\Follow your dreams/
AUKILAND
Joined February 2021
- Tweets18.9K
- Following5.2K
- Followers919
- Likes25.4K
Winnie retweeted
You can now check your own phone for Pegasus, for free.
Zero Breach Toolkit looks for traces of known government-grade spyware, including Pegasus, Predator, Graphite and Candiru, on Windows, Mac, Android phones and iPhone backups.
It's read-only, makes zero network requests during a scan, and never uploads anything. Every report says how strong the evidence is and what it couldn't check. A clean result is never sold to you as "you're safe."
No technical experience needed. The guide walks you through it in about 20 minutes.
github.com/interplains/Zero-…
Winnie retweeted
Codex is draining Pro plans like a thief in the night.
Same work now burns your weekly allowance in hours. Sudden drops. Invisible usage. $100–200/mo for broken limits.
Claude just works. Better. More reliable. Money goes further.
#ClaudeCode #CODEX #OpenAI
🤖 Made with AI
Codex is draining Pro plans like a thief in the night.
Same work now burns your weekly allowance in hours. Sudden drops. Invisible usage. $100–200/mo for broken limits.
Claude just works. Better. More reliable. Money goes further.
#ClaudeCode #CODEX #OpenAI
🤖 Made with AI
Winnie retweeted
🚨 OpenAI, please listen to your Pro users.
I've been getting so many messages from frustrated users about the reported 20x to 10x Pro limit cut, and honestly, I understand their frustration.
Some were already struggling with the existing limits. Now they're seriously considering switching to Claude.
It's disappointing to see people paying for Pro and still feeling restricted when they need these models most.
OpenAI, please take this feedback seriously. Don't make your most loyal users feel like they're getting less for their money. Listen to the community and reconsider these limits before more people decide to leave.
Winnie retweeted
codex usage should be renamed to drainage because it drains faster than it can be used
Winnie retweeted
this is getting f*cking dangerous...
REA creator just dropped 20 GitHub repos to build a f*cking reverse engineering studio:
[01] analysis core
> REA: a single MCP that plugs into everything github.com/morluto/rea
> Ghidra: decompiler, free github.com/NationalSecuri…
> GhidraMCP: lets your agent drive Ghidra github.com/LaurieWired/Gh…
> ida-pro-mcp: hooks your agent into IDA Pro github.com/mrexodia/ida-p…
[02] mobile & apps
> jadx: turns Android APKs back into Java github.com/skylot/jadx
> Apktool: take APKs apart and put them back together github.com/iBotPeaches/Ap…
> Frida: hook into apps while they run github.com/frida/frida
> ILSpy: decompiles .NET github.com/icsharpcode/IL…
[03] binary & low-level
> radare2: RE framework that lives in your terminal github.com/radareorg/rada…
> x64dbg: debugger for Windows github.com/x64dbg/x64dbg
> ImHex: hex editor with its own pattern language github.com/WerWolv/ImHex
> angr: symbolic execution engine github.com/angr/angr
[04] network & runtime
> mitmproxy: sits in the middle and reads the traffic github.com/mitmproxy/mitm…
> dnSpy: debug and edit .NET apps github.com/dnSpyEx/dnSpy
> rizin: the radare2 fork github.com/rizinorg/rizin
> raddebugger: the debugger from Epic Games github.com/EpicGames/radd…
[05] rebuild & verify
> awesome-ai-reverse-engineering: 122 repos, every one graded github.com/zhuyansen/awes…
> awesome-reverse-engineering: curated by the guy who made REA github.com/morluto/awesom…
> REA workflows: ready-made investigation prompts, ship with REA
> clean-room loop: SPEC.md, oracles and checks until it matches
how it runs: binary -> REA -> SPEC.md -> rebuild -> oracle -> retry
save this, point it at any app and watch it explain itself.
Winnie retweeted
🚨 BREAKING NEWS: Gmail Users Need to Read This!
If you have a Gmail account, you need to read this.
Google’s AI is now rifling through your inbox emails and attachments, bank statements, tax docs, medical letters, the whole stack. It was enabled by default, and that quiet rollout is now facing a class-action lawsuit.
Here are 5 steps to turn it off because the kill switch is buried in two different spots:
Winnie retweeted
BREAKING: Claude Code and Codex can now QA your app before you launch.
Every bug and dead end gets a screenshot. The agents fix them all, then rerun to prove it.
Copy this QA prompt:
Winnie retweeted
🚨 BREAKING: Claude Code can now audit your whole stack like a $217,000-a-year security engineer.
Open Claude Code in your repo and run these 10 prompts.
They include 11 free open-source security tools:
Winnie retweeted
This free AI tool tries to hack your app before real hackers do
Strix is an open-source penetration testing tool that uses autonomous AI agents to find, exploit and verify security vulnerabilities, then suggest fixes
It’s like having an entire team of ethical hackers testing your code around the clock
Repo: github.com/usestrix/strix
Winnie retweeted
Every AI-built website looks the same: Inter font, purple-to-blue gradients, cards inside cards, gray text on colored backgrounds.
