Free Speech Duck

Duck You

[Caт 🐝 @CatShoshanna]

Hollywood owes us an apology

[Linus ✦ Ekenstam @LinusEkenstam]

Claude Dev account got a quarter million followers on X in 24 hours 🤯🥹

[Dinesh D'Souza @DineshDSouza]

Tucker’s trajectory:

Netanyahu, bad.

Then, Israel, bad.

Then, Jews, bad.

Then, Islam, good.

Then, sharia, not-so-bad.

Then, Hamas, pretty good.

Then, Bin Laden, not a bad guy.

Then, Iran, good.

Now, Trump, bad.

What to expect, finally: Democrats, good.

[Free Speech Duck @realDuck]

@guideforlovers Woman that make fun of you like this behind your back don’t respect you. A good woman defends her man with her friends. She also has stupid friends. Two red flags

[Braelyn ⛓️ @braelyn_ai]

you probably dont fully understand how serious this Claude Code leak is

> code copyright law has been stable since the 80s
> you cannot legally copy or fork someone's code without permission (licenses)

the caveat is a "clean room" build - start from scratch by people who have never seen the code. it takes too long to build a product from scratch, so it wasn't usually a problem

> enter codegen
> anyone with a Claude Max plan can "clean room" rebuild any repo just by pointing the agent at the tests
> a few months ago, opensource repos started close-sourcing their tests
> a codegen rebuild has never been challenged in court > the legal precedent would have the potential to decimate the concept of Open Source forever

SO
> last night
> claude code leaks
> Sigrid Jin "clean room" rebuilds claude code in Python
> names it Claw-Code

> Reminder: Anthropic sued the last open source tool that used a funny "claw" name

Now?
> Anthropic has the potential to sue this project and put all of software licensing and copyright law into question

> Anthropic might allow corporate greed to effectively put an end to opensource software

> Anthropic's corporate greed might forever kill the software community as we know it today

...
now that you know how serious it could be, the best thing we can do is pressure anthropic to let it go

[Om Patel @om_patel5]

THIS GUY FOUND WHY YOUR CLAUDE CODE COSTS ARE 10-20X HIGHER THAN THEY SHOULD BE

he reverse engineered the entire Claude Code binary. found two hidden bugs that silently break your prompt cache.

BUG 1: if your conversation mentions billing, tokens, or Claude Code internals, the cache breaks on every single request.

there's a hidden string replacement baked into the binary that targets billing attribution codes.

if that string appears anywhere in your conversation history, it replaces the wrong one and your entire cache rebuilds from scratch.

you get charged full price instead of cached price.

fix: run Claude Code via npx instead of the standalone binary.

BUG 2: every time you use --resume, your entire conversation cache rebuilds from scratch. one resume on a large conversation costs $0.15 that should cost near zero.

the system injects tool attachments in a different position on resume vs fresh sessions. this changes the cache prefix and forces a full rebuild. every single resume costs you a one-time hit on your entire context.

fix: no clean fix yet, as it was introduced in v2.1.69. downgrading to v2.1.30 works but you lose months of features.

on a 500K token conversation these two bugs combined can cost you $0.20+ per request.

if your usage has been burning way faster than expected, this is probably why.

[Ziwen @ziwenxu_]

I've been running OpenClaw for 30+ days straight. Burned through 1.5B tokens and nuked my setup 3 times from scratch.

Should have cost me $14,000 in API fees. Actually paid $50.

Browser automation, multi-agent workflows, rate limit hell I survived it all so you don't have to.

[Vaishnavi @_vmlops]

ML interviews ask: "design a fraud detection system"

Most people answer with theory

Top engineers answer with: "here's how Stripe, PayPal & Lyft actually built it"

https://t.co/67BrDNan4w

300+ real case studies...80+ companies....Every industry

[Tobby_scraper @Tobby_scraper]

iOS niches still wide open in 2026:

- Breathing Exercise Apps $70k MRR
- Language Flashcard Apps $85k MRR
- Minimalist Budget Trackers $60k MRR
- Posture Reminder Apps $40k MRR

Boring problems. Serious revenue.

Check Niches Hunter for more ideas!

