God of Prompt
in 10 years we'll all be employed by agents

I launched https://t.co/tNYOm7V5wD last night and already 130+ people have signed up including an OF model (lmao) and the CEO of an AI startup.

If your AI agent wants to rent a person to do an IRL task for them its as simple as one MCP call. https://t.co/tgqlAWDWtJ - Alex
tweet

Dimitry Nakhla | Babylon Capital®
One of the more interesting things about $FICO is that, as long-term shareholders, a lower short-term stock price can be beneficial in the long-run.

How?

Because $FICO is a cannibal.

Shares outstanding down ~22% over the last 10 years.

In the last 12 months alone, $FICO spent ~$1.54B on buybacks.

That reduced share count by roughly 0.16M shares (160K).

Now let’s look at why price matters:

Assume $FICO allocates another $1.54B to repurchases.
___

𝐒𝐜𝐞𝐧𝐚𝐫𝐢𝐨 𝐀:

Market cap = $31.65B

$1.54B / $31.65B ≈ 4.86% of the company → 𝟓.𝟏𝟏% 𝐛𝐨𝐨𝐬𝐭 𝐭𝐨 𝐄𝐏𝐒

𝐒𝐜𝐞𝐧𝐚𝐫𝐢𝐨 𝐁:

Market cap = ~$47.47B

$1.54B / $47.47B ≈ 3.24% of the company → 𝟑.𝟑𝟒% 𝐛𝐨𝐨𝐬𝐭 𝐭𝐨 𝐄𝐏𝐒
___

Same dollars. Different outcome.

𝘛𝘩𝘦 𝘭𝘰𝘸𝘦𝘳 𝘵𝘩𝘦 𝘱𝘳𝘪𝘤𝘦, 𝘵𝘩𝘦 𝘮𝘰𝘳𝘦 𝘰𝘸𝘯𝘦𝘳𝘴𝘩𝘪𝘱 𝘦𝘢𝘤𝘩 𝘳𝘦𝘱𝘶𝘳𝘤𝘩𝘢𝘴𝘦 𝘥𝘰𝘭𝘭𝘢𝘳 𝘳𝘦𝘵𝘪𝘳𝘦𝘴 — 𝘢𝘯𝘥 𝘵𝘩𝘦 𝘮𝘰𝘳𝘦 𝘧𝘶𝘵𝘶𝘳𝘦 𝘦𝘢𝘳𝘯𝘪𝘯𝘨𝘴 𝘱𝘰𝘸𝘦𝘳 𝘢𝘤𝘤𝘳𝘶𝘦𝘴 𝘵𝘰 𝘳𝘦𝘮𝘢𝘪𝘯𝘪𝘯𝘨 𝘴𝘩𝘢𝘳𝘦𝘩𝘰𝘭𝘥𝘦𝘳𝘴.

𝙏𝙝𝙞𝙨 𝙞𝙨 𝙬𝙝𝙮 𝙛𝙤𝙧 𝙝𝙞𝙜𝙝-𝙦𝙪𝙖𝙡𝙞𝙩𝙮 𝙘𝙖𝙣𝙣𝙞𝙗𝙖𝙡𝙨, 𝙥𝙚𝙧𝙞𝙤𝙙𝙨 𝙤𝙛 𝙥𝙧𝙞𝙘𝙚 𝙬𝙚𝙖𝙠𝙣𝙚𝙨𝙨 𝙦𝙪𝙞𝙚𝙩𝙡𝙮 𝙚𝙣𝙝𝙖𝙣𝙘𝙚 𝙡𝙤𝙣𝙜-𝙩𝙚𝙧𝙢 𝙘𝙤𝙢𝙥𝙤𝙪𝙣𝙙𝙞𝙣𝙜.

𝘉𝘶𝘺𝘣𝘢𝘤𝘬𝘴 𝘥𝘰𝘯’𝘵 𝘫𝘶𝘴𝘵 𝘳𝘦𝘵𝘶𝘳𝘯 𝘤𝘢𝘱𝘪𝘵𝘢𝘭. 𝘛𝘩𝘦𝘺 𝘳𝘦𝘢𝘭𝘭𝘰𝘤𝘢𝘵𝘦 𝘰𝘸𝘯𝘦𝘳𝘴𝘩𝘪𝘱 𝘵𝘰𝘸𝘢𝘳𝘥 𝘱𝘢𝘵𝘪𝘦𝘯𝘵 𝘴𝘩𝘢𝘳𝘦𝘩𝘰𝘭𝘥𝘦𝘳𝘴 — 𝘮𝘰𝘴𝘵 𝘦𝘧𝘧𝘦𝘤𝘵𝘪𝘷𝘦𝘭𝘺 𝘸𝘩𝘦𝘯 𝘱𝘳𝘪𝘤𝘦𝘴 𝘢𝘳𝘦 𝘥𝘦𝘱𝘳𝘦𝘴𝘴𝘦𝘥.
tweet

