Search: “yohei-nakajima--x”

“The baseline question for VC content was once - are you publishing anything at all? The new bar is whether anyone cares when you do. When competence gets commoditised, distinctiveness becomes the sca

this is awesome. he didn’t import @activegraphai but borrowed design principles to improve his systems (and found improvement opportunities) great walkthrough in the linked post (for your agent to ing

Soak testing for AI agents involves running agents continuously over extended periods to identify performance degradation, resource leaks, stability issues, and edge cases that may not appear during s

A comprehensive evaluation of over 30 frontier embodied AI models reveals that current generalist robot policies lack the robustness needed for reliable real-world manipulation tasks. The analysis dem

Following the amazing reaction to the Marble Curriculum yesterday, we've decided to make it open source 🛰️👇 Everything a child learns in primary school. 1,590 concepts. 3,221 connections across 8 subj

haha i'm like a fish out of water Media 🚀 Introducing Lingbot-World-2, our newest real-time world model. Richer interactivity, sharper visuals, and advanced camera controls that make exploring what yo

ikeabench Furniture assembly is the task everyone name-drops and nobody actually attempts at real scale. Every demo I have seen is a scaled down IKEA leg or a single arm on a toy chair. This paper doe

recent survey of Ai engineers 1/ Last week at @aiDotEngineer, I presented the 2026 AI Engineering Survey: 1,000+ AI engineers on model selection, build vs. buy, who’s shipping with AI, and (of course)

Variable rewards are game mechanics that provide unpredictable or randomized incentives to players, designed to encourage repeated engagement through the uncertainty of outcomes. This concept is commo

the “harness” will never go away, and it’s just as important as the model new post on harness engineering for AI self-improvement: https://lilianweng.github.io/posts/2026-07-04-harness/ It is hard to

this is a great approach, seeing this more @flymy_ai also does this when you build an agent via their api, they'll build a deterministic reusable workflow, except for where you need models we built th

This post likely explores the philosophy or practical approach of balancing intense work ethic with equally committed leisure and personal life, suggesting that professional ambition should be matched

Yohei Nakajima proposes an alternative model development structure where AI models are created through specialized production teams assembled like film studios, with each team tailored to the specific

yessssss Excited to announce our partnership with @tryramp to offer day-one incorporation for startups directly in Cofounder. You can now apply for incorporation, an EIN, and bank account without leav

This post discusses how observing Claude's internal activation patterns (J-space) reveals the model's hidden reasoning processes, such as detecting code bugs and analyzing images, even when these step

Yohei Nakajima humorously addresses criticism from Hacker News users who perceived him as claiming to have discovered event sourcing and CQRS (Command Query Responsibility Segregation), established ar

Active Graph proposes a paradigm shift in AI agent architecture by using logs as the primary mechanism for agent operations rather than conversation-based interactions. This design approach is particu

ActiveGraph makes the agent trace the runtime: Yohei Nakajima's open-source Python runtime treats an append-only event log as the source of truth, enabling replay, forking, and lineage for long-runnin

joined my in-laws for an annual gathering where they had a flag ceremony, reading of the constitution, and we sang while marching… I met a third cousins once removed. definitely the most beautiful 4th

Yohei Nakajima used Claude AI to construct a comprehensive family tree that connected all family members for a weekend gathering. The post highlights a practical application of AI in organizing and vi

The Log is the Agent 它的核心观点是：不要把日志当成 agent 的副产品，而要把 append-only event log 当成 agent 本身。 在 ActiveGraph 里，目标、规则、工具调用、LLM 响应、产物和关系都写入同一条事件日志；当前状态只是日志 replay 后投影出来的一张图。 这样带来三个关键能力： 可确定性重放 可在任意事件处分叉实验 从最终输出

.@activegraphai v1.2.0 is live 👇 🧩 graph projection is now pluggable 🕸️ falkordb = native edges + cypher pushdown ⚡ 2-hop query: ~8.9s → ~300ms 🧪 conformance suite + full ci gate 🤝 community-built cor

A casual social media post from Yohei Nakajima wishing followers a happy Fourth of July. The post likely includes holiday greetings or brief commentary related to Independence Day celebrations.

