rootwarp.eth

A big technical breakthrough in ZK: we've just successfully executed our first mainnet blocks with ZK-Nethermind on @ziskvm. This means the battle-tested @Nethermind EVM can be used in Ethereum’s ZK future. 1/2

Ethereum Korea Build the Path, Connect the World, Execute the Future 기여가 인정으로, 기록이 연결로, 펀딩이 공공재로 이어지는 생태계를 만들어나갑니다.

Your work tools in Claude are now available on mobile. Explore Figma designs, create Canva slides, check Amplitude dashboards, all from your phone. Give it a try: claude.com/download

You can now schedule recurring cloud-based tasks on Claude Code. Set a repo (or repos), a schedule, and a prompt. Claude runs it via cloud infra on your schedule, so you don’t need to keep Claude Code running on your local machine.

속보: 미국 SEC, 암호화폐 16개 자산을 공식적으로 ‘디지털 상품’으로 분류 해당 자산은 다음과 같습니다: $XRP, $APT, $AVAX, $DOGE, $SOL, $ADA, $BCH, $ETH, $HBAR, $ALGO, $LTC, $DOT, $SHIB, $XLM, $XTZ, $LINK 아무도 관심이 없을때 미국은 조용히 암호화폐 미래를 구축하고 있습니다.

Today, the Foundation’s Board released the EF Mandate. This document, which was first intended for EF members, reaffirms the promise of Ethereum, and the role of EF within this ecosystem.

1 million context window: Now generally available for Claude Opus 4.6 and Claude Sonnet 4.6.

A2A Protocol v1.0 is here! 🚀 It's the first stable, production-ready standard for AI agent communication. We’re proud to build this alongside our partners. 🌉 Don't build a fence; build a bridge. a2a-protocol.org/latest/announc… How are you connecting your agents?

Macrohard or Digital Optimus is a joint xAI-Tesla project, coming as part of Tesla’s investment agreement with xAI. Grok is the master conductor/navigator with deep understanding of the world to direct digital Optimus, which is processing and actioning the past 5 secs of real-time computer screen video and keyboard/mouse actions. Grok is like a much more advanced and sophisticated version of turn-by-turn navigation software. You can think of it as Digital Optimus AI being System 1 (instinctive part of the mind) and Grok being System 2. (thinking part of the mind). This will run very competitively on the super low cost Tesla AI4 ($650) paired with relatively frugal use of the much more expensive xAI Nvidia hardware. And it will be the only real-time smart AI system. This is a big deal. In principle, it is capable of emulating the function of entire companies. That is why the program is called MACROHARD, a funny reference to Microsoft. No other company can yet do this.

Claude Code has a built-in scheduler now! /loop [interval] <prompt>

@r2Jamong obsidian 🙌

매일 더 똑똑해지는 나만의 리서치 에이전트 구축하기 : Knowledge Index 피드백 루프 여러분이 사용하는 AI도구들은 지난 데이터를 학습하고 있지 않는다는 것을 알고 계시나요? Openclaw든 Claude code든 Gemini CLI든 사용하는 방식에 따라 지난 대화 내용을 기억하게 할수는 있습니다. 하지만, 여러분이 아무리 리서치를 요청하고 자료 조사를 시키더라도 이 결과는 1회용일 뿐입니다. 사진은 제가 약 1개월간 14개의 에이전트를 활용해 쌓아온 이더리움 리서치 리포트들입니다. 이렇게 자료를 쌓아뒀다 하더라도, 새로운 리서치를 요청한다면 과거의 지식에 대한 참고 없이 LLM서버를 통해 제로베이스에서 분석하게 됩니다. 제가 사용하고 있는 방법 "Knowledge Index 피드백 루프"를 간단히 소개합니다. 1. 에이전트들이 생성하는 문서들은 md파일로 생성하도록 합니다. 2. index.json 파일에 각 문서의 핵심 요약과 주요 키워드들을 인덱싱합니다. 3. 새로운 요청이 들어왔을 때, 먼저 index.json 파일을 읽고 관련된 문서들을 참조합니다. 필요한 경우 원본 문서를 읽습니다. 4. 매일 자동화된 리서치 파이프라인을 운영한다면, 매일 자동으로 지식이 쌓이고, 시간이 지날수록 내 에이전트들은 과거 자신이 수행했던 리서치를 토대로 더 똑똑해 집니다. 단순히 LLM을 사용하는 것은 매번 똑같은 제로베이스에서 시작하는 것입니다. 결국 구조를 갖추고 어떻게 설계하는지에 따라 내 에이전트를 더 똑똑하게 만들수 있습니다.

