Free Radical retweeted
Elon Musk called his own father "the most terrible human I've ever known." What his father did to his stepdaughter is one of the darkest family stories in modern history.
Errol Musk (Elon's father) raised a girl named Jana from the age of 4 when he married her mother. He was her stepfather for decades. He watched her grow up in his house.
Then he had a child with her.
Jana was 30. Errol was 72. A man who raised a girl as his daughter had a baby with her. Then he had a second child with her.
When reporters asked Errol about it, he showed no remorse. He said the only thing that mattered was that the child was "beautiful."
Elon found out like the rest of the world. Through the press. He described his father as a man capable of "almost every crime you can think of" and said he was evil.
He has said that his father would deliberately plan horrible things and execute them with precision. Not out of impulse. Out of design.
Elon grew up in this house. Under this man. Being shaped by someone he later called the worst person he's ever met.
People look at Elon and see the rockets, the wealth, the companies. They don't see the household he escaped from. A home run by a man who would eventually cross a line that most people can't even process.
Every builder is running from something or toward something. Sometimes the darkest starting point produces the brightest trajectory.
Free Radical retweeted
If I had 6 months to become an Agentic AI Engineer.
I'd do this.
Stage 1: Python + Async Foundations
asyncio, FastAPI, event-driven architecture, error handling, API integration patterns.
Stage 2: LLM Fundamentals for Agents
Context management, model routing, token economics, latency tradeoffs, failure modes.
Stage 3: Tool Calling + Structured Outputs
Pydantic validation, function calling schemas, error recovery, dynamic tool discovery.
Stage 4: Memory + State Management
Short-term buffers, long-term vector recall, context compression, cross-session sync.
Stage 5: Single Agent Workflows
ReAct loops, plan-and-execute, self-reflection, iteration limits, graceful degradation.
Stage 6: Multi-Agent Orchestration
LangGraph/CrewAI, supervisor patterns, message passing, conflict resolution, handoffs.
Stage 7: Human-in-the-Loop Systems
Uncertainty detection, approval gates, audit trails, resume logic, intervention points.
Stage 8: Evaluation + Quality Assurance
Automated eval harnesses, LLM-as-a-judge, regression testing, hallucination metrics.
Stage 9: Observability + Tracing
Distributed tracing (LangSmith/Arize), cost dashboards, latency monitoring, alerting.
Stage 10: Security + Guardrails
Prompt injection defense, output filtering, PII redaction, sandboxed execution, compliance.
Stage 11: Production Deployment
vLLM/SGLang, Kubernetes scaling, CI/CD for agents, canary releases, rollback strategies.
Stage 12: Open Source + Portfolio
Ship autonomous agents publicly, write architecture docs, record demos, contribute to libs.
Most people stay stuck watching tutorials.
Builders get hired.
(Bookmark it)
Free Radical retweeted
A Coforge Public Library opened 5 minutes from where I live in Delhi. So excited for me and the baby.
Good collection. Really well designed and spacious. Lots of reading space. There's a separate kids room as well.
No fees. Refundable deposit of โน1,000 to start borrowing books. One at a time.
Such a good and powerful CSR initiative
Free Radical retweeted
i have been a big article and essay enjoyer for 7 years.
i have probably read more than 10,000+ essays online
below is a thread of my favourite essays or articles of all time (that i remember)
pls drop your favourite ones below.
Free Radical retweeted
What are the ways in which you analyse high agency & ownership in a potential hire while screening them?
Would love to learn models others have used successfully to gauge candidates
Free Radical retweeted
Overheard at a bar in Palo Alto. Two guys, late 40s, both visibly funds. One of them says โIโm done. I sold everything.โ The other one nods slowly and says โthe Mag 7?โ and the first guy says โno, the dignity.โ Long pause. He keeps going. โI bought Nvidia at $14 and I sold it at $19 because I thought it had gotten ahead of itself. I bought Tesla in 2013 and sold it for a Honda Civic. I bought Meta in November 2022 the day before it ripped and sold it in December for a 3% gain. I have been right about every company in this cycle and wrong about every stock.โ His friend orders another drink. โWhat are you doing now.โ First guy stares at the ceiling for a full ten seconds. โIโm just buying the index and lying about it on X.โ Friend laughs but itโs the laugh of a man who recognizes himself. They sit there. Neither of them looks at their phones. A waitress brings the check. The Bloomberg on the wall above the bar shows the Nasdaq up 0.4% on the day. Neither of them looks at it. Theyโve stopped looking at it. Thatโs the trade.
4. Tidur dan bangun di jam yang sama selama 30 hari, termasuk weekend.
Pola tidur yang berantakan sering jadi penyebab utama badan gampang capek dan susah fokus. Konsistensi yang kelihatannya membosankan justru bisa bantu reset tubuh dan ngembaliin energi yang sempat hilang.
