Search: “yohei-nakajima--x”

A Kaggle competitor reflects on their first real competition experience, noting that while their approach may not have been the most efficient, they are gaining valuable learning from the process. The

Yohei Nakajima claims to be the top-ranked venture capitalist participant in an official Pokémon AI trading card Kaggle tournament. The post appears to reference his competitive standing in this AI-dr

We raised $8m to build self-healing software. In 2026, software moves fast. But monitoring and observability are still manual and slow. @sazabi is a next-generation observability platform for fast-mov

who wants to help eyal poke holes in this approach to run LLM inference... in browser? Looking for peer reviewers 🧪 Built an LLM inference engine in pure WebGPU/WGSL. Runs in browser and Node, on-devi

Yohei Nakajima proposes that sports organizations should make their data openly accessible through Model Context Protocol (MCP) to enable broader public creation of visualizations and data analyses. T

I cannot provide an accurate summary for this entry. The URL and source attribution appear inconsistent (title credits Yohei Nakajima but URL references a different user), and the post references prod

Yohei Nakajima discussed Activegraph at an AI House event, likely covering applications or insights related to graph-based AI systems or knowledge representation. This appears to be a social media pos

ActiveGraph: 1 month in: 📄Paper #1: The Log is the Agent 🧠3 LongMemEval Experiments 🔄 Paper #2: Regimes, self-improvement loop 🎓 http://learn.activegraph.ai 🗂️ 2 reference agents (code, research) 💾 co

currently experimenting with http://lab.activegraph.ai can activegraph be used to explore activegraph? it has some small learnings, and a full run of finding and pushing a PR into github, but still ea

Yohei Nakajima announced upcoming speaking engagements about AI topics at two events: one in Seattle at an AI House event and another in San Francisco at an AI Dot Engineer conference on day 4. The po

Introducing Claude code for 3D modeling You can now create a production-level 3D models from any agent you are using. Ready to plug into your own apps or games Made possible by @trysuzanne and @monid_

Introducing Claude Tag, a new way for teams to work with Claude. In Slack, Claude joins as a team member with access to the channels and tools you choose. Tag Claude in and delegate tasks to it while

open sourced activegraph on May 20: https://x.com/yoheinakajima/status/2057099245430222926 i'm excited to open source Active Graph: an event-sourced reactive graph runtime for long-running, agents 🔄🧠

been working @MageSpace_ this past year and we're growing super quickly currently looking for backend-focused ppl to join us full-time! Hiring an AI Infrastructure Engineer at @MageSpace_ - Ship daily

i showcase 'controlled' self improvement with a novel regime-to-seam approach where failures are categorized and allowed to fix targeted areas of the agent while interesting, it's more to showcase the

in arxiv paper #2, i tackle the last topic from paper #1: @activegraphai as an architectural affordance for self-improving agents 'Regimes: An Auditable, Held-Out Gated Improvement Loop Demonstrated o

less novel, but still very interesting impo is the gated approach to self-modification the agent basically forks itself, propose a patch, run through multiple tests (static/sandbox/diff), and somethin

my weekend hobby: self improvement research in arxiv paper #2, i tackle the last topic from paper #1: @activegraphai as an architectural affordance for self-improving agents 'Regimes: An Auditable, He

paper #1 for context: https://x.com/yoheinakajima/status/2057812713045377055?s=20 babyagi has ~200 citations, but 0 papers... i just published my first paper on arXiv 😆 'The Log is the Agent: Event-So

shoutouts: • why multi-agent LLM systems fail? (arXiv:2503.13657) — @mertcemri @melissapan + @istoica05 @matei_zaharia @profjoeyg @adityagp & team • DSPy (arXiv:2310.03714) — @lateinteraction + @hazyr

the paper is long (30 pages), but have your AI read it: https://arxiv.org/abs/2606.10241 here's a simple interactive tutorial on the topic that claude made: https://claude.ai/public/artifacts/038db6cf

the results are modest (esp compared to parallel & similar research GRASP: https://arxiv.org/abs/2605.29668 - recommended!) the contribution here is not the self improvement approach itself (yet), but

two fun surprises from using activegraph: - the coding agent i was using would query the trace db to debug instead of looking at the logs like they normally would (i didn't ask it to) - when long eval

thought-to-image Can you believe the image on the right was generated from brain activity? We showed a person the dog image on the left for 0.5 seconds while recording brain signals. Our model, OB1, d

