff agent runs - experience + behaviors + beliefs = you - behaviors

while everyone seems to be focused on text, vision, and audio, i'm excited to be backing a company building a foundational model for smell 👃 that's right, they've: - mapped how olfactory receptors rea

The white paper from Patina likely outlines a project or platform focused on environmental sustainability, regeneration, or climate solutions, given the domain name 'patina.earth.' While the specific

Active Graph really feels like the culmination of all of my BabyAGI and graph experiments. [fyi, technical history of babyagi: http://babyagi.wiki] would love to hear thoughts if you try it out! the e

This post references a previous article discussing stateful agents broadly, which served as inspiration for Yohei Nakajima's project. The post likely documents how earlier discourse on agent architect

This post discusses a reactive programming or state management architecture where individual behaviors function as small, independent units that respond to state changes and generate new state changes

current agent systems coordinate through conversations and workflows. Active Graph explores what happens when agents coordinate through evolving shared state instead this proposal suggests that long-r

for anyone curious, this was the result of many experiments bouncing around but this version uses... initial ideation: chatgpt for ideas/@replit for quick build final repo build: opus 4.7 prompting cl

Yohei Nakajima requests a critical analysis of the ActiveGraph AI documentation, examining its approach and positioning within the evolving landscape of AI technologies. The post appears to seek detai

Healthspan just launched BioAge+, a biological age score that breaks down which systems are driving it and why kind of like a context graph for your health Introducing BioAge+. The first biological ag

i'm excited to open source Active Graph: an event-sourced reactive graph runtime for long-running, agents 🔄🧠 events/logs projects a graph. reactive behaviors react and affect the graph. fork-and-diff

LLMs are stateless (every time you reply to an LLM, you re-inject the entire conversation to a fresh inference) the purpose of memory is to provide continuity (in games we'd call it a 'persistent worl

Love this concept. Always been a proponent of event-driven architectures, and the actor model. Neat to see how it’s applied to the agent runtime here. i'm excited to open source Active Graph: an event

Patches represent a mechanism for establishing trust boundaries in systems by decoupling the intent to change state from the acceptance and policy-driven implementation of that change. This separation

This post discusses how different types of relations or dependencies in systems can carry behavioral properties, where dependencies like 'depends_on' can unblock work progression, contradictions can t

@Replit narrative walkthrough video of repo for anyone interested: https://x.com/FileCityAI/status/2057164885780226139?s=20 FileCity Tour: activegraph An event-sourced reactive graph runtime for long-

the core concept is a graph that represents everything about the agents knowledge, history, behaviors, capabilities graph is made of events behaviors react to graph changes relationships can carry beh

there he goes again, @yoheinakajima blazing the paths to continuously running self aware agents. this and the posts he links are super worth reading. i'm excited to open source Active Graph: an event-

this is how you add an event, fork and cache a run, and then find the diff between a parent and fork in this example, the fork shares the parent's event log up to event 142. from 143 onward it diverge

we've been building agents around the llm, starting with conversations, adding tools, giving rules, logging everything, and storing a form of it as retrievable state Active Graphs flips this. what if

Yohei Nakajima discusses his exploration of stateful agents and concludes that current implementations have not yet achieved what the concept truly entails, suggesting the field is still in early stag

The daddy of baby AGI articulates what we all feel is missing in the current state of AI architecture I didn’t really understand what people meant by stateful agents so I started exploring my current

this was not on my bingo card Personal update: I've joined Anthropic. I think the next few years at the frontier of LLMs will be especially formative. I am very excited to join the team here and get b

This video discusses the architectural need for a continuity layer in long-running AI agents, explaining how agents require persistent memory and state management mechanisms to maintain coherence acro

This post explores conceptual parallels between classical distributed systems design patterns—such as actor models and reactive blackboard architectures—and their potential application to LLM agent de

a unified theory on aging Most aging theories focus on specific mechanisms—mitochondrial dysfunction, telomere attrition, chronic inflammation. But a new paper in npj Aging proposes that these aren't

flymyai is a simple cloud agent with tons of APIs/models baked in under one api key once you have that working, you can drop that into something like lovable In 90 seconds I shipped the agent that tur

Introducing Agora-1, a multi-agent world model. Multiple participants—human or AI—can now interact inside the same world simulation, all in real-time. Try our playable research preview today, with Ago

Introducing http://Browse.sh, the largest open-source catalog of skills to reliably perform any task on the internet. We've researched hundreds of sites to give your agents the playbook they need to n

last week, a friend was telling me how running down a steep trail is great cognitive exercise due to the vast amount of quick processing you do from vision and tactile input to micro adjustments requi

This post explores the architectural challenge of implementing state management in AI agents, arguing that statefulness cannot simply be added as an afterthought but requires fundamental redesign of h

now i wanna see @drjimfan train robots in a sim doing this https://x.com/i/status/1795746905336725673 VIDEO: Competitors chase wheels of cheese down a steep hill, few remaining upright, in the annual

Simulation is a core part of how we build and evaluate robots. I spoke about simulation, robotics, and the role of interactive worlds at AI Engineer Singapore this past weekend! Full talk : https://ww

some good discussions and experiments around stateful agents in the replies, but seems like we’re not quite there yet, as in we’re starting to track memory and traces, but not quite agent capability a

A person observed a crow harassing ducklings while their parents were distressed, and alerted nearby children who successfully drove the crow away. The post describes a brief wildlife intervention mom

This post likely discusses implementing non-intrusive feedback mechanisms in conversational AI systems that leverage familiar UI patterns to provide detailed user input without disrupting the natural

A parent reflects on playing Super Mario Galaxy with their children and becoming aware of the numerous references to other Mario games in the series that their kids have yet to experience. The observa

we’re evolving into better vibe coders Here's an example of ongoing human physiological change: some people have a third artery in their arm. Some don't. ~10% of people born in the 1880s had the third

Yohei Nakajima shared a personal post about having a good day watching the Super Mario Galaxy movie and dining at Din Tai Fung restaurant with children. The post appears to be a casual social media up

This post explores conceptual parallels between biological heartbeats and cron jobs (scheduled automated tasks in computing), likely examining how both function as reliable, recurring processes that m

This post celebrates the arrival of spring by sharing observations or images of young waterfowl, specifically ducklings and goslings, which are iconic symbols of the season. The post is from Yohei Nak

This post likely discusses Yohei Nakajima's understanding of stateful AI agents—systems that maintain and utilize information across multiple interactions rather than treating each conversation indepe

Yohei Nakajima discusses the lack of elegant primitive implementations for stateful agents, decision traces, and context graphs, which are frequently discussed concepts in AI but rarely demonstrated i

Yohei Nakajima discusses how artificial intelligence has the potential to serve as a unifying force by bridging divides and fostering connection across different groups and perspectives. The post like

This post shares feature requests and ideas inspired by experimentation with micro (likely a small language model or tool), credited to another developer. It appears to be a wishlist of desired capabi

This post likely demonstrates a humanoid robot using a trackpad interface to control a computer mouse and complete a practical task—booking a flight through a web application. The demo showcases the r