😱

It is hard to communicate how much programming has changed due to AI in the last 2 months: not gradually and over time in the "progress as usual" way, but specifically this last December. There are a number of asterisks but imo coding agents basically didn’t work before December and basically work since - the models have significantly higher quality, long-term coherence and tenacity and they can power through large and long tasks, well past enough that it is extremely disruptive to the default programming workflow. Just to give an example, over the weekend I was building a local video analysis dashboard for the cameras of my home so I wrote: “Here is the local IP and username/password of my DGX Spark. Log in, set up ssh keys, set up vLLM, download and bench Qwen3-VL, set up a server endpoint to inference videos, a basic web ui dashboard, test everything, set it up with systemd, record memory notes for yourself and write up a markdown report for me”. The agent went off for ~30 minutes, ran into multiple issues, researched solutions online, resolved them one by one, wrote the code, tested it, debugged it, set up the services, and came back with the report and it was just done. I didn’t touch anything. All of this could easily have been a weekend project just 3 months ago but today it’s something you kick off and forget about for 30 minutes. As a result, programming is becoming unrecognizable. You’re not typing computer code into an editor like the way things were since computers were invented, that era is over. You're spinning up AI agents, giving them tasks *in English* and managing and reviewing their work in parallel. The biggest prize is in figuring out how you can keep ascending the layers of abstraction to set up long-running orchestrator Claws with all of the right tools, memory and instructions that productively manage multiple parallel Code instances for you. The leverage achievable via top tier "agentic engineering" feels very high right now. It’s not perfect, it needs high-level direction, judgement, taste, oversight, iteration and hints and ideas. It works a lot better in some scenarios than others (e.g. especially for tasks that are well-specified and where you can verify/test functionality). The key is to build intuition to decompose the task just right to hand off the parts that work and help out around the edges. But imo, this is nowhere near "business as usual" time in software.

@r2Jamong 경이로우면서 허무하다는 말보다 적절한 문장을 못찾겟네요.

x.com/ngnicky/status… 15년 가까이 경력을 쌓아온 내 직업의 종말을 지켜보는건 경이로우면서도 허무합니다.

Claude Code on desktop can now preview your running apps, review your code, and handle CI failures and PRs in the background. Here’s what's new:

Introducing Claude Code Security, now in limited research preview. It scans codebases for vulnerabilities and suggests targeted software patches for human review, allowing teams to find and fix issues that traditional tools often miss. Learn more: anthropic.com/news/claude-co…

Gemini 3.1 Pro is here. Hitting 77.1% on ARC-AGI-2, it’s a step forward in core reasoning (more than 2x 3 Pro). With a more capable baseline, it’s great for super complex tasks like visualizing difficult concepts, synthesizing data into a single view, or bringing creative projects to life. We’re shipping 3.1 Pro across our consumer and developer products to bring this underlying leap in intelligence to your everyday applications right away. Rolling out now to: - Developers in preview via the Gemini API in @GoogleAIStudio - Enterprises in Vertex AI and Gemini Enterprise - Everyone through the @Geminiapp and @NotebookLM

Introducing EVMbench—a new benchmark that measures how well AI agents can detect, exploit, and patch high-severity smart contract vulnerabilities. openai.com/index/introduc…

secret package seems to be great 👍