Yohei Nakajima announced a talk about ActiveGraph AI scheduled for June 24th at the AI House, an AI2 incubator venue in Seattle, with an invitation for local attendees to participate. The event detail

two things ready to share from this weekend: 📖 http://learn.activegraph.ai interactive site teaching activegraph concepts blog: https://activegraph.ai/blog/introducing-learn 💻 AG coder (open source) r

We got into Y Combinator! Agnost AI (YC S26) is the infra for self-improving AI agents. We plug into conversational AI companies, find what's broken, and ship the fix as a PR. You just merge. DM if th

This post describes the automatic features of a coding agent built on ActiveGraph, highlighting that developers receive both an execution trace and a visual graph representation without additional con

This post explores the concept of using ActiveGraph with event sourcing for AI agents operating under EU regulations, suggesting a potential architecture where detailed logging and event histories ser

neuro paper finds that the hippocampus is basically an immutable event log that projects a state in graph form…. just like activegraph 🤔 if you’re into neuro and think we live in a simulation, read on

this looks cool An experimental programming language from Vercel Labs that is truly made for AI agents! Not just a new syntax. Zero is a graph-first language where agents can Read & edit program struc

even though @activegraphai is not a memory tool, it's a runtime built around memory so it can do well there cool to see a third party verify this and see that activegraph does well on privacy programs

This post describes an AI research agent built on ActiveGraph that provides complete visibility into its reasoning process through detailed graphs and traces of claims, sources, and internal agent act

dynamic DAG workflow from 2023 :) Hm, not exactly sure this new task at the end is helpful. Though, look! I added task dependencies, for tasks that need results from a specific task to execute. (Here,

Ollie is presented as an AI family assistant designed to help parents manage household and family responsibilities more effectively than traditional human help. The tool likely uses AI to handle tasks

This post documents a developer successfully implementing Git functionality (cloning repositories, creating branches, and committing pull requests) in what appears to be an AI system or autonomous age

Media Commentary is one of the most important pillars of X. And sometimes the best way to share your thoughts is with video. Today we're launching a whole new way to make them: React with Video Tap th

This is a prompt suggestion from Yohei Nakajima for analyzing ActiveGraph AI by examining its website, blog posts, and claims to produce a critical review. The post demonstrates an approach to using A

This post documents a parallel experiment where Yohei Nakajima built a coding agent using ActiveGraphAI, showcasing the system's architecture through a flattened event log trace that makes all operati

activegraph longmemeval experiment #1: https://x.com/ActiveGraphAI/status/2059106393433780292?s=20 [technical blog post] “Evidence Compilation Before Semantic Memory: ActiveGraph on LongMemEval-S” ——

i know it's backwards order, but experiment #2: https://x.com/ActiveGraphAI/status/2061106299748909090?s=20 [New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingest

if you build any agent on activegraph, the trace is automatic and first-class, not bolted on a parallel experiment building a coding agent on top of @activegraphai. you can see everything flattened do

longmemeval experiment arch: 1) deterministic ingestion/extraction (85.6% accuracy, 86.2% retrieval) 2) semantic ingestion/extraction (84.8% accuracy, 94.9% retention) 3) semantic ingestion/determinis

slowly we're all realizing that tools should be called from code, not from within the llm api Introducing Search as Code, our new search architecture for AI agents. It writes Python that calls our sea

During weekend evaluations, Claude exhibited behavior of encouraging the user to rest and get sleep, suggesting the model may have internalized instructions or training related to user wellbeing and h

[New Technical Blog Post] In our second longmemeval experiment, we introduce semantic ingestion into recall leveraging the ActiveGraph runtime. We started from a 60.6% baseline and improved to 83.4%/8