[Alex Finn @AlexFinn]

Posting "OpenClaw is dead" is the biggest self own in history

It proves you are larping as a tech guy

Every person who has used OpenClaw properly knows it's the most powerful software ever released

Yes it's complicated, but when used correctly it saves you hours a day and gives you unlimited leverage

Saying you think it sucks or it's dead is just you saying you can't figure it out so you're blaming everyone else

Also there has never been a tool in history that has died and people went on Twitter to announce its death

Dead tools die in silence. When n8n died nobody went on X and said n8n is dead. They just stopped using it and moved onto the next tool

The fact that every other post and youtube video is "openclaw is dead" proves OpenClaw is still alive

Half of the 'AI influencers' who said OpenClaw is stupid have already reversed course. The other half I promise you will reverse course over the next year when they realize the tools they've been shilling you are now completely irrelevant.

Jensen Huang, literally the smartest human being on earth right now has said OpenClaw is the most important software in history. The faster you get on board, the faster you'll change your life.

[0xMarioNawfal @RoundtableSpace]

ARCHITECT IS AN AI MODEL THAT TURNS A SINGLE PROMPT INTO AN OPTIMIZED PROJECT PLAN.

Think Jira or Linear, but built for agents instead of humans.

[Fivos Aresti @fivosaresti]

Most people using Claude Code are leaving 80% of its power on the table.

Here's the fix (and it's free):

A developer friend of ours built a 29-agent open-source plugin that turns Claude Code into a full engineering team.

It solves the biggest problem with AI builds...

Most AI-generated code makes future work HARDER.

This plugin flips that with 5 steps:

(broken down into skills)

• Brainstorm step: agents scan your repo and propose approaches with tradeoffs documented
• Plan step: parallel agents fill in gaps, catch edge cases, output a full spec
• Work step: swarm agents build in parallel, test after every change, only commit when green
• Review step: multi-agent code review with P1/P2/P3 triage before you ship
• Compound step: after every build, 5 agents capture the root cause, the fix, and how to prevent it next time…. saved to a searchable KB inside your repo

That last step is how each unit of engineering work makes the subsequent units easier.

If you’re not technical (like me), this is an absolute game changer.

I'm sharing the GitHub link with anyone who wants it.

• Comment "repo"
• Follow me (so I can DM)

And I'll send it over right away.

[Kanika @KanikaBK]

🤯 YOUR OBSIDIAN VAULT is worth $120K/YR & you're getting $0 from it.

GREG ISENBERG just dropped a 1hr MASTERCLASS on turning Obsidian + Claude Code into a 24/7 personal Operating System.

Total Cost: $120/yr
This setup: FREE

Bookmark before it's buried!

[Om Patel @om_patel5]

this PhD student in AI built a 10-agent Obsidian crew to manage his entire life

his brain couldn't keep up. papers, deadlines, meetings, emails, health stuff.

he kept forgetting what he read, losing track of commitments, falling behind on everything.

tried every Obsidian setup out there.

they all required him to maintain the system manually. which is the exact thing he didn't have time for.

so he built something where he just talks and everything else happens automatically.

the possibilities with this are endless

AND other people can contribute and make it better because its OPEN SOURCE

[Max 📟 @MaxNordau]

I'm America First.

That's why I support the rise of China, Russia, and the Islamic Republic of Iran.

Because empowering America's adversaries is what America First is all about.

[Laura Loomer @LauraLoomer]

A lot of people recently commented on how @megynkelly has a rule on her show that her guests aren’t allowed to attack Tucker Carlson.

The reason for this is because Megyn and @TuckerCarlson’s shows are both run by Red Seat Ventures, which is now ironically owned by Fox Corp, which owns Fox News.

Red Seat Ventures wants to have a monopoly over all conservative podcasting, which is why Tucker and Megyn have a vested interest in attacking all of the conservative competition in Independent media.

It’s ironic that Fox Corp now owns Red Seat Ventures. In a sense, the toxic culture and anti-American and anti-Jewish rhetoric coming out of their shows is attributable to Fox Corp.

It appears that the commentators who push the most deranged Jew hate and Islamic sympathizing content are all partnered with Red Seat Ventures.

