Radu17e

[Tyler Todt @tyromper]

My buddy in Vegas had his pool pump break.

He called a repair guy.

The guy said it was a HUGE problem & around an $8,000 job & he could get started right away.

My buddy called another guy after.

He showed him exactly what was wrong & said he even had a used spare part that would save him money if he wanted.
Allin the job was $700.

My friend not only tipped him $1,000 after, but has probably referred him $100,000 in business the last year or two by telling this story!!

It's a farce you should LIE, CHEAT, STEAL, & SCREW PEOPLE OVER to get ahead in life.

Do the right thing & have integrity because it's the right thing & also because it's just better for long term business & life!!

[Rustavi @Rustavi]

🚨 BREAKING: Big news from Finland. Traficom, the country’s official transport authority, just released one of the most honest and thorough assessments of Tesla’s FSD (Supervised) in Europe.
Key highlights:
✅ “The system has been observed to often make safer decisions than a human driver”
✅ “Its response capability in many situations is faster than that of a human”
✅ “The overall view of the system is positive”
Traficom is still assessing the provisional approval granted by the Netherlands (RDW) and has not yet decided on recognition in Finland. They’re taking a careful, evidence based approach and could move faster after the key EU meeting on June 30.
Finland already has ~6,500 FSD capable Teslas on the road. This positive report is a strong step forward and contrasts nicely with some of the more fear-driven narratives elsewhere in Europe.
Full article from Traficom (published today):
https://t.co/sHj8Q9Rm16
Proper regulation based on real data. This is how it should be done. Looking forward to the next steps. 🚀
#Tesla #FSD #AutonomousDriving #Finland

[Joe Tippens @JoeTippen]

This is nothing short of a miracle.

Dr John Campbell breaks down the study of an 83yr old woman with stage 4 breast cancer that had metastasised to the liver, spine and bones.

Usually a death sentence.

She took a daily dose of 222mg of FenBen for 8 months. Which normalised her liver enzymes. The tumor marker dropped from 316 to 36.

There was an absence of any abnormal metabolic activity indicative of cancer. Please like, share, and follow my page. Information like this need to be heard and seen by everyone.

[Joe Tippens @JoeTippen]

This is nothing short of a miracle.

Dr John Campbell breaks down the study of an 83yr old woman with stage 4 breast cancer that had metastasised to the liver, spine and bones.

Usually a death sentence.

She took a daily dose of 222mg of FenBen for 8 months. Which normalised her liver enzymes. The tumor marker dropped from 316 to 36.

There was an absence of any abnormal metabolic activity indicative of cancer. Please like, share, and follow my page. Information like this need to be heard and seen by everyone.

[Natural Immunity FTW @NaturallyFTW]

🚨 This is INSANE.

CANCER has been Cured via something found in Japanese forests.

• Literally ERADICATED TUMORS IN A SINGLE DOSE
• Head to Head against chemo & immuno — worked Way Better
• No bad side effects
• Prevented Recurrence: the cancer COULD NOT be brought back

All this was possible via a single bacterium isolated from the intestines of Japanese tree frogs - Ewingella americana. 🐸

➡️ When a single dose of the E. americana was injected into the veins of mice bearing colorectal cancer, the tumors were 100% Rapidly, Completely eliminated.

➡️ No side effects (except mild necessary inflammation, gone w/in 72 hrs). No signs of long-term toxicity (multi-month observation period).

➡️ It also induced immune memory against rechallenge (prevented cancer from coming back).

➡️ And importantly: Zero colonization in normal organs + GONE from the body w/in 24 hours.

➡️ It's Highly likely these results will translate well to humans & to other (especially solid tumor) cancer types.

I pay attention to cancer studies (have for decades) and these are actually an INSANE results.

✅ Why E. americana is the perfect CANCER KILLING MACHINE:

• E. americana thrives in the same (low oxygen, immunosuppressive) environment tumors thrive. And proteins + metabolic byproducts that cancer cells produce actually support the growth of E. americana, right there near the tumors.

