God of Prompt
RT @godofprompt: R.I.P few-shot prompting.

Meta AI researchers discovered a technique that makes LLMs 94% more accurate without any examples.

It's called "Chain-of-Verification" (CoVe) and it completely destroys everything we thought we knew about prompting.

Here's the breakthrough (and why this changes everything): 👇
tweet

Wasteland Capital
$MU now passed the 300%+ return mark. Meanwhile $AEO just hit new 4-year highs.

$LYFT outperforming +55-60% vs $UBER and $DASH (both of those are negative).

Average return now +139%.

Compounding is beautiful. https://t.co/ZerFN5dOf0

Apart from my earnings reviews, I’ve only tweeted five new cases on here over the last year.

They ended up the #1 Mag7 YTD $GOOG, the #1 Semi YTD $MU & #1 China LargeCap YTD $BABA. Plus 2 🚀 smallcaps, $AEO & $LYFT

Average return +111% currently.

Less is more, as they say. https://t.co/LGr5bglq7t - Wasteland Capital
tweet

Illiquid
Wrong kind of storage to be checking out today. https://t.co/mTqMenqxLE
tweet

Brady Long
RT @0xgaut: Mom: "how's the job search going?"

you: "Claude, build me a prediction market arbitrage bot" https://t.co/eFnRqOu05Y
tweet

God of Prompt
RT @godofprompt: 🚨 DeepMind discovered that neural networks can train for thousands of epochs without learning anything.

Then suddenly, in a single epoch, they generalize perfectly.

This phenomenon is called "Grokking".

It went from a weird training glitch to a core theory of how models actually learn.

Here’s what changed (and why this matters now):
tweet

memenodes
RT @Bqmbulu: Loving a girl more than she loves you: https://t.co/gmD2gP0Wxk
tweet

memenodes
Porn addiction is so crazy like how you addicted to other nig*as getting pussy?

STOP WATCHING PORN!!

STOP WATCHING PORN!!!

STOP WATCHING PORN!!

YES YOU!!👀👀..STOP IT!!

STOP WATCHING PORN!! - m
tweet

memenodes
RT @Mona_Trades: You don’t suck at trading

You suck at waiting
tweet

memenodes
locking in and seeing no results

Apart from breakup, what else can make a man be like this?
https://t.co/fEOVkIpgF8 - naiive
tweet

Brady Long
If you’re building agents, this matters more than another bigger model launch.

MiroThinker 1.5 is about agentic density: better reasoning per parameter, lower cost, and more controllable behavior.

Explore: https://t.co/mlOCZjARcI

https://t.co/q3P6xXXYhW

We just flipped the scaling narrative: Agentic Density > Parameter Count.

#MiroThinker 1.5 operationalizes Interactive Scaling—agents that seek evidence, iterate, and revise in real time (with a time-sensitive sandbox to avoid hindsight leakage).

Result: 30B hitting frontier-class agentic search, ~$0.07/query (≈20× cheaper vs 1T-class baselines).

Fully open source, read more: https://t.co/m4HzxiidRX
Try: https://t.co/dwKmu3O9t7
GH:https://t.co/u4VhL8o8Gt
HF: https://t.co/ClqKRrQn6R - MiroMindAI
tweet