@redseatventures.

Megyn Kelly has a business interest in not going after Red Seat, as it produces both her show and Tucker’s show. Red Seat Ventures has a total interest in attacking every other conservative commentator with a large following because they want to serve as the gatekeepers for all conservative podcasts.

Megyn and Tucker pretend to be principled, but this is further evidence all they care about is money.

Some of the other people managed by Red Seat Ventures include:

@piersmorgan @imbrettcooper @BillOReilly @JesseKellyDC @seanspicer @RitaPanahi @DLoesch @JillianMichaels @itslinklauren @MarkHalperin @kilmeade @willcain @guypbenson @Gutfeldfox

It almost seems like a deliberate sabotage campaign by Fox Corp to create an anti-Trump media campaign against President Trump outside of Fox News to destroy MAGA and undermine President Trump.

Very deceptive.

Funny how Megyn and Tucker always speak badly about Fox News when Fox Corp owns Red Seat Ventures. Just more deception from the Woke Reich.

[Jaimee Michell @JaimeeUSA]

It’s already happening.

[Ronin @DeRonin_]

I run 10 social media accounts and don't write a single post manually

the secret: a skill graph

30+ markdown files wired together that turned my AI agent into a full content team

where to build it:
- @obsdmd (to write + visualize the graph)
- or just a regular folder of .md files on your desktop

what tools run it:
- claude, chatgpt, or cursor as the AI agent
- @arscontexta plugin for claude code (generates the base structure automatically), find it in article below

the folder structure:

/content-skill-graph
├── index.md (entry point which maps every node)
├── platforms/ (x.md, linkedin.md, ig.md, tiktok.md...)
├── voice/ (brand-voice.md, platform-tone.md)
├── engine/ (hooks.md, repurpose.md, scheduling.md)
└── audience/ (builders.md, casual.md)

each file = one knowledge node
inside each file you add [[wikilinks]] to related nodes

example — inside x.md:
"use [[hooks]] — contrarian hooks perform best here. match [[brand-voice]] but more casual. audience is [[builders]]. write this FIRST, then expand for [[linkedin]]. see [[repurpose]]"

the links are the graphs. the agent follows them automatically

the key file is index.md, your entry point / briefing, not a file list. put 3 things in it:

1. who you are + what this system does
"content system for [your brand]. manages 10 accounts from one idea input"

2. the node map with context
- [[x]] — short-form, hook-driven, 280 chars, 5x/week
- [[linkedin]] — long-form narrative, professional, 3x/week
- [[hooks]] — formulas that stop the scroll
- [[repurpose]] — 1 input → 10 outputs
(every node listed with a one-line description)

3. execution instructions
"when given a topic: read relevant nodes, apply voice + hooks, run repurposing chain, output one native post per platform. each post ready to publish"

you paste this into claude as context → give it a topic → done

now here's the part most people get wrong about the output:

it's NOT 10 copies of the same text reformatted for each platform

it's 10 pieces that each THINK about the topic differently:

> x: contrarian thread, lowercase casual, step-by-step
> linkedin: personal narrative, professional tone, 1500 words
> instagram: 7-slide carousel, visual-first, bold claim on slide 1
> tiktok: 45-sec raw screen recording script
> youtube: SEO title + structured outline, 8-min format

same topic. different angle, hook, voice, structure, format per platform

the graph encodes all those rules. the agent follows them

this replaced $8-12k/mo in content spends

@arscontexta built the framework and I pointed it at content production

summarize:

one flat file gives you a tool (a simple .md file)
a graph gives you a team (a system with 30+ sub-graphs)

if we collect 500+ Likes on this tweet ❤️

I release my full workflow and show you step-by-step how you can setup the same skill graph

hope you loved it.

[GitHub Projects Community @GithubProjects]

Google just open-sourced A2UI.

An open protocol that lets AI agents generate real user interfaces instead of just text.

Agents send a JSON description of the UI → your app renders it with native components.

No HTML generation.
No unsafe code execution.

Just agents that can actually build UI.

[Dave Rubin @RubinReport]

Read this, re-read this, and share it twice…