• Tumor blood vessels are poorly structured, very permeable/leaky. Because of this, E. americana can easily exit the bloodstream and enter the tumor tissue.

IN OTHER WORDS: when this bacterium is injected, a perfect symphony transpires where it goes DIRECTLY to tumors & eliminates them  — while leaving normal cells & organs alone. 😯

✅ HOW IT WORKS:

E. americana eliminates cancer via 2 mechanisms:

• Directly damages cancer cells.

• Activates immune system — E. americana attracts T cells, B cells, and neutrophils to the tumor area (which then eliminate the cancer cells).

✅ WHY THIS IS LIKELY TO WORK IN HUMANS:

Curing cancer via bacteria has been tried before. Here's what we know.

⚫️ Efficacy results shown in mice usually DO translate to humans— ie. bacteria that accumulate in mice tumors usually do the same w/in a human body
⚫️ Toxicity results shown in mice also show up similarly in humans
⚫️ There has Never been a mice study showing results this good OR w/o toxicity (the other ones showed a lot of toxicity & even death in the mice)
⚫️ In other bacteria cancer studies: the bacteria DID accumulate in normal organs. This one does not.
⚫️ IMPORTANTLY: all other bacteria that have been tried thus far were bioengineered/GMO.
⚫️ E. americana is naturally occurring & far less likely to lead to bad side effects.

So anyway. Given these INSANENELY EFFECTIVE & safe results...they surely will FAST TRACK human trials on E. americana (perhaps on those who have nothing to lose and everything to gain) Right? ...Right?!

I doubt it. It'll probably be forever... IF they even let this get to the public.

They'll probably announce some new "miracle" genetic therapy instead, and try to pull all attention & resources toward that.

UNLESS we do something.

Be loud. Share this. Don't let this die down and be forgotten about.

This is one of the most promising "1 & done" type of cancer solutions I've ever seen.

But even if this does become mainstream, Natural Medicine & healthy living will still have it's place. This therapy does require an at least somewhat functioning immune system to work.

And know: there are ways to fix your body. 

Please see my other posts on cancer reversal via high dose IP6 (Inositol Hexaphosphate), large amounts of vegetable juicing (carrots/greens especially), high doses of specific mushrooms (Mesima, certain types of Reishi), etc. 

I've posted tons of studies & reversal reports (often stage 4).

Nature is amazing. Spread the word.

[Joe Tippens @JoeTippen]

Don’t tell Pfizer

🚨 Stage 4 Cancer... GONE in 3 Months — Naturally!

A 73-year-old woman was told there was no cure. Stage 4. “Nothing we can do,” doctors said.

👉 But just 90 days later… her scans showed NO disease detected.

What changed?
Her son went down the research rabbit hole on X and found my posts on IP6 (Inositol Hexaphosphate), juicing, Mesima mushrooms, and Ivermectin.

Here’s what she did ⬇️
• 🥄 IP6: 2 scoops, twice a day on an empty stomach
• 🥕 24 oz carrot juice daily (+ some other juices)
• 🍄 A bit of Mesima mushroom & Olive leaf
• 💉 3 immunotherapy sessions (docs said it wouldn’t cure her)
• 💊 Ivermectin: added as support — we’re seeing more and more remarkable responses when it’s included 👏

⚡ No chemo. No radiation. No Fenben.

And guess what? The cancer disappeared.

This isn’t a one-off story. I’ve been receiving multiple reports of stunning cancer reversals using these exact protocols — especially IP6, juicing, and Ivermectin.

There are also published studies and case reports showing the same thing:
👉 These natural compounds have powerful anticancer effects.

People deserve to know this.
(But shhh… don’t tell Pfizer, or they might “regulate” them 😉) Follow @ZakariaMDv3 .

[Aiden Tech @Aiden_Tech_Ai]

BREAKING: AI can now build you a complete website in 2 hours (for free).

