YOUR MACBOOK BATTERY IS DYING TWICE AS FAST AS IT SHOULD.
Not because of how you use it.
Because of a setting Apple built to protect it and chose not to turn on by default.
Millions of MacBook owners are killing their batteries every single day without knowing it. 🧵
What the Artemis II astronauts did over the last 10 days was a testament to their bravery. And the fact that they traveled farther from Earth than anyone ever has, re-entered our atmosphere at more than 24,000 mph, and splashed down safely was a testament to human ingenuity. Thanks to everyone at @NASA for making this mission possible, and for taking us along for the ride.
NASA appears to be centralizing a lot of their high-resolution Artemis II media at this link. A good one to keep in your bookmarks.
https://t.co/5xBvnDaB92
This 2 hour Stanford lecture on AI careers will teach you more about winning in the AI race than every piece of AI content you have scrolled past this year.
Bookmark this & give it 2 hours, no matter what. It'll be the most productive thing you could do this weekend.
5. Step-by-Step Deep Dive Prompt
Perfect for technical subjects.
Prompt:
Teach me how [Concept/System] works step by step.
Start with fundamentals → mechanisms → advanced implications.
Avoid jargon unless explained clearly.
🚨 Google just dropped 150 pages on Health AI Agents. 7,000 annotations. 1,100 expert hours — but the real value isn’t in the big metrics. It’s the shift in design philosophy.
Instead of a monolithic “Doctor-GPT,” Google’s Personal Health Agent (PHA) orchestrates 3 specialists:
✸ Data Science Agent → analyzes wearables + labs.
✸ Domain Expert Agent → grounds outputs in medical knowledge + checks facts.
✸ Health Coach Agent → guides conversations, goals, empathy.
10 benchmarks.
7,000 annotations.
1,100+ expert hours.
The outcome?
More accurate insights.
More trusted summaries.
Stronger engagement than baseline LLMs.
The orchestrator ties them together with memory (user goals, barriers, insights).
⚡ Results
✸ Outperformed baselines across 10 benchmarks.
✸ End-users preferred PHA over single-agent + parallel systems (20 participants, 50 personas).
✸ Experts rated it 5.7%–39% better than baselines on complex health queries.
⚡ Design principles
✸ Address comprehensive user needs.
✸ Adaptive support → dynamically combine agents.
✸ Low user burden → don’t ask for data you can infer.
✸ Keep it simple → avoid unnecessary latency.
⚡ User journeys tested
• General health Q&A
• Personal data interpretation (wearables, biomarkers)
• Wellness advice (sleep, nutrition, activity)
• Symptom assessment (still limited, no diagnosis)
⚡ Limitations + future
✸ Slower than single-agent (244s vs 36s avg).
✸ Needs safeguards: bias audits, privacy, regulatory compliance.
✸ Next frontier: adaptive style → empathy vs accountability depending on user state.
⚡ The takeaway
Google’s PHA shows the path forward:
Not a “super doctor bot.”
But modular, specialized, agentic crews.
Healthcare is just the first test.
Tomorrow: finance, law, education, science.
Google 150 Health AI Agents: https://t.co/cDp9kCiPxm
≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣
⫸ From confused to confident AI agent builder in 30 days?
Stop watching tutorials. Start building.
𝟯𝟬 𝗗𝗮𝘆𝘀 × 𝟭 𝗛𝗼𝘂𝗿/𝗗𝗮𝘆 = 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗠𝗮𝘀𝘁𝗲𝗿𝘆
✔ 9 real-world agents
✔ 5 frameworks: MCP · LangGraph · PydanticAI · CrewAI · Swarm
✔ Working code, not toy examples
1,500+ developers ⭐⭐⭐⭐⭐ | 90+ countries
👉 𝗦𝘁𝗮𝗿𝘁 𝗬𝗼𝘂𝗿 𝟯𝟬-𝗗𝗮𝘆 𝗝𝗼𝘂𝗿𝗻𝗲𝘆 (𝟱𝟲% 𝗢𝗙𝗙): https://t.co/5i2v1fIrhJ