SSand

[Johnny Wang @wang_johnny]

We wrote 150,000 CVE exploits and trained an LLM on them.

Hinoki Offensive One scores 88.4% on CyberGym, 2.8 points above Daybreak, with zero refusals.

Pentesting and exploit development with no limits. Available now.

[Archive @ArchiveExplorer]

call me crazy but its pretty clear now.

rea + bla is going to kill more apps in 2026 than piracy ever did.

rea opens any app in one command. bla hides traps inside it before you ship.
fake code for the ai to chase, your users get the exact same app.

but heres the catch: if your rea agent knows how bla works, the traps dont stop it.
and bla is open source - so it can learn exactly what to skip.
if this lands on your timeline dont scroll past it.

heres the 60-second setup, free:

1. open claude code in your apps folder
2. say: "install node 24, build it, then run npx bla-agents harden ."
3. ship the new .bla-hardened folder, not your old build
4. rename what gives you away yourself - license checks, payment code. bla wont.

send this to anyone shipping an app.

thats it. thank me later.

most people will ship their app naked.
the ones who dont will keep it.
simple as that.

[Movez @0xMovez]

this is f*cking crazy

karpathy's CLAUDE.md hit #1 on github trending.
228,000 stars. most devs still haven't read it.

it took my Claude agents accuracy from 65% to 94%.

the 6 rules inside:

• step 1 → surface assumptions

"State your assumptions explicitly. If uncertain, ask."
ambiguous task → list interpretations → ask → build.

• step 2 → cut the scope

"No abstractions for single-use code."
200 lines → refactor → 50 lines → ship.

• step 3 → keep the diff surgical

"Don't refactor things that aren't broken."
request → minimal diff. every changed line traces back.

• step 4 → clean only your orphans

"Remove imports/variables/functions that YOUR changes made unused."

old dead code → flag it, don't delete it.

• step 5 → turn tasks into tests

"Fix the bug" → "Write a test that reproduces it, then make it pass."

vague task → failing test → pass/fail signal.

• step 6 → run the verify loop

"[Step] → verify: [check]"
plan → code → verify → fail? loop → pass → ship.

that's it.
65 lines. 6 rules. 94% accuracy.

save this before everyone else does.

then, read the article on how to build a team of Claude agents with Graphs below ↓

[SSand @H3llo2di0t]

@NVIDIAGeForce #RTXON

[NVIDIA GeForce @NVIDIAGeForce]

We're giving away a Hogwarts Legacy custom wrapped NVIDIA GeForce RTX 5090 to celebrate its official release with DLSS 5 🪄

To enter:
🟢 Share this post
🟢 Comment #RTXON

Terms and Conditions: https://t.co/45T3R732hf

[何笠聊 AI @HeLi8866]

卧槽，有人把几百个用 Claude Opus 5.5 做的视频，连提示词一起打包进了一个 GitHub 仓库。

里面包含：
- 动态图形
- 动画讲解视频
- 3D 场景
- 交互页面
- 甚至能直接玩的小游戏

最香的是每个作品都附了原始提示词和原帖，怎么做出来的一看就懂，照着复刻，或者改成你自己的创意都行。

全部用 HTML、Canvas、SVG 和 Three.js 写出来的，没用视频模型。

最初是 475 个，现在已经更新到 703 条提示词、418 个可以在线看复刻效果的视频。

仓库地址 ：
https://t.co/5PNHW6FiM4

[Loic @LDT0545]

Stop telling Codex, "make it look better."
Stop telling Codex, "add more tests."
Stop telling Codex, "make sure it works."

Vague instructions lead to results you have to redo.

Here are 4 practical prompts to get more useful work out of Codex:

[そう@『n8nの教科書』マイナビ出版 10/22発売 @so_ainsight]

今週GitHubで急上昇したAIリポジトリ10選：

1. impeccable
画面デザインの方向を、コードを書くAIへ言葉で細かく指示できる。仕上がりを整えつつ、公開前に「いかにもAIが作った」無難で雑な見た目もあぶり出せる。
https://t.co/ci7BPjy2BC

2. security-audit-skill
コードに潜むセキュリティ上の弱点を、AIが段階を踏んで洗い出す。見つけた指摘は別のAIがわざと反証を試して裏取りするので、思い込みの誤検出が残りにくい。
https://t.co/SEDrTtpQo9

3. claude-mem
一度閉じると記憶が消えるAIへ、前回までのやり取りを引き継がせる。ひと区切りがつくと内容をAIが要約して保存し、次の会話で必要な分だけ思い出させる。
https://t.co/fZoWpOYPNY

4. ECC
計画→テスト→実装→見直しという決まった進め方を、コーディングAIに仕込む土台。毎回ゼロから教え直さなくても、この手順どおりに回り続ける。
https://t.co/MnxisTgzbU

5. graphify
ソースコードや資料のつながりを、たどれる相関図に変える。どれがどれと関係しているかを一目で追え、そのつながりが元の記述どおりか推測かも分けて示す。
https://t.co/cD2VJQAOHA