Here are 9 insane Claude Opus 4.6 + Figma Make prompts that create $5,000 websites in 2 hours:

(Save this before your competitors do)

[Alif Hossain @alifcoder]

🚨 HOLY SH*T: The most complete Claude Code setup just got open-sourced.

91K+ stars.

It’s called everything-claude-code.

Inside:

→ 28 agents
→ 116 skills
→ 59 commands
→ 15+ hooks
→ 34 rules (6 languages)
→ MCP integrations
→ Built-in security scanner

This is basically a full AI engineering system.

Link 👇

[Akshay 🚀 @akshay_pachaar]

https://t.co/SSSIK3BX4z

[Jaynit Makwana @JaynitMakwana]

Instead of watching a 2-hour movie, watch this Claude FULL COURSE (Build & Automate Anything):

[Aakash Gupta @aakashgupta]

There are 6 levels of making Claude Code run autonomously, and most people are stuck on Level 1.

Level 1: Kill the permission prompts. Run claude --dangerously-skip-permissions. One flag. Now it stops asking “Can I edit this file?” every 30 seconds while you’re checking Slack.

Level 2: Context window management. Claude Code now supports 1M tokens. Use /clear between tasks. Run /compact at 60% usage instead of waiting for auto-compaction to fire at 90% when the model is already forgetting your instructions.

Level 3: Subagents. The reason it stops at 15 minutes: everything runs in one context window. Subagents run in separate contexts. Build a looping todo command, each task executes in its own window. Builds, tests, and git operations never touch the main conversation. 2+ hours autonomous with zero intervention.

Level 4: Ralph Wiggum loop. Official Anthropic plugin. Claude works, tries to exit, a Stop hook blocks the exit, re-feeds the same prompt. Each iteration sees modified files and git history from previous runs. One developer ran 27 hours straight, 84 tasks completed. Geoffrey Huntley ran one for three months and built a programming language with a working LLVM compiler.

Level 5: Karpathy’s AutoResearch. On March 7, Karpathy pushed a 630-line script to GitHub and went to sleep. Woke up to 100+ ML experiments completed overnight. 25K stars in five days. The difference from Ralph: structured eval loops. Define a metric, run, measure, analyze failures, improve, repeat. One Claude Code port took model accuracy from 0.44 to 0.78 R² across 22 autonomous experiments.

Level 6: VPS + OpenClaw for 24/7. Your laptop lid closing kills everything. Run Claude Code on a VPS inside tmux. Detach, close your laptop, come back tomorrow to a finished diff. OpenClaw (247K GitHub stars) takes it further: a persistent gateway connecting LLMs to your real tools, running 24/7 across messaging, email, git, and calendars. Jensen Huang at GTC called it “probably the most important release of software ever.”

The unlock at every level is the same: give Claude a way to verify its own work.

[Evan Luthra @EvanLuthra]

🚨BREAKING: ANTHROPIC IS GIVING AWAY THE SAME CERTIFICATION THAT DELOITTE IS MASS-TRAINING 15,000 EMPLOYEES TO GET.

It costs $0. You need a laptop. That's it.

It's called the "Claude Certified Architect."

Think of it like the AWS cert but for AI.

If you were around when AWS certs started, you know what happened. They went from "cool to have" to "you're not getting hired without one." That took about 5 years.

This is going to happen way faster.

Look at who's already moving:

Accenture - training 30,000 people on Claude
Cognizant - rolled it out to 350,000 employees
Deloitte - opened Claude access to 470,000 people
Infosys - anchor partner

These aren't startups experimenting. These are billion dollar consulting firms restructuring their entire workforce around Claude.

And the certification they need? You can take it right now from your bedroom.

Let me be real though. This is not one of those "watch 2 videos and get a badge" type certs that nobody respects.

This thing is hard.

60 questions. 2 hours. Proctored. Webcam on. No breaks. No googling.

They drop you into real scenarios like designing a customer support agent that handles refunds or setting up Claude in a CI/CD pipeline. The wrong answers look right on purpose. They're the exact mistakes real engineers make in production.

