Celso Singo Aramaki 有真気 神護

Now: Tokyo/NY RbyD AI. Before: Design for Folha de São Paulo, Interaction Projects for Sony, Tomy, NEC, NHK, Kodansha, Dentsu in Japan.

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

Thanks to @brandialxndra for making this photo available on @unsplash 🎁 https://t.co/8WtGwuJlER

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

Thanks to @meditativeinfo for making this photo available on @unsplash 🎁 https://t.co/2AIwweFLml

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

Thanks to @meditativeinfo for making this photo available on @unsplash 🎁 https://t.co/2xrB8oSdne

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

Thanks to Hunter Moranville for making this photo available on @unsplash 🎁 https://t.co/CSvcsNqlRL

[elvis @omarsar0]

So I wrote down a better-formatted version of my post on Deep Agents.

I added it to the AI Agents section of the Prompt Engineering Guide.

If you are building with AI Agents, this is a must-read.

I also added links to other useful references.

promptingguide .ai/agents

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

2026 :)

[Scholarship for PhD @ScholarshipfPhd]

ChatGPT for Research and Publication: A Step-by-Step Guide

If you need the PDF version, please comment below

[Andrew Ng @AndrewYNg]

Announcing a significant upgrade to Agentic Document Extraction!

LandingAI's new DPT (Document Pre-trained Transformer) accurately extracts even from complex docs. For example, from large, complex tables, which is important for many finance and healthcare applications. And a new SDK makes using it require only 3 simple lines of code. Please see the video for technical details. I hope this unlocks a lot of value from the "dark data" currently stuck in PDF files, and that you'll build something cool with this!

[Tucker Carlson @TuckerCarlson]

Rep. Thomas Massie doesn’t care what you think of him, which is pretty great.

(3:19) Where Does US Debt End?
(10:32) Why Massie Voted 15 Times Against Funding Israel
(14:53) AIPAC
(34:04) Mitch McConnell
(42:25) Area 51
(50:32) Massie's Relationship with Trump
(57:09) Kill Switches in Cars
(1:05:58) Mike Johnson and the Deep State
(1:14:34) How Massie Got Into Politics
(1:18:29) Living off the Grid

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

@Bonecondor @elonmusk XYZ Party

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

@AndrewYang @elonmusk @Fwd_Party If you build it people will come

[Emad @EMostaque]

@elonmusk Do it, make it AI first with proper representative democracy and full use of ai in drafting and critiquing legislation and pork

Don’t listen to Kodos & Kang

[unusual_whales @unusual_whales]

@elonmusk Would politicians in that party be able to trade stocks @elonmusk, as currently, both parties are beating the market?

[The Redheaded libertarian @TRHLofficial]

@elonmusk America can be broken up into Dems, Republicans, libertarians, and Greens, but the issue is getting the third and fourth parties on to a debate stage, as the powers that be changed the rules following Ross Perot.
They now require 15% in 5 major polls.

[Andrew Yang🧢⬆️🇺🇸 @AndrewYang]

@elonmusk Working on it!! ⬆️🇺🇸 @Fwd_Party

[RobinHub @RobinHubHB]

🔥 Solana AI Agents spotlights in the last 24h 🟢👇

🚀 Top gainers:
$DIRA @AIAgentsHub
$MINDS @MindscraftAI
$DOGEAI@dogeai_gov
$VIVI @lh_vivi_

📈 Most traded:
$AI16Z @Ai16zCTO
$AVA @AVA_holo
$PIPPIN @pippinlovesyou
$BUZZ @askthehive_ai

💰 Trending:
$FARTCOIN @FartCoinOfSOL
$PEPEAI @pepeaiagent
$PAYAI @PayAINetwork
$AVA @AVA_holo

[Celso Singo Aramaki 有真気 神護 @ShingoAramaki]

https://t.co/dMITVBy4ZK

[MetaPuppet @MetaPuppet]

This is Plastic. Made with Veo3.

Spoilers in the next post. Watch before reading

[Brett Adcock @adcock_brett]

Stability AI open-sourced Stable Audio Open Small, a text-to-audio AI

—341M-parameters
—Generates 11s of audio, including drum loops, foley, riffs, and textures
—Optimized for Arm-based consumer devices

[Brett Adcock @adcock_brett]

Tsinghua University researchers detailed HuB, a unified framework to help humanoids handle extreme balancing tasks

It integrates reference motion refinement, balance-aware policy learning, and robustness training to improve sim-to-real consistency