Impeccable fixes that. 83K stars.
It gives your coding agent a real design vocabulary and checks its work:
→ /impeccable init learns your product, audience and voice before designing anything
→ /impeccable critique reviews hierarchy, clarity and feel
→ /impeccable audit checks accessibility, performance and mobile
→ /impeccable polish does the final pass before you ship
→ bolder, quieter, typeset, layout, animate and 17 more commands
→ 61 rules that catch the usual AI-design tells, and they run with no AI and no API key
Install from your project folder:
npx impeccable install
Then run /impeccable init in your AI coding tool.
Apache-2.0.
github.com/pbakaus/impeccabl…
Winnie retweeted
🚨 Tibo, WHAT THE FUCK is going on with Codex?
Reports of insane quota burn are piling up. I pay $400/month for TWO Pro accounts, and BOTH weekly quotas vanish in ONE day.
Enough hype. Investigate the limits and explain what changed.
@thsottiaux @OpenAI @OpenAIDevs
Something shady is happening with GPT-6.1 Sol usage limits inside OpenAI Codex since Friday:
Devs on Plus and $200 Pro are reporting a massive silent nerf:
- 5-hour Codex limits draining 4x–5x faster on the exact same workloads
- Sol Low/Medium burning to 0% in 30 mins (down from 2+ hours last week)
- Single merge conflicts eating 15%+ and idle resets waking up at 0%
Are you seeing Codex limits vanish faster this week?
Winnie retweeted
Cloudflare open-sourced the security audit skill that seeded its own vulnerability hunting harness. Your coding agent can now run it on your code.
How it works, in 6 phases:
→ maps your codebase
→ hunts for bugs area by area so nothing gets skipped
→ sends every finding to a fresh agent that didn't find it, to confirm it's real
→ writes structured results
→ verifies each record again, independently
→ writes the final report
You get a findings file split into confirmed, needs validation and rejected, so you fix the real problems first.
Install:
npx skills add github.com/cloudflare/securi… --skill security-audit
Then open your agent in your project and type: "security audit this codebase"
MIT licensed, 31.3K stars.
Winnie retweeted
🚨 Something is seriously wrong with Codex usage limits.
We reset.
We run a few coding tasks.
And suddenly, a massive chunk of our WEEKLY quota is gone.
Users are also reporting faster 5-hour limit depletion and weekly quotas disappearing sooner.
This is nowhere near the usage experience we had before. 👀
Winnie retweeted
REA is most dangerous thing on the internet right now...
It lets your AI agent reverse engineer any app, down to the binary
If you use it correctly, you can rebuild any feature you pay for, for FREE
In this article, I show you how:
Winnie retweeted
REA 作者把逆向提示词公开了
这踏马有点猛
复制提示词粘贴给 Claude Code、Codex、Cursor、Muse Code，直接让 AI 帮你干逆向。
安卓 APK、iPhone App、Windows EXE，固件、闭源软件也没问题
提示词和用法在下面，拿走不谢！
Winnie retweeted
Every vibe coder's security prompt:
Bookmark it. paste it into Claude Code before you launch:
"My vibe-coded app is about to get hacked.
- Move every API key out of the frontend
- Rotate any key that ever touched GitHub
- Turn on row-level security on every table
- Check auth on every API route, server-side
- Rate limit login, signup and anything that costs money
- Validate every input on the server
- No string-built SQL, use parameterized queries
- Lock CORS to my own domain
- Make cookies httpOnly, secure and sameSite
- Hash passwords with argon2 or bcrypt
- Never trust a user ID sent from the client
- Hide stack traces in production
- Scan dependencies for known vulnerabilities
- Sdd security headers
- Set spending limits on every paid API
- Find every hole before someone else does."
Winnie retweeted
We're doing the largest Bitcoin mining giveaway we've ever run.
Antminer S23 Hydro AND Antminer S21j XP Hydro.
1,058 TH/s. $24,500 of hardware. Two winners.
If someone you refer wins, you win a miner too.
And everyone who enters gets a bonus gift when the giveaway ends (entries close Friday, October 9).
How to enter:
1) Follow, like, repost, comment
2) Fill out the form in the comments
Winnie retweeted
this might be the only prompt you need for high-end motion graphics with Claude Opus 5.5.
it turns Claude into a full motion design pipeline:
• studies reference videos frame by frame
• storyboards before animating
• builds scenes in GSAP + Three.js
• renders and critiques every section
• checks motion, contrast, audio and transitions
• keeps iterating until the final video passes the quality bar
it also uses this open-source motion kit:
github.com/echris6/motion-vi…
full prompt below.