720 out of 1000 to pass.

People who took it are saying the agentic architecture and multi-agent orchestration sections are brutal.

Most of the exam is about building AI systems that actually work in the real world. Not prompting. Not chatting with Claude. Architecting production systems.

All the prep? Free. Anthropic put out 13 courses on their Academy. No paywall. The cert itself is free for the first 5,000 people. After that $99 per attempt.

How to get it:

1. Join the Claude Partner Network (free) → https://t.co/TWMshPoKDn
2. Start the free prep courses → https://t.co/9OVwtjbvh0
3. Register for the exam → https://t.co/WWFAhSZUVd
4. Take the official practice exam
5. Book the real one when you're ready

It launched 10 days ago. Almost nobody has it yet.

That's the whole point. Get it before it becomes the thing everyone has.

[Charly Wargnier @DataChaz]

Andrej Karpathy (@karpathy), OpenAI co-founder, ex-Tesla AI, "vibe coding" creator.

In just 4 mins, he explains why Claude Skills, MCP servers, and AI agents are past the hype and are now the new baseline for building.

Worth every second ↓

[Dharmik Harinkhede @AiwithDharmik]

🚨BREAKING: Someone just solved Claude Code's biggest problem.

It's called Claude-Mem and it gives Claude persistent memory across sessions.

- You can use up to 95% fewer tokens each time.
- Make 20 times more tool calls before reaching limits.

100% Opensource.

For Repo :

Like + comment " send " + Retweet+
Follow me @Dharmikpawar31 so that it can be auto DM

[Radu17e @Radu17e]

@expertwith_AI @AshikNewazAJ Claude

[Vivo @vivoplt]

- Claude = coding. ($20/mo)
- Supabase = backend. (Free)
- Vercel = deploying. (Free)
- Namecheap = domain. ($12/yr)
- Stripe = payments. (2.9%/transaction)
- GitHub = version control. (Free)
- Resend = emails. (Free)
- Clerk = auth. (Free)
- Cloudflare = DNS. (Free)
- PostHog = analytics. (Free)
- Sentry = error tracking. (Free)
- Upstash = Redis. (Free)
- Pinecone = vector DB. (Free)

Total monthly cost to run a startup: ~$20

There has never been a cheaper time to build.

[Akshay 🚀 @akshay_pachaar]

How to setup your Claude code project?

TL;DR

Most developers skip the setup and just start prompting. That's the mistake.

A proper Claude Code project lives inside a .𝗰𝗹𝗮𝘂𝗱𝗲/ folder. Start with 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱 as Claude's instruction manual. Split it into a 𝗿𝘂𝗹𝗲𝘀/ folder as it grows. Add 𝗰𝗼𝗺𝗺𝗮𝗻𝗱𝘀/ for repeatable workflows, 𝘀𝗸𝗶𝗹𝗹𝘀/ for context-triggered automation, and 𝗮𝗴𝗲𝗻𝘁𝘀/ for isolated subagents. Lock down permissions in 𝘀𝗲𝘁𝘁𝗶𝗻𝗴𝘀.𝗷𝘀𝗼𝗻.

There are two .𝗰𝗹𝗮𝘂𝗱𝗲/ folders: one committed with your repo, one global at ~/.𝗰𝗹𝗮𝘂𝗱𝗲/ for personal preferences and auto-memory across projects.

The .𝗰𝗹𝗮𝘂𝗱𝗲/ folder is infrastructure. Treat it like one.

The article below is a complete guide to 𝗖𝗟𝗔𝗨𝗗𝗘.𝗺𝗱, custom commands, skills, agents, and permissions, and how to set them up properly.

[klöss @kloss_xyz]

Karpathy just outlined the next era of AI.

all over 66 minutes… I broke down his 10 major takeaways so you don’t have to watch the full video (but you still probably should after reading this)

here’s what he said matters most….

