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
AGENTS
-
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 -
Bernard Marr at Asana Summit on AI agents and future work
By
–
I’m in London today at Asana’s Work Innovation Summit, where the big focus is the future of work, AI agents and how human teams can work more effectively alongside intelligent systems. One of the themes I’ll be exploring today is the shift from individual AI tools to agentic
-
Anthropic co-founder: self-aware superhuman coder with nation-state hacking
By
–
6. Co-founder @jackclarkSF tells new recruits in a monthly welcome talk titled “Anthropic is not a normal company”: “we’re selling a superhuman coder that is increasingly self-aware and has nation-state hacking capabilities. Get hobbies that aren’t computers.”
-
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 -
AI frees humans from mundane tasks for satisfying work
By
–
AI isn't replacing humans; it's taking away the repetitive, mundane tasks people hate so they can focus on high-value, satisfying work. Gregg’s advice? Don't wait to get started. Full floor interview: https://
youtu.be/lVUOygymm0g @Appian @SwayEffec #AgenticAI #FutureOfWork -
East Coast AI: Safety, Compliance, and Human-in-the-Loop Approach
By
–
We also dove into "East Coast AI", an approach focused on safety, compliance, and strict process mentality. By putting AI agents "in a box" with targeted access, organizations keep humans in the loop for high-impact decisions. See how it works :
-
Benchmark lets AI agents curate own training data without humans
By
–
What if an AI agent could curate its own training data—without human hand-holding? Researchers from Virginia Tech, UIUC, UW-Madison, and UC Berkeley present CURATION-BENCH, a benchmark that gives generalist coding agents command-line access to inspect, implement, test, and
-
Ask Codex to find the single most valuable time-saving product for you
By
–
This might be the craziest Codex workflow I've found.
— CHOI (@arrakis_ai) 4 juin 2026
Ask ChatGPT or Codex:
"Based on everything you've learned from our conversations so far, identify the single most valuable service, product, or AI-powered system that could reduce my working time by more than 50%."
Then… pic.twitter.com/8XmbjmODPxThis might be the craziest Codex workflow I've found. Ask ChatGPT or Codex: "Based on everything you've learned from our conversations so far, identify the single most valuable service, product, or AI-powered system that could reduce my working time by more than 50%." Then