Free Radical retweeted
Anthropic engineer:
"You're not supposed to prompt Claude. You're supposed to build a system that prompts itself."
this is one of the best workflows I've seen in a long time
in this video he breaks down exactly how most people are using Claude:
- the 14% you lose to CLAUDE.md before typing a word
- the plugins that 95% of users have never installed
- the caching setup that keeps it at 95% hit rate and almost free
- why starting every chat from zero is the slowest way to use Claude
if you've been using Claude for more than a month and never left the chat window, you've been using one project when you could be running a team of them
instead of another show tonight, watch this
make sure to bookmark it before it gets lost in your feed
full guide in the article below
Free Radical retweeted
Dan Koe's work will change your life forever.
His writing takes 100s of hours to read. I've gone through it so you don't have to.
12 ideas. 12 opportunities to upgrade your mind.
Free Radical retweeted
SpaceX was founded under the belief that a future where humanity is out exploring the stars is fundamentally more exciting than one where we are not.
Watch @ElonMusk and @Boca_Bill_R discuss SpaceXโs mission
Free Radical retweeted
To put it simply: Mission beats money.
โข Meta is building AI for commercial dominance.
โขย xAI's building AGI to "maximize truth-seeking."
Engineers want their work to shape humanity's future.
But the second factor is even more powerful:
Free Radical retweeted
I've tried all (61 ๐ตโ๐ซ) AI Coding Agents & IDEs
[Emergent, CodeRabbit, Anything, Zed, Factory, Cursor, Windsurf, Wrapifai, Copilot, Lovable, Bolt, v0, Replit, MarsX, Canva, Devin, Github Spark, Figma Make, Cline & more]
The most complete list ever made (with demos & notes):
Free Radical retweeted
๐ฟฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ ๐นฬฒ.๐ถฬฒ ๐ฬฒ๐ฬฒ ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ขฬฒ ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ๐ฬฒ!
Proud to announce our most significant framework overhaul since its inception. See what it's all about at Parlant(io).
This version transforms Parlant into a production-ready conversational AI framework for customer-facing applications.
With dramatic performance improvements, reworked developer experience, and enterprise-grade security features, Parlant 3.0 is ready to fix your hardest AI consistency issues and power your most critical customer-facing applications.
"๐๐บ ๐ง๐ข๐ณ ๐ต๐ฉ๐ฆ ๐ฎ๐ฐ๐ด๐ต ๐ฆ๐ญ๐ฆ๐จ๐ข๐ฏ๐ต ๐ค๐ฐ๐ฏ๐ท๐ฆ๐ณ๐ด๐ข๐ต๐ช๐ฐ๐ฏ๐ข๐ญ ๐๐ ๐ง๐ณ๐ข๐ฎ๐ฆ๐ธ๐ฐ๐ณ๐ฌ ๐ต๐ฉ๐ข๐ต ๐ ๐ฉ๐ข๐ท๐ฆ ๐ค๐ฐ๐ฎ๐ฆ ๐ข๐ค๐ณ๐ฐ๐ด๐ด! ๐๐ฆ๐ท๐ฆ๐ญ๐ฐ๐ฑ๐ช๐ฏ๐จ ๐ถ๐ด๐ช๐ฏ๐จ ๐๐ข๐ณ๐ญ๐ข๐ฏ๐ต ๐ช๐ด ๐ฑ๐ถ๐ณ๐ฆ ๐ซ๐ฐ๐บ!โ โ Vishal Ahuja, JPMorgan Chase
I know many have awaited the improvements in this new release โ and many have helped test it. We do it all for our users, as we've become obsessed with the massive challenge of getting customer-facing AI agents under control. Parlant (@EmcieCo) is continuing to lead this endeavor.
If you haven't tried it yet, you should, as it's like nothing you've already tried. Check out the blog below for a summary of the release and what's coming next (1st comment)
Free Radical retweeted
Andrew Huberman once said:
"The brain is like a muscle. If you don't use it, you lose it."
A few years ago, I could barely focus for 2 minutes.
Today, 12-hour workdays feel effortless.
Here are Huberman's 7 principles for superhuman focus that changed my life:
Free Radical retweeted
Joe Rogan just dropped bombshells on interdimensional aliens, the Anunnaki, and the Book of Enochโwith a sitting member of Congress.
Rep. Anna Paulina Luna has seen evidence of โinterdimensional beings.โ
She thinks the Anunnaki are real.
And sheโs convinced the deep state has reverse-engineered alien tech.
๐งตTHREAD
Free Radical retweeted
Elon Musk built rockets for 2% of NASAโs cost.
Jeff Bezos built the fastest supply chain in history.
Both use a 2,300-year-old method to turn โimpossibleโ into reality while everyone else follows the rules.
Hereโs how First Principles thinking works (and how to use it):
Free Radical retweeted
The no bullshit guide to raising angel funding/venture capital as an outsider.