→ “I don’t think I’ve typed a line of code since December.” the default workflow for software engineers has changed permanently since late 2025. we don’t write code anymore. we express intent to persistent AI agents for 16+ hours a day

→ he coined “AI psychosis”… the anxiety of knowing you have unused tokens just sitting there. success isn’t measured in your flops anymore. it’s measured in your token throughput

→ the limits aren’t model capability anymore. they’re orchestration skill. the people who know how to direct agents are operating 10x above everyone else using the same tools

let me walk through all of his points…

1. mastery looks different now

Karpathy built a personal agent called “Dobby” that controls his entire home through natural language. persistence + memory + parallel agents = a 2 person team operating like a 20 person org

2. software becomes disposable

humans don’t need custom apps anymore. the customer is no longer the human… it’s agents acting on behalf of humans. entire industries have to account for and refactor for this

3. AutoResearch changes everything

his side project (github .com/karpathy/autoresearch)… fully autonomous research loops. agents edit code, train models, and iterate overnight while you sleep. human only writes the high level goal

4. the skills that matter now

understand that an agent can be both a brilliant PhD level systems programmer and a 10 year old’s unformed mind in the same conversation. and your job is to overcome those challenges and direct your agents. everything else they’ll soon do better

5. specialized models > one giant brain

stop trying to build one know it all mega brain model. the future looks like an ecosystem… diverse adaptable and specialized models built for specific jobs. a team of focused models beats one mega model every time

6. distributed research could disrupt the lab monopoly

imagine thousands of smartphones and computers around the world running AI experiments at the same time… not owned by one company. results are easy to verify but hard to discover.

it’s how open collaboration could disrupt big closed labs

decentralized internet

7. jobs data says something completely different than the narrative

Karpathy looked at all the real data. engineering job demand is still rising. cheaper engineering creates MORE demand, not less. like how ATMs actually created more bank teller jobs

8. open source is the safety net

open models generally lag frontier by 6-8 months but they’re also essential. closed models carry systemic risk from over-centralization.

Karpathy wants ensembles of minds, not 2-3 labs behind closed doors making decisions for everyone

9. robotics will lag badly

the physical world is messy and capital intensive. digital transformation will be orders of magnitude faster.

future prediction… most AI agents will pay humans to act as their hands and eyes in the physical world, creating information markets for real world data to sell between themselves

10. education gets rebuilt from scratch

the core LLM training algorithm fits in about 200 lines of Python. the rest is bloat.

the new model? humans explain concepts to agents once, agents tutor humans infinitely and personally.

write documentation for agents first.

yes, a markdown first file world

his one liner that hits hardest for me…

“I put in just very few tokens… and a huge amount of stuff happens on my behalf”

we’re in the era of autonomous agents.

humans become directors, not doers.

the leverage is insane, but it’s only really available to people who learn how to use it properly

if you’re building with AI now, this is required listening material imo

the ones who move first?

they don’t ask permission

they just do it: master AI

[GREG ISENBERG @gregisenberg]

i heard about a guy in a small town in england who turned his openclaw into a short form video marketing machine

millions of views, steady app downloads, and revenue coming in every day

i needed to find out how he was doing it

1. spin up an ai “employee” using openclaw

2. give it one job like grow your app with tiktokk

3. give it access to tiktokk analytics, a browser to research and image/video tools to create content

4. the openclaw studies your niche and starts generating slideshows and videos

5. every post feeds performance data back into the system

views → hook quality
downloads → CTA quality
revenue → funnel quality

the openclaw then iterates on

- new hooks
- new formats
- new CTAs

until it finds winners

one of his posts hit 170k+ views

and the system keeps improving because the analytics loop feeds back into the content generation

so the agent slowly learns what works

what i like about this is the framing

most people think about ai tools

this is different

you spin up an ai employee

you give it a job

and let it run the loop

thanks to @oliverhenry for coming on the @startupideaspod today

more like this soon, i will share the most interesting stories and gatekeep nothing

this episode was dripping in sauce

i gotta try this and see if it works

kinda wild if it does

watch