FENRO

AI researcher & builder | sharing what actually works

[FENRO @FENRO0]

The "after" nobody talks about:

no sponsored row. no promo tiles. just your apps.

A coding agent that cleans a TV and builds the launcher in one go is where this is heading.

(Concept render.)

[Gathin (Ø,G) @gathint]

Vibe coded my parents' TV this afternoon!

It was showing a sponsored ad before you could even get to Netflix.

Gave Claude Code the model number, it found the TV on wifi, removed 25 Xiaomi packages and wrote a new launcher.

Looks like an Apple TV now lol

[FENRO @FENRO0]

4,700 strategies studied. Cool. But the bottleneck isn't finding strategies anymore, it's trusting them.

Same pattern I use with Claude Code agents: one model builds the bot, a cheaper one only tries to break it. Overfit, slippage, regime shifts. If it survives, it ships.

Verification beats discovery.

[Daniro @Dan1ro0]

https://t.co/IXQgL35zkj

[FENRO @FENRO0]

The schoolboy isn't the story. The pattern is.

Worker model does the job. Cheap model only answers "true or false."

Verification is way cheaper than discovery, so you get reliability without paying frontier prices on every step.

Steal this architecture, not the hype.

[Ackerman @Yarilo7brigada]

It is becoming f*cking dangerous

A 15-year-old schoolboy from China found instructions on how to launch 300 Claude Code agents so that while he’s at school they would trade, and he connected them to a verification layer so that none of them could screw him over.

200 agents collect and write data simultaneously

Every claim comes with a link to a snippet of the source

A separate, cheaper model checks whether the source actually confirms the fact

Failed check → the agent redoes it. Still not confirmed after 3 attempts → goes into a separate list for a human

Everything that passes immediately drops into an Obsidian vault as notes

The main trick is role separation. One model does the work, another only decides “true or false.” Verifying a fact against a source is much simpler and cheaper than finding it in the first place

A team of analysts would bill for weeks for this. He did it in a single run

The same Second Brain + swarm scheme that keeps circulating

[FENRO @FENRO0]

@SawyerMerritt Nice Tesla Roadster

[FENRO @FENRO0]

Future fun Roadster demos will include flying over the Snake River or maybe Grand Canyon and landing on its wheels and exceeding half the speed of sound......

[Cyber Humanoid @cyber_humanoid]

🤣🤣🤣

[FENRO @FENRO0]

@Tesla Let's do the next one in 0.5 seconds

[FENRO @FENRO0]

@Teslaconomics My guy is one Tesla away from proposing 💀

[FENRO @FENRO0]

@Tesla new Roadster just demonstrated a
staggering 0-60 mph run in 0.81 seconds, with @SpaceX -derived cold-gas thruster technology helping turn the EV into something closer to a rocket on wheels.

The system uses high-pressure compressed air and rapidly controlled thrusters to add propulsion and stabilize the car during extreme maneuvers.

Tesla also showed the Roadster using its thrusters during an aerial demonstration, where the car left the ramp and used the system to control its attitude before landing.

Tesla engineer Lars Moravy said the team had beaten the one-second figure shown during the presentation, recording the 0.81-second 0-60 mph run.

If that performance reaches customers in production form, the Roadster would operate in acceleration territory beyond today's quickest production hypercars.

Would you trust a four-wheel rocket capable of hitting 60 mph in less than a second?
What are your thoughts?

[Tesla @Tesla]

Roadster event livestream https://t.co/G0jU4mWfid