MIT and Apache 2.0 are both permissive open-source licenses, but Apache 2.0 provides more explicit legal protections including patent grants and indemnification clauses, while MIT is simpler and short

spending the last week at @aidotengineer was awesome. too many great convos to cover them all, but jotted down some things that stood out: - Lots of discussion around open source models. I spoke with

hosted three side events, a lunch, and did a talk this week. pretty tired, but worth it! Heaps of fun watching last night’s USA v BIH World Cup match at @yoheinakajima’s watch party after @aiDotEngine

In 12 hours we've had 323 people sign our petition to protect local AI. Open Source must win, not because anyone else must lose. But so that we can all win. Please help me get 10,000 signatures so tha

Something about this year’s @aiDotEngineer World’s Fair just hit different. Last year was the year of “let the agents rip.” This year was the year of realizing that autonomy without structure creates

Yohei Nakajima shared a brief update on X about completing a talk and meeting interesting people afterward. The post reflects a positive experience at what was likely a speaking engagement or event. W

ORA.ai is a tool that evaluates website 'agent readiness' by analyzing how well-suited a site is for autonomous agent interaction, then generates prompts that coding agents can use to implement necess

if you joined us on Wednesday, you can find more pics here: https://lightroom.adobe.com/shares/136e7f64192a4c55968d1f8a3d5d5dc8 Last night we hosted the BabyAGI x Physical AI Happy Hour in SF with @yo

Yohei Nakajima will present ActiveGraph, an event-sourced graph runtime designed for building auditable agents, at 11:10am in room 2005 of a conference's graph track. The presentation focuses on lever

Yohei Nakajima hosted a networking event in San Francisco bringing together the BabyAGI and Physical AI communities for casual conversation and relationship-building. The event likely focused on discu

Yohei Nakajima announced a milestone of 70,000 agent transactions, expressing surprise at the rapid growth. This likely refers to autonomous AI agent activity or transactions within a system or platfo

guess who’s back, back again We’ve received notice that the Department of Commerce has lifted export controls on Claude Fable 5 and Mythos 5. We'll begin restoring access tomorrow, and will share an u

This post explores the concept that an agent's log or execution history serves as the primary mechanism for decision-making and learning, suggesting that the sequential record of actions and outcomes

Yohei Nakajima posted a brief thank you message to Firecrawl for providing fast WiFi service, mentioning the location was conveniently located just across the street. The post appears to be a casual s

Yohei Nakajima shared a post about wearing a new t-shirt related to BabyAGI and ActiveGraph, likely promoting or celebrating these AI projects. BabyAGI is a simplified autonomous AI agent framework, w

FalkorDB and ActiveGraph enable querying, sharing, and scaling of agent graph projections beyond in-memory limitations, allowing developers to persist and manage complex agent architectures in a graph

This post by Yohei Nakajima acknowledges or addresses someone with the handle @aidotengineer on social media, likely engaging in a conversation or commentary about AI engineering or development. The s

We’re sharing the next major milestone in our non-invasive brain-to-text decoder research: Brain2Qwerty v2. Building on v1, which was published today in @Nature, Brain2Qwerty v2 is the highest-perform

and here’s a filterable visualization of the side events: wanted a quick way to visualize side events for @aidotengineer world fair next week https://yoheinakajima.github.io/aie-side-events/ filter by

Yohei Nakajima developed a feature for the AI Engineer World Fair that enables users to discover similar talks through an embedded search functionality, while also adding a map interface and bookmark/

updated with new events + a link to the event page wanted a quick way to visualize side events for @aidotengineer world fair next week https://yoheinakajima.github.io/aie-side-events/ filter by date/t

excited to come down to SF for @aidotengineer next week! let’s hang :) We're hosting a BabyAGI x Physical AI Happy Hour with @yoheinakajima on June 30th, 6PM in SF! If you're building across AI agents

Yohei Nakajima created an interactive visualization tool for side events at the AI Dojo Engineer World Fair, accessible via a GitHub Pages site. The tool appears to include filtering capabilities to h