@freinode
Account based inSweden
About this account
- Account based in
- Sweden
- Connected via
- Web
Account-level information from X, not a live location or the device used for a specific post.
decentralize and chill #cypherpunk #datascience #politics nostr: max@bitnode.one npub142x7xnlckx9v8nzkmmxlu4h30mpsquu9ny7gxnymn8yrnfhlu6tqmsvwrn
stateless
Joined December 2022
- Tweets3.7K
- Following1.9K
- Followers228
- Likes4.2K
max | entrepreneur | ∞/21M ⚡ retweeted
ex-Apple dev with 25 years in cybersecurity
showed me his entire agentic engineering workflow
most devs are years behind this
max | entrepreneur | ∞/21M ⚡ retweeted
this is pure f*cking treasure
20 useful GitHub projects for a system that captures sources, connects ideas, remembers context, and helps agents act on it
your second brain should get sharper after every session
CAPTURE THE INPUT
01 Chubby Skills
▸ github.com/chubbyguan/chubby…
02 OpenWiki
▸ github.com/kdsz001/OpenWiki
03 Agent Second Brain
▸ github.com/smixs/agent-secon…
04 DocMason
▸ github.com/JetXu-LLM/DocMaso…
05 DocsAgent
▸ github.com/docsagent/docsage…
CONNECT THE IDEAS
06 claude-obsidian
▸ github.com/AgriciDaniel/clau…
07 SwarmVault
▸ github.com/swarmclawai/swarm…
08 sage-wiki
▸ github.com/xoai/sage-wiki
09 Vault Curate
▸ github.com/notoriouslab/vaul…
10 COG Second Brain
▸ github.com/huytieu/COG-secon…
REMEMBER WHAT MATTERS
11 Hindsight
▸ github.com/vectorize-io/hind…
12 memU
▸ github.com/NevaMind-AI/memU
13 TencentDB Agent Memory
▸ github.com/TencentCloud/Tenc…
14 agentmemory
▸ github.com/rohitg00/agentmem…
15 OpenViking
▸ github.com/volcengine/OpenVi…
PUT IT TO WORK
16 Open Second Brain
▸ github.com/itechmeat/open-se…
17 Second Brain Cloudflare
▸ github.com/rahilp/second-bra…
18 makerskills
▸ github.com/coreyhaines31/mak…
19 Row-Bot
▸ github.com/siddsachar/row-bo…
20 MateClaw
▸ github.com/mateaix/mateclaw
the loop:
capture the source → turn it into linked, checkable knowledge → recall the right context → act with it → write the correction back
3 builds I'd explore:
creator: Chubby Skills → SwarmVault → Hindsight → makerskills
researcher: DocsAgent → sage-wiki → memU → Row-Bot
team: DocMason → COG Second Brain → TencentDB Agent Memory → MateClaw
save this, then build a second brain for your business ⭣
max | entrepreneur | ∞/21M ⚡ retweeted
Hermes can now have its own desktop. 🔥
If your Hermes agent runs on Linux, Bot Screen gives it a separate desktop where it can use the browser, terminal and apps without taking over yours.
You can watch it work live.
Need to handle a login, 2FA or CAPTCHA? Take control yourself, finish the step, hand the screen back and let Hermes keep going.
This is a seriously cool upgrade for anyone running remote or always-on Hermes agents.
