When one prompt isn't enough, stop cramming! Brilliant piece by my good friend Mari! It covers how AI reads in a "U-shape" (ignoring the middle) + how to scale complex tasks using subagents instead of these fragile MEGA-prompts
GENERATIVE AI
-
AI writes site that curates 40,000 daily posts
By
–
AI wrote every word on my site that reads 40,000 posts a day here on X and picks the best. It's pretty good: https://
alignednews.com/ai While I agree with you, there is some reason to have AI write. I can't read 40,000 posts a day. Can you? -
New goto negative prompt: “no embellishments” for unwanted creativity
By
–
My latest goto negative prompt: "no embellishments" For when a model is trying to be creative in a way you don't like.
-
AI’s ERNIE model digitizes martial arts legacy, preserving ancient movements.
By
–
When ancient movements meet modern algorithms, AI carries on the legacy of martial arts.
— Baidu Research (@BaiduResearch) 4 juin 2026
Powered by Baidu ERNIE, the martial arts large model can capture movements, preserving and recording them in digital form.
This approach allows the traditional oral transmission and… https://t.co/6OSPtMm6huWhen ancient movements meet modern algorithms, AI carries on the legacy of martial arts. Powered by Baidu ERNIE, the martial arts large model can capture movements, preserving and recording them in digital form. This approach allows the traditional oral transmission and
-
AI hallucination leads candidate to wrong company with confidence
By
–
Somewhere, a candidate is walking into the wrong company with total confidence because their “research assistant” hallucinated the restaurant, the CEO, and possibly the menu. I laughed because this is exactly how AI confidence feels before verification enters the room. The
-
Hardmaru will discuss Sakana AI’s 1T parameter model on WBS
By
–
On TV Tokyo’s WBS (
@wbs_tvtokyo
) tonight I’ll be discussing Sakana AI’s upcoming 1T parameter model project, supported by METI’s GENIAC initiative. We are scaling up to build Japan’s first 1T parameter agent-native model, specifically optimized for long-horizon deep research and -
Official MiniMax AI M2.7 documentation and API links
By
–
… and for your reference, here is the official @MiniMax_AI documentation: – MiniMax M2.7 official page: https://
minimax.io/models/text/m27
– MiniMax API docs: https://
platform.minimax.io/docs/api-refer
ence/api-overview
… -
SambaCloud’s MASSIVE 435 t/s output speed for OpenClaw multi-agent frameworks
By
–
When you run multi-agent frameworks like @OpenClaw
, you know the output speed is critical. As the chart below shows, SambaCloud serves MiniMax M2.7 at a MASSIVE 435 output tokens per second, more than 3x faster than the nearest competitor (Fireworks at 127 t/s). Combine that -
HeyGen announces FRAME.md format for branded videos
By
–
HeyGen announced a new FRAME.md format 👀
— 🚨 AI News | TestingCatalog (@testingcatalog) 4 juin 2026
This format converts DESIGN.md files (which describe your brand guidelines) into a new format that also explains how to generate branded videos.
It comes as an open-source repository that any brand can use, so the new FRAME.md file can… https://t.co/VstZJOyQAf pic.twitter.com/uekrNaDRDGHeyGen announced a new FRAME.md format This format converts DESIGN.md files (which describe your brand guidelines) into a new format that also explains how to generate branded videos. It comes as an open-source repository that any brand can use, so the new FRAME.md file can
-
AI Answers Beat Law Professors in Blind Stanford Study
By
–
A blind Stanford-led study of nearly 3,000 anonymized matchups found law professors across 16 schools preferred AI-generated answers to student contract-law questions over those written by fellow professors 75% of the time, and judged the AI responses far less likely to be