Towards Autonomous Biology: Compiler-Verified Protocols as a Foundation for Real-World AI Execution Paper: https://
biorxiv.org/content/10.648
98/2026.05.05.720956v1
… Our report: https://
mp.weixin.qq.com/s/MhS1fG2I9HIb
fXzW0H19bg
…
AUTOMATION
-

Towards Autonomous Biology with Compiler-Verified Protocols for AI Execution
By
–
-

Bota Biosciences’ BPL-COGEN Enables Error-Free Biological Experiments
By
–
Biology's EDA moment has arrived! Yes, now AI can truly run biological experiments without human error! Bota Biosciences presents Biology Protocol Language (BPL) and BPL-COGEN: a compiler-verified protocol language and AI pipeline that turns ambiguous natural language lab
-
A proactive AI learns to help you with your website
By
–
☎️ÚLTIMA HORA: ya existe una IA que no solo responde, sino que entra en contexto y se pone a trabajar contigo.
— SONIA (@S0N_IA_) 23 juin 2026
Me registré en Pancake y, sin un onboarding pesado, empezó a enseñarme cómo podía ayudarme con mi web: hasta me recreó el logo y cogió contexto de la página para… pic.twitter.com/rsX381cpFYBreaking news: an AI already exists that does not just respond, but enters context and starts working with you. I signed up for Pancake and, without a heavy onboarding, it started teaching me how it could help me with my website: it
-

Code as Agent Harness: Unified Framework for Reasoning, Action, Verification
By
–
Cool, Code as Agent Harness! Researchers from UIUC, Meta and Stanford present "Code as Agent Harness": a unified framework where code serves as an operational substrate for agent reasoning, action, and execution-based verification — and not only as
-
Clarification: Sakana Fugu is a multi-agent orchestration system, not a standalone model.
By
–
To clarify, @SakanaAILabs' headline is somehow misleading.
— Charly Wargnier (@DataChaz) 23 juin 2026
While Sakana does train its own standalone models, Sakana Fugu is not one of them.
Rather, Fugu is a multi-agent orchestration system designed to coordinate already-existing AI models https://t.co/Blb3WjmjzzTo clarify, @SakanaAILabs
' headline is somehow misleading. While Sakana does train its own standalone models, Sakana Fugu is not one of them. Rather, Fugu is a multi-agent orchestration system designed to coordinate already-existing AI models -
Sakana Fugu is a multi-agent orchestration system, not a standalone model.
By
–
Addendum: @SakanaAILabs
' headline is misleading. While Sakana does train its own standalone models, Sakana Fugu is not one of them. Rather, Fugu is a multi-agent orchestration system designed to coordinate already-existing AI models -
AI and marketing: intelligent agents, deep personalization, and rapid execution
By
–
#AI changes #marketing from a discipline built around #campaigns, #content, and #dashboards into a discipline shaped by #intelligent agents, deeper personalization, and faster execution. The greatest
-
The Core of AI Agent: Context, Harness, and Loop
By
–
这个讲得非常好,推荐大家看一下这个视频。
— 艾略特 (@elliotchen100) 23 juin 2026
很多人做 AI 还停在“怎么写 prompt”,但 Agent 真正能开始干活,是从 context、harness 到 loop 这一整套东西接起来:知道什么、能用什么、怎么判断下一步、怎么反复推进。
把这几个概念串起来看,很多 AI 产品的差距就很清楚了。 https://t.co/vrKCKQ5jvcThis is very well said. I recommend everyone to watch this video. Many people working on AI are still stuck on 'how to write prompts', but an Agent can truly start working only when the whole set of things from context, harness, to loop are connected: knowing what, being able to use what, how to judge the next step, how to iteratively advance. By linking these concepts together, the gaps between many AI products become clear.
-

Waymo no fatalities, Tesla FSD 4x safer than average
By
–



Also added Waymo and Tesla FSD to http://
airlinelist.com Interestingly, Waymo never had fatalities yet And Tesla FSD is ~4x safer than the average car (in fatal odds per trip) 1,190,000 people die every year in traffic deaths 80% of those would be prevented with self -
Writing Threatened by AI: A Sense of Collapse
By
–
The situation with writing right now is really bad! You can almost feel the collapse of the mode. Everyone writes with AI all the time. And when they don't write with AI, they produce text that looks so much like AI that it's hard to make the