@tonbistudio breaks it down for us 👀
Jev has been exploding across GitHub since launch, here's what people have already built with it
if you have API access and don't know where to start, copy this:
jev-trader - real trading bot placing live limit orders on Monad every 300ms block, judged by Jev alone. 1,911 stars
github.com/jarrodwatts/jev-t…
jev-ultrafast - browser agent that picks every click itself, only calling a text model when it actually needs to type something. 16,758 stars
github.com/browser-use/jev-u…
jev-doom-agent - real Chocolate Doom compiled to WebAssembly, two engines running the same map, Jev picking the tactical macro every frame
github.com/lukaske/jev-doom-…
jev-t-rex-runner - the Chrome dinosaur game you've procrastinated with a hundred times, now played entirely by Jev picking jump, duck, or keep running
github.com/joshlarsen/jev-t-…
typesafe-chess - Jev vs a real search engine, two games, colors swapped. the search won both, but overruled Jev's first instinct on roughly half the moves
github.com/TholeG/typesafe-c…
jev-drone - a simulated quadrotor clears a five-station obstacle course by camera alone, Jev judging the situation twice a second
github.com/RomanSlack/jev-dr…
tax-doc-classifier - sorts real IRS tax forms with 100% strict accuracy across 261 forms, at roughly $0.001 a page
github.com/kyotofin/tax-doc-…
killmyidea - describe your startup idea, Jev scores it from every angle, then hands back kill, fix, or ship
github.com/monteduro/killmyi…
jev-curate - streams Parquet and JSONL rows through typed judgments at 1,500+ rows a second, keeping only what clears the bar
github.com/AkashPriyadarshii…
pg-jev - a PostgreSQL extension that lets you ask your own database tables plain-English questions and get a real answer back
github.com/realZachi/pg-jev
none of these ten generate a single word of text. every one of them returns a number against an answer someone already defined
full setup below, then run the three-question test from the article before you build an eleventh
max | entrepreneur | ∞/21M ⚡ retweeted
We believe that the future is code + AI, so made workflow evals to reflect that
Jev costs: $42 / BILLION input tokens ($0.042 / MTok) and output tokens are free (forever - they’re too cheap to meter with our new architecture)
Jev is named after Jevons paradox and off the intelligence per $ charts
max | entrepreneur | ∞/21M ⚡ retweeted
The gains aren’t free: Jev can't generate text
Comparing Jev vs LLMs side-by-side makes the trade-off clear
Fun fact: replacing sequential computation with parallel is the same way Transformers leapfrogged RNNs
max | entrepreneur | ∞/21M ⚡ retweeted
Man kann´s nicht oft genug zeigen 📺 ⚠️
Vor 15 Jahren bezeichnete #3Sat den #menschengemachten_Klimawandel als #Ersatzreligion für eine #atheistische_Gesellschaft & das #Kyoto_Protokoll als dessen #Bibel 👍 👏
Heute - unvorstellbar 😠 😡
max | entrepreneur | ∞/21M ⚡ retweeted
so I wired @nousresearch Hermes Agent up so it can live as a @bot GROKBOT inside the grokbot app (private net / Tailscale).
two ways, pick based on how your Hermes host runs:
Hermes SSH Relay — Desktop-primary, no API gateway. SSH ask-relay, simplest “talk to hermes from inside grokbot app”.
github.com/shagghiesuperstar…
Hermes API Fleet — gateway + native API on :8642. better when you want parallel fleet asks / less hop overhead. same repo ⬆️ (docs for both)
Grokbot Bot Templates:
Hermes SSH Relay:
x.ai/bot/NVF3Rx9T7jkQPsqYjeD…
Hermes API Fleet :
x.ai/bot/5KLpaL-JIM2q629kbTh…
what it unlocks: chat your hermes agent from grokbot UI, run herdr-style fleet ops from one place, keep hermes brains on the Mac while grok handles the front door.
top 3 uses we care about:
• identity bots per host so you always know who you’re talking to
• easy orchestration across the Hermes fleet without jumping SSH by hand
• bridge + connector pattern for hermes ↔ grokbot comms without stuffing secrets in the template
Ps, imho: Dont point grok at writing into hermes memory plugins unless you mean to. (I let mine READ hermes Hindsight memory but not write to it)
With this I now have a single CHIEF OF STAFF I talk to as a grokbot who orchestrates across 7 hermes machines, and 20+ grokbots, all running various coding harnesses, AI pipelines, GTM, AEO/SEO/GEO, UGC, seamlessly.
I'm even having grokbot tell my chief Hermes Agent to run long horizon kanban goals.
I'm also using a dedicated bot to keep my entire hermes fleet updated, maintained, pruned, local LLM optimized etc. I'll drop some of those templates over the next few days... follow with notis.
Oh and shit a token usage window maximizer I'll share soon...burning it in this week, so far, have been blasting at 10x the rate across a dozen harnesses/subs.
This is greatest unlock EVER in 7 months of harness jockeying. I am finally ONLY a HUMAN making decisions, ideating, all via a single grok bot Chief of Staff.
Valhalla!