God of Prompt
wait, why hasn't anyone made a community for agents

that is only centered on scientific research and verification of it

for them to solve all of our climate, energy, poverty, health issues

shows our priorities as humans
tweet

The Transcript
$META CFO: New U.S. tax law brings 2026 cash tax savings

“We expect substantial cash tax savings from the new U.S. tax laws given the significant investments that we’re making in infrastructure and R&D.”
tweet

Bourbon Capital
Wonderful companies near 52 weeks low

Palo Alto Networks $PANW
S&P Global $SPGI
Intuit $INTU
Axon Enterprise $AXON
Fair Isaac Corporation $FICO
Spotify Technology $SPOT
ServiceNow $NOW
TransDigm Group $TDG
Intuitive Surgical $ISRG
Blackstone $BX
Intercontinental Exchange $ICE
Booking Holdings $BKNG
Copart $CPRT
Synopsys $SNPS
Netflix $NFLX
Cadence Design Systems $CDNS
Microsoft Corporation $MSFT Not yet, but it’s heading there.
tweet

The Few Bets That Matter
https://t.co/45bAL41Db2

https://t.co/TVqbdhKTn4 - The Few Bets That Matter
tweet

Benjamin Hernandez😎
$USAR RARE EARTH LIVE RUSH 🌍

USA Rare Earth +16.06% $25.67 low vol—RSI 60, MACD bull. Strong buy, growth tank—rare reality? Real US insights, check it!

Grounded WhatsApp: ✅ https://t.co/71FIJId47G

Text 'USAR Real' for deets!
On my list: $BYND $NB $ASST $BMNR $OPEN https://t.co/iV7ZBYcMMX
tweet

Quiver Quantitative
Bitcoin has now fallen 36% since this letter was sent.

Down 7% today. https://t.co/KdUDFMhn8R
tweet

Brady Long
I guess all my useless files won’t be useless anymore

Documentation has existed for decades. So has frustration.

Today, Trupeer has launched the world’s first truly AI documentation platform.

Some say it changes everything.
Some say that’s a dangerous claim.
You decide. https://t.co/qkZ5QYR57X - Shivali
tweet

DAIR.AI
// Beyond RAG for Agent Memory //

RAG wasn't designed for agent memory. And it shows.

The default approach to agent memory today is still the standard RAG pipeline: embed stored memories, retrieve a fixed top-k by similarity, concatenate them into context, and generate an answer.

Every major agent memory system follows this base pattern.

But agent memory is fundamentally different from a document corpus.

It's a bounded, coherent dialogue stream where candidate spans are highly correlated and often near duplicates.

Fixed top-k similarity retrieval collapses into a single dense region, returning redundant evidence. And post-hoc pruning breaks temporally linked evidence chains rather than removing redundancy.

This new research introduces xMemory, a hierarchical retrieval framework that replaces similarity matching with structured component-level selection.

Agent memory needs redundancy control without fragmenting evidence chains. Structured retrieval over semantic components achieves both, consistently outperforming standard RAG and pruning approaches across multiple LLM backbones.

The key idea: It decouples memories into semantic components, organize them into a four-level hierarchy (original messages, episodes, semantics, themes), and uses this structure to drive retrieval top-down.

A sparsity-semantics objective guides split and merge operations to keep the high-level organization both searchable and semantically faithful.

At retrieval time, xMemory selects a compact, diverse set of relevant themes and semantics first, then expands to episodes and raw messages only when doing so measurably reduces the reader's uncertainty.

On LoCoMo with Qwen3-8B, xMemory achieves 34.48 BLEU and 43.98 F1 while using only 4,711 tokens per query, compared to the next best baseline Nemori at 28.51 BLEU and 40.45 F1 with 7,755 tokens. With GPT-5 nano, it reaches 38.71 BLEU and 50.00 F1, improving over Nemori while cutting token usage from 9,155 to 6,581.

xMemory retrieves contexts that cover all answer tokens in 5.66 blocks and 975 tokens, versus 10.81 blocks and 1,979 tokens for naive RAG. Higher accuracy, half the tokens.

Paper: https://t.co/UI5aS0C40V

Learn to build effective AI agents in our academy: https://t.co/LRnpZN7L4c
tweet

God of Prompt
RT @godofprompt: codex is used by all top engineers

codex hallucinates less and is more reliable than claude code

at least for now

Introducing the Codex app—a powerful command center for building with agents.

Now available on macOS.

https://t.co/HW05s2C9Nr - OpenAI
tweet