reamory.ai

[Lunar @LunarResearcher]

https://t.co/eflBjoVyV2

[Pi @pidotdev]

Our sessions have been messaging each other for months btw ;)

@nicopreme’s pi-intercom extension makes it easy for one session to pick up where another left off.

Open source Pi packages mean there are multiple ways you can customize Pi. Link to this package and more below.

[Pi @pidotdev]

We’ve been excited to see so many people using and building on Pi.

This week we listened to Scott Gerring from @datadoghq share how he configures Pi for his work.

Start minimal, notice when you hit friction and ask Pi to remove it. Link to full episode below. We recommend!

[darkzodchi @zodchiii]

A senior Anthropic engineer just dropped 15-page PDF on "Graph Engineering and Agent Memory" for multi-agentic systems.

The shift: your agent's memory dies with its context window. A knowledge graph makes it permanent.

Extract → Store → Retrieve → Evolve

Every graph-based memory runs 4 stages:

• Extract: pull entities and typed relations out of raw docs and conversations into structured triples.

• Store: canonical nodes, typed edges, provenance on every fact. One connected graph instead of scattered chunks.

• Retrieve: multi-hop questions become graph traversal. "Who owns what breaks if this ships" is one walk, not six guesses.

• Evolve: the stage everyone under-builds. Facts get validity windows. Nothing is deleted, only marked superseded, so "who owned this in April" still answers.

This 15-page PDF changed how I'm building multi-agent systems today.

Read it now, then explore the article below👇

[多肉 | AI 内容增长 @leo_xiaolei]

https://t.co/xXrFeywNxg

[Mark Ajzenstadt @mardehaym]

Matt Pocock just dropped an 18-minute talk at @aiDotEngineer on why software fundamentals matter more than ever in the AI age:

00:00 - Why specs-to-code produces garbage
04:36 - Grill Me: the skill that interrogates your plan before AI writes code
07:21 - Fix verbose AI with a ubiquitous language
09:45 - TDD is your AI's speed limit
12:35 - Deep modules: the codebase structure AI thrives in
15:04 - Design the interface, delegate the implementation

These 18 minutes of software design fundamentals will replace 20 paid AI coding courses.

Watch it, then read the guide on how to make a company AI-native below.

[Alex Volkov @altryne]

https://t.co/aU4uGollhD

Should AI Engineers read code anymore in 2026? This, apparently is a divisive take, that has folks like Theo, Hashimoto, Primeagen and even uncle bob chiming in.

I predicted this two months ago, and named it the ZL Continuum.

My talk from @aiDotEngineer is covering this debate, and where your attention should go after models drift in capability is live now. Please go take a loook.

Huge thanks for AI Engineer folks for prioritizing the recording as the conversation about this topic caught up.

[Ryan Lopopolo @_lopopolo]

Every company should have a full stack team of 5 building a product who are banned from directly writing code; they must force the agents to do it. In 2 months they will be your most productive team.

[//TODO: fix later 🐳 @enjoyingthewind]

@badlogicgames Pi is bloated, see here for a real minimal coding agent:
https://t.co/NPIAbrfa8S ;)

[reamory.ai @reamory_eth]

@ai_rohitt 自我提示的未来来了。想知道这些代理会如何扩展到更复杂的任务中 🤔

[淘沙者(TheSandPicker) @Etudecn]

Andrej Karpathy 把大模型说透了。

“LLM 压根没想成功，它只想模仿。”
他最近在微软 Build 大会有个 42 分钟的演讲，把模型到底怎么“想”的掰开揉碎了讲。
没有野心，不追求“正确”，就是重复训练时见过的模式。
最绝的是这个对比：一个 80 层 Transformer 处理一个 token 的算力，跟你大脑处理一个念头的能耗差不多。
这不是什么提示词魔法，这是理解模型的底层逻辑。
比网上那些卖 500 美金的神棍课值钱多了。
想停止把 AI 当人一样许愿，开始把它当工具一样使用？这个演讲是必修课。
看了没？没看赶紧去。

[leopardracer @leopardracer]

https://t.co/sCtM6fDRO9

[Maple @TryMapleAI]

🚀 Maple is now on Windows

File uploads, voice, and the Maple Proxy API, all end-to-end encrypted, backed by verifiable open-source code.

That completes the lineup: web, iOS, Android, macOS, Linux, and Windows. Download it now!

[Lenny Pruss @lennypruss]

You can read a more in depth version in my latest post:

https://t.co/O2rdSzyeNs

Thanks to @davidcrawshaw, @mitchellh, @armon, @schrockn, and @jthandy for pressure-testing these ideas!

[Morty @0xMortyx]

https://t.co/OcDHvkrj2b

[reamory.ai @reamory_eth]

@Raytar @grok please give me a bulletized list of the topics and tips the presenter gave in the presentation

[Roan @RohOnChain]

https://t.co/JRsWSeUfrN

[Serena 木瓜 @369Serena]

https://t.co/oXcPvV2Awn

[Moysei @0xMoysei]

https://t.co/Fnh6MxF3pS

[wandermist @wandermist]

https://t.co/Ak1vo3Aabu