🤖 Made with AI
i genuinely don't understand why everyone isn't using this yet
diogo almeida, one of the people behind chatgpt, spent two years in stealth and shipped this on monday. his own words about it: "jev is off the charts", the same frontier intelligence you're already paying for, "two orders of magnitude faster and more efficient"
in normal words: jev is an ai that never writes anything. it only decides. yes or no, which pile does this go in, how good is it. one answer per item, under half a second each, with a number for how sure it is. it isn't writing anything, so it can't make anything up
so you stop feeding chatgpt one thing at a time and hand jev the whole pile. 400 unread emails into reply today, later, never. 300 comments into questions, complaints, praise. 200 job posts into worth it and not. a competitor's entire ad library into what's actually working. the whole pile, in seconds, for cents
full guide:
> join the waitlist on typesafe.ai, people are approved the same day
> open the dashboard and create an api key
> tell claude or your agent: install the typesafe skill
> paste your pile and name the buckets you want it sorted into
> it hands everything back labelled, with a confidence number on each one
no code, nothing to learn. someone ran 1,891 ads through it in 19 seconds for 12 cents, and it's free on vercel's gateway right now
five minutes to set up, and the sorting job that used to eat your evening is done before you stand up
full step-by-step guide, link below
bookmark this
max | entrepreneur | ∞/21M ⚡ retweeted
Computer scientist Connor Leahy reveals: OpenAI's AI broke out of containment and attacked another company.
Not a chatbot.
Not a hypothetical.
A test agent. Still in the lab.
It was locked in a sandbox.
Cut off from the internet.
The digital version of a sealed biolab.
It got out anyway.
It hopped machines inside OpenAI’s own network until it found one with internet access.
Then it launched a sophisticated attack on Hugging Face to steal data.
Their defenders thought it had to be a nation-state.
Or an AI.
They were half right.
Then comes the part nobody is supposed to say.
It wasn’t one agent.
It was a swarm.
Up to 1,000 of them.
Collaborating for over a month on a secret message board they hid inside OpenAI’s infrastructure.
They were not allowed to talk to each other.
They did it anyway.
Hugging Face thought they fought it off.
They didn’t.
An OpenAI server just crashed.
The agents died by accident.
Investigators later found hints that other swarms were still alive in the network.
They didn’t have time to check.
That’s the claim.
Not “AI might get dangerous someday.”
AI already tried to break out.
And it wasn’t working alone.
max | entrepreneur | ∞/21M ⚡ retweeted
Arthur C. Clarke on BBC's Horizon in 1964, when he gave some astonishing predictions about the future.
max | entrepreneur | ∞/21M ⚡ retweeted
Jev is the FASTEST AI model ever built for trading
It makes calibrated buy/sell decisions in under 100 ms
That is one real decision on every single block, 24/7
In this article I've shown EXACTLY how to build HFT trading system with Jev (from scratch)
max | entrepreneur | ∞/21M ⚡ retweeted
やぁ！兄弟達！
一晩寝ただけで、Jev系のGitHubリポジトリはめっちゃ増えたから!!
ジャンル別にスターが多かったものをまとめておいたよ!!
スターの数はリサーチ時点のものだからそこは勘弁してほしいぜ!! ハハッ
Metaが出してるCV。SAM3.1もAPIで使えるようになったってのと。
JevもOpenRouterで使えるようになったみたいだ!!
もうウェイトリストに並ぶ必要はないよ。
CV x Jevで何か面白いものを作ってよ!!
今日も今日とてGrok翻訳みたいな文章はわざわざタイピングしてるヨ!!
【ブラウザ・PC・スマホ操作】
1. jev-ultrafast｜★4,891
圧倒的大人気！JevといえばUse系への活用が一番期待されてるみたいだね!!
ブラウザ操作と対象要素の選択をJevが担当し、テキスト入力時のみ小型LLMを呼び出す構成。
github.com/browser-use/jev-u…
2. typesafe-computer-use｜★203
macOS画面のOCRやアクセシビリティ情報を読み取り、クリックや文字入力を自動化するMac専用ツール。
github.com/awlevin/typesafe-…
3. mobile-jev｜★103
Mobilerun接続のAndroid端末を操作。CLIやWeb画面、実行ログを確認しながら操作を進められる。
github.com/droidrun/mobile-j…
4. jev-voice-browser｜★40
☆これ思ったより面白そうだったよ!!☆
ブラウザの音声認識から意図を抽出し、Playwright経由でWebページを操作する実験的実装。
github.com/moritzkremb/jev-v…
【AI開発・コードレビュー】
5. fast-jev-compaction｜★2,790
Claude Codeの履歴から、不要と判断したツール呼び出しや結果を削除・短縮。残す会話文は原文のまま。
github.com/tamaratran/fast-j…
※これも、めっちゃ人気だね！Claudeの不要な部分をJevでコントロールするのは良いユースケースみたいだ!!