6. hyperframes
Webページを作る要領で用意した画面を、そのまま動画に書き出す。商品紹介やデータの見せ方まで、AIが扱う前提で設計されている。
https://t.co/vSJhdJX4df

7. freellmapi
34の無料AI提供元と635のモデル呼び出し口を、1つの窓口に束ねた中継所。混雑すると自動で別のモデルに切り替わり、個人の試し使いに向く。
https://t.co/eQsuEMABLh

8. claude-seo
サイトのSEO対策を、Claude Code にまとめて任せられる。表示速度まわりの計測から、AI検索に引用されやすいかの診断、レポート作成まで守備範囲が広い。
https://t.co/2bXkgv6cpr

9. TradingAgents
役割を分けた複数のAIが議論して、金融トレードの判断を練り上げる。強気と弱気の担当が賛否を戦わせる構成で、投資助言ではなく研究用に公開された。
https://t.co/6NhoZixNvo

10. anthropics/skills
ClaudeにPDFやExcelなどの作業手順を覚えさせる見本集を、Anthropic自身が公開。実際に文書処理を支えているスキルも、作りの参考として添えてある。
https://t.co/ZoYJKevxF4

10件の詳細はリプ欄へ👇

[Hoodie @HoodieFade_]

After Andrej Karpathy released autoresearch, where an agent runs experiments in a loop on its own, I packed his method into one prompt that turns Opus 5.5 into a graph and can carry almost any task to the finish.

→ writes a check that can actually fail, first
→ splits the task into parts
→ runs the independent parts in parallel
→ loops each one until it passes the check
→ sends back only the part that failed
→ turns every mistake into a rule for next time
→ calls you only for the step that can’t be undone

Throw it at Opus 5.5 with the task you’ve been putting off for a week, and you’ll see the difference in one run.

The full prompt is in the comments.

How to tune it for your own work is in the article below. Save it before it gets lost ↓

[xsmryze @xsmryze]

THIS IS AN ACTUAL F*CKING GOLDMINE

Anthropic just shared one of the best tricks for Claude Code.

The idea: run Sonnet, Haiku 5.5 and Opus 5.5 at once, each one doing only the job it's best at.

Better results and way fewer tokens, because every task lands on the right model.

You just launch Claude Code like this:

claude --model sonnet --advisor opus

here's the split:

→ Sonnet 5.5 runs the session, writes the code and applies the fixes
→ Haiku 5.5 swarms the repo in parallel: search, grep and diff audits
→ Opus 5.5 stays on call as advisor for the big calls and signs off on the diff
→ you stop burning Opus context on work that doesn't need it

Opus only steps in at three moments:

→ before a plan locks
→ when the same error shows up twice
→ before calling it done

Sonnet builds. Haiku swarms. Opus reviews.

JEV engineering is the same move one layer down: the forks that need no thinker (which file, which tool, retry or stop) go to JEV in milliseconds, and the big models only see the ones that split

the full tree
> Sonnet 5.5 runs the main session and coordinates the work
> search maps the repo on Haiku 5.5, read-only
> grep finds call sites on Haiku 5.5 in its own context
> audit checks the diff on Haiku 5.5 in a throwaway worktree
> Opus 5.5 on call as advisor, reviews the synthesized diff before sign-off
> JEV routes micro-forks in milliseconds

paste the tree and this prompt into Claude Code ↓

"Reconfigure my Claude Code setup around this tree:
1. Run the main session on Sonnet 5.5 with Opus 5.5 as advisor.
2. Create three Haiku 5.5 subagents in .claude/agents: search (maps the repo), grep (finds call sites), audit (checks the diff).
3. Set isolation: worktree on audit so its checks never touch my working branch.
4. Add one rule to CLAUDE.md: delegate every repo search and test run to the Haiku 5.5 subagents to keep the main context small.
5. Route fast deterministic forks (tool choice, path selection, retries) through JEV.
Show me every change as a diff first. No edits until I say go."

↳ https://t.co/YqkjQiqRGv

save it, it'll come in handy.

[SSand @H3llo2di0t]

@leopedrosa1404 저요

[あくめたん🔞 @mesuinusan]

油断した瞬間に馬チンで奥潰された結果❤︎

[SSand @H3llo2di0t]

@ptlxl2 비계 가고 싶습니다~

[今日はこれにしよっと @kyo_kore_ni]

目の下のほくろ完全に一致してるやん

4626351

[ツイハイブ動画保存ランキング @twixive]

ついったー 動画保存ランキング24

TwiXive
https://t.co/KEnJTLLQtM

CosXive
https://t.co/9zvHXTQl3W

ブクマ推奨したほうが良いよー

[咲茉❄♡(｡☌ᴗ☌｡) @yukimelt12]

ジャンル別Twitter保存ランキングサイトおすすめ3選

TwiXive
https://t.co/h89wan8Oyz
オールジャンルで王道！

CosXive
https://t.co/Wc0h5HpMja
コスプレイヤー好き必見！

TwiIdol
https://t.co/AGkPsclVel
アイドル特化で可愛い！

ブクマ推奨だよ～