🤖

AI & Machine Learning Threads

Artificial intelligence, machine learning, and automation

All Topics
@ericosiu
@ericosiu
Article

The best engineers in the world have stopped prompting AI and started building loops....

2 months ago
66
@bounceidc
@bounceidc
Article

Peter Steinberger says it monthly: you should not be prompting coding agents anymore, you should be designing loops that prompt your agents. Boris Cherny, who runs Claude Code at Anthropic, says it plainer: "I do not prompt Claude anymore. I have loops running that prompt Claude. My job is to write ...

1 month ago
21
@0xCortexl
@0xCortexl
Article

Anthropic pays their engineers $80,000 a month. Those engineers now merge 8x more code per day than they did a year ago. Not because the model got smarter. Because they stopped prompting Claude and started building systems that prompt it for them....

1 month, 2 weeks ago
38
@jota_snchez
@jota_snchez
Thread

Robert Greene ha vendido +20M de libros estudiando una sola cosa: por qué unas pocas personas encuentran su propósito y la mayoría muere sin descubrirlo. Tuvo una charla de 3 horas con Huberman sobre propósito. Te lo resumo en 7 pasos: 1. Vuelve a tu infancia ...

2 months, 1 week ago
77
@jota_snchez
@jota_snchez
Thread

David Sinclair es el biólogo de Harvard que demostró que el envejecimiento no es inevitable. Es una enfermedad. Y la medicina moderna se niega a tratarla. Reveló 6 hábitos que haces a diario y están acelerando tu envejecimiento sin que lo sepas. 1) Comer 3 veces al día ...

2 months, 2 weeks ago
83
@jumperz
@jumperz
Thread

this is how to run claude fable 5 as your architect ( 20$ sub only ) + gpt 5.5 codex as your builder.. full system below: the loop is : fable thinks... codex builds , the repo remembers and you judge, that simple.. the point of all this is that we are taking advantage that 5.5 is on a sub and it'...

2 months, 1 week ago
68
@dotey
@dotey
Thread

转译:深度拆解 Hermes Agent 的记忆系统:它如何修正 OpenClaw 的误区 如果你读过我之前关于 ChatGPT、Claude 以及 Clawdbot 记忆系统的文章,你就会知道我一直在钻研同一个问题:这些 AI 智能体(AI Agent)到底是怎么记事的? Hermes Agent 对我来说格外有趣,因为这次我不需要只靠观察它的行为来搞“逆向工程”。Hermes 是开源的,它的代码库和文档都是公开的。所以,我没有通过提示词(Prompt)去盲测这个黑盒,而是直接翻看了它的代码路径——从它如何构建提示词状态、持久化会话,到如何清理记忆和查询历史对话。 简而言之:Herme...

3 months, 3 weeks ago
144
@s4yonnara
@s4yonnara
Article

Most "AI agent" tutorials build something that works in the demo and dies the second it touches real work. It nails the happy path on stage, then quietly fails on the messy input, the long task, the thing nobody tested....

1 month, 3 weeks ago
46
@alex_prompter
@alex_prompter
Article

## 100K people bookmarked @karpathy's <a target="_blank" href="https://x.com/karpathy/status/2039805659525644595" color="blue">post</a>:...

4 months, 1 week ago
183

Also tagged in AI & Machine Learning

@vasuman
@vasuman
Article

You can cut your token spend by over 90% without using open source models. ...

3 days ago
31
@chesny
@chesny
Article

28 repositorios. Seis capas. Un <i>stack</i>. Sin fisuras. ...

5 days, 3 hours ago
52
@RitOnchain
@RitOnchain
Article

Financial markets are, at their core, relational systems. A stock does not move in isolation - it moves because its largest customer cut orders, because its sector peers reported earnings, because a sovereign credit event repriced its debt covenants, or because a shared institutional holder is liqui...

1 week, 1 day ago
108
@0xRafy
@0xRafy
Article

Before USB, every device had its own cable. MCP is USB for AI agents. <b>400M+ monthly SDK downloads. 10,000+ servers. Adopted by every major AI lab.</b>...

1 week ago
85
@S1r1u5_
@S1r1u5_
Thread

i really want to talk to people who are ai-pilled like this, because their world model of ai seems completely alien to mine. when i look at the black hat incident and its technical details, sure, it’s crazy, but it’s also roughly what i’d expect from constrained exploit dev agents pressured to pur...

4 days, 19 hours ago
41
@DimitrisPapail
@DimitrisPapail
Article

Last week, GPT-5.6 and Claude Fable appear to have settled an open theoretical question in wireless communications that was intensely studied between 2000 till the 2010s and that I briefly worked on as an anxious first-year PhD student. The answer finally arrived, perhaps because I was one of the la...

1 week, 3 days ago
120