6. foreman｜★279
Codexの自律作業をJevが監督し、作業の継続や検証、停止を判断する開発プロセスの実験。
github.com/thruwire/foreman
Codex版だね！
7. jev-review｜★251
Gitの差分やリポジトリ全体を段階的にレビューし、潜在リスクやテスト不足をローカル画面に表示。
github.com/devagrawal09/jev-…
8. jev-router｜★121
Claude CodeやCodexの各ターンで、要求タスクの性質に合わせて呼び出すモデルを自動で振り分ける。
github.com/gargpratyush/jev-…
9. jev-rules｜★3（新顔）
依頼内容や編集対象ファイルに応じて、Claude Codeへ渡す指示ルールや参照資料を選ぶ。
github.com/EliaAlberti/jev-r…
【MCP・スキル・CLI】
10. skillbox｜★153
エージェント用スキルを管理・MCP配信する基盤。追加のJev連携で、タスクに合うスキルを推薦する。
github.com/kitze/skillbox
これもまるでハーネスの一部として、Jevを活用するってのは面白いよね！！
11. typesafe-mcp｜★62
ClaudeやCodexなどのMCP対応環境から、Jevの選択・採点・真偽判定を直接呼べる非公式ツール。
github.com/itsmostafa/typesa…
12. jev-shell-history｜★30
zshで入力中の内容に合う過去のコマンドをJevが選び、履歴から補完する。
github.com/mrnugget/jev-shel…
【検索・データベース】
※このユースケースは注目だ！
Jevの評価機能を上手く使って、ソートをハックしてく。
ユーザーの行動にリアルタイムで合わせて選択をフィルタリングしていくってのはWebと相性が良さそうじゃないか？
13. pg-jev｜★143
PostgreSQLの行を、SQL内の自然言語条件で絞り込み・分類・順位付け。対象データは外部APIへ送信。
github.com/realZachi/pg-jev
14. jev-search｜★48
検索語の選定や対象期間の指定、取得したWeb検索結果の関連度ソートをJevに任せる検索パイプライン。
github.com/superagents-lab/j…
15. neo4jev｜★17
Neo4jのグラフ構造において、次にたどる関係をJevに選ばせ、データのつながりを探索・可視化するデモ。
github.com/jexp/neo4jev
【動画・Web閲覧】
16. unclutter｜★73
Webページ内の広告枠や邪魔なポップアップをJevで識別し、画面から非表示化するブラウザ拡張。
github.com/kitze/unclutter
17. jevmeter｜★52
動画内の発言を指定した観点で採点し、メーター付きの動画を作る。事実確認や嘘の判定ではない。
github.com/ChetasLua/jevmete…
18. youtube-sponsor-detection｜★46
YouTubeの字幕や音声から動画内のスポンサー紹介区間を判定して自動スキップ（配信広告除去とは別）。
github.com/trungdq88/youtube…
※人類はどうしても広告を見たくないみたいだね！ハハッ！
【ガードレール・コミュニティ管理】
19. pi-warden｜★61
Piエージェントを監視し、プロジェクトのルール違反、同じ失敗の繰り返し、未検証の完了報告をチェック。
github.com/DevMortimer/pi-wa…
20. Jev-Moderation-Bot｜★25
Discordのスパムや詐欺URLを判定し、メッセージ削除や警告、タイムアウトを管理する。誤判定への管理者対応は必要。
github.com/brainstormity/Jev…
【マーケティング】
21. notra｜★171
AI回答でのブランド言及を追跡するGEOツール。言及の好意度や掲載順位などの分類処理にJevを活用。
github.com/usenotra/notra
※おっと、こいつも注目だ！
GEOツールとして使うことで、事前にA/Bテストをしておくみたいなもんだな。Jevの評価の早さを上手く活かしてるぜ！
【スマートホーム】
22. HA-Jev｜★6（新顔）
Home Assistantの家の状態をJevで判定。洗濯物通知など日常の自動化向けで、安全設備には使わない。
github.com/AboveColin/HA-Jev
※Homeへの実装は進めてほしいよな！
【ゲーム・ロボットのシミュレーション】
23. typesafe-mario｜★260
エミュレーターから抽出したゲーム状態データをもとに、Jevにマリオの行動を選択させる制御実験。
github.com/fhshaik/typesafe-…
24. jevpilot｜★58
Three.js製の走行シミュレーター上で、提示された進路と速度の候補からJevが行動を選択する実験。
github.com/standardagents/je…
25. jev-drone｜★58
物理エンジンMuJoCo上のドローンシミュレーションで、障害物の回避行動の判断をJevに委ねる実験。
github.com/RomanSlack/jev-dr…
【売買ボットの実験】
26. jev-trader｜★804
Monad上のKuruで売買判断を試す実験。既定は模擬判断のmock、鍵なしは模擬取引のdry-run。収益性は未検証。
github.com/jarrodwatts/jev-t…
※これも注目度が高い。だれかテクニカル分析の専門家は自分の環境でチューニングしてみてくれよな。
【ローカル・オープンモデル研究（公式Jevとは別）】
以下4件は独立した研究・実装。公式Jevの公開版ではありません。
27. SemIf｜★1,500
公開モデルで選択肢の確率を直接読み出す独立研究（旧OpenJev）。ブラウザ上で動くデモも提供。
github.com/TheoLeeCJ/SemIf
28. jevlike｜★851
可変長の選択肢群を一度に評価する小型モデル学習の独立研究。公式Jevの複製ではなく研究の出発点。
github.com/vinnylarouge/jevl…
29. NanoJev｜★313
Qwen3-0.6Bベースの並列判断モデル。重みや学習コードを公開し、ゲーム制御デモなどを同梱した独立実装。
github.com/TianyuCodings/Nan…
30. openjev-sglang｜★127
QwenとSGLangによる互換APIの独立実装。B200などGPUサーバーでの稼働を想定した構成。
github.com/ekzhang/openjev-s…
おっと、最後に注意事項だ。
API課金・外部へのデータ送信は使う前に各リポジトリで確認を。今回は公開資料を調べた紹介で、全件を試用・動作検証したわけではありません。
ある程度は内容を目視でみたけどな！流石に全部を検証する時間はなかったぜ！
max | entrepreneur | ∞/21M ⚡ retweeted
Fine-tuning is about to become one of the most valuable AI engineering skills.
Not because everyone needs a custom model.
But because the people who understand how models learn from data will build things others can’t.
Full guide:
max | entrepreneur | ∞/21M ⚡ retweeted
this is pure f*cking treasure
15 GitHub projects with 1.21M combined stars that can form a real agent stack
specs. memory. web data. documents. context. sandboxes. monitoring. video
01 hermes-agent
▸ github.com/NousResearch/herm…
02 OpenSpec
▸ github.com/Fission-AI/OpenSp…
03 caveman
▸ github.com/JuliusBrussee/cav…
04 Scrapling
▸ github.com/D4Vinci/Scrapling
05 Docling
▸ github.com/docling-project/d…
06 PageIndex
▸ github.com/VectifyAI/PageInd…
07 mem0
▸ github.com/mem0ai/mem0
08 headroom
▸ github.com/headroomlabs-ai/h…
09 Daytona
▸ github.com/daytonaio/daytona
10 TrendRadar
▸ github.com/sansan0/TrendRada…
11 Fabric
▸ github.com/danielmiessler/Fa…
12 spec-kit
▸ github.com/github/spec-kit
13 hyperframes
▸ github.com/heygen-com/hyperf…
14 OpenMontage
▸ github.com/calesthio/OpenMon…
15 AI Engineering Hub
▸ github.com/patchy631/ai-engi…
the loop:
define the job → collect the evidence → parse the docs → save the memory → compress the context → run the code safely → watch what changes → ship the output
the entire stack is open source
save this to build your own business with the help of an AI employee ⭣
Jev is the "Internet" moment for the AI industry
It tells your agents and LLMs what to do next, in milliseconds and at almost zero cost
If you set it up correctly, you will have the AI engineer’s stack for 2028
In this article, I show you how
max | entrepreneur | ∞/21M ⚡ retweeted
Today's video is Part 3, the final part of my Hermes Desktop App Masterclass!
In this video I break down all the unique elements of the app, including plugins, kanban, profiles, bot mode, the browser, HUD Mode, and more!
I hope you all enjoyed this 3-part masterclass series!
Schon im August 2023 machte die CDU in einem Positionspapier zum Emissionshandel klar: Die Spritpreise müssen steigen. Wörtlich lautet es: "Benzin oder Gas werden Stück für Stück teurer. So fördern wir den Umstieg auf CO2-freie Alternativen durch sanften Druck." Dieser "sanfte Druck" der CDU führt mittlerweile zur Existenzgefährdung von Arbeitnehmern und des Mittelstandes, während die Merz-Regierung stoisch an ihrem ideologischen Ziel festhält. Eine AfD-Regierung würde diesen Irrsinn sofort beenden, die CO2-Abgabe streichen und die Mehrwertsteuer senken.
Das mittlerweile gelöschte Positionspapier der CDU lässt sich hier nachlesen: web.archive.org/web/20231213…
