Gigi Liu

Las presentaciones que genera NotebookLM por defecto son una vergüenza. Pero no es culpa de la herramienta. Es que nadie te dijo que existe un repositorio en GitHub que lo cambia todo. Se llama awesome-notebookLM-prompts. Decenas de prompts de diseño probados por researchers, founders y diseñadores de todo el mundo. Tipografías modernas. Gráficos complejos. Acabado visual de agencia. El mismo contenido. Un prompt diferente. Resultado completamente distinto. El proceso es así: 1️⃣ Entras al repositorio en GitHub 2️⃣ Copias el prompt de diseño que quieras 3️⃣ En NotebookLM, ve a Slide deck → Personaliza → pega el prompt en "Instrucciones personalizadas" 4️⃣ El mismo contenido pasa a tener un acabado profesional Sin configuración. Sin pagar nada. Sin complicaciones. El contenido ya lo tenías. Solo te faltaba el prompt correcto. Te dejo el enlace al repositorio en los comentarios. ¿Cuánto tiempo llevas conformándote con slides mediocres?

Here's probably the best Claude Cowork tutorial under 25 minutes. It is by Tina Huang ( ex-Meta data scientist).

New Fun Quiz "Mechanical Power" societymechanicalventilation.org/quizz/

📈 Hospitalists are key to leading the AI revolution in medical education! See how GAI transforms teaching, coaching & assessment to shape future care. #AIinMedicine #MedEd 🖥️ 🔗: doi.org/10.1002/jhm.13… ✍️: @vschaye, @marctriola

Over 1,000 clinicians have assessed MedArena LLM performance for their medical questions. #MedTwitter Try it! medarena.ai/login @james_y_zou

An intriguing spectral Doppler pattern. A patient with normal biventricular size and function. CW Doppler interrogation across the tricuspid valve in 4 chamber view is shown, consistently yields systolic diastolic flow. Whats are possible explanation?

#VExUS versus CVP for assessing venous congestion: oasis or mirage?🔗Crit Care 30, 240 (2026). doi: 10.1186/s13054-026-06016-7 #POCUS #FOAMed Authors mention that, when done carefully, CVP can continuously monitor the risk of venous congestion and can be easily reassessed before and after interventions like a fluid bolus. But I think this overlooks the significant institutional variability in CVC use. For example, where I did my critical care fellowship, midlines were used far more commonly outside the cardiac ICU, so #POCUS often became the primary way of assessing these patients.

This 3-minute video from Anthropic will make you realize you've been using Claude wrong this whole time "when you open Claude Code without a CLAUDE.md file, it has to start fresh every single time" most people have no idea how much this one file changes the way Claude actually works for you and this isn't only for developers the article below has 21 CLAUDE.md examples you can use in your daily routine I'm sure everyone will find something that fits exactly how they work

Aortic stenosis is one of the most common and lethal valvular diseases, and it can be detected at the patient's neck before a single cardiac view is obtained. The carotid Doppler waveform changes in a predictable and measurable way as the valve narrows.

What modern #guidelines still fail to emphasize clearly enough: regardless of whether MR is ASMR or VSMR, the LV initially responds with hypercontractility as an adaptive mechanism to chronic volume overload. A “normal” EF in significant MR is not necessarily normal physiology.

For Echo experts Dx?

Can you connect this echo finding to a classic auscultatory sign?

we all know about the MP, good start but Need to dig deeper into the components of energy balance. The video explains it from our new simulator now capable of making all inspiratory, expiratory work/MP in both VCV and PCV societymechanicalventilation.org/simulators/ youtu.be/o9Dq5ULJr6c

#POCUS image of the day: Not every pulsatile structure is an artery. 👇 Pulsatile internal jugular vein in severe tricuspid regurgitation. Courtesy 🔗 doi: 10.1007/s00134-019-05542-z.

Instead of watching an hour movie, watch this. In 14 minutes, an Anthropic engineer who wrote Building Effective Agents will teach you more about building agents right than most developers figure out on their own in months.

Excellent Case of Troubleshooting Ineffective Triggering in COPD Instead of a diagnostic challenge, let's focus today on how to treat an important cause of this dyssynchrony:

Academic Researchers right now:

So cool chatting with Dr. Paul Marino. thinkingcriticalcare.com/2026/05/09/tim… ping @icmteaching @khaycock2 @EMNerd_ @edu_kattan @NephroP @ArgaizR @Francofoam1

Our study has been published today in @AcadMedJournal! I'm proud to see my PhD student contributed to the literature as the first author. #MedEd In this study, we created and evaluated a transferable process for generating Concordance of Professional Judgment (CoPJ) items using LLMs. We created a generic zero-shot prompt, ChatGPT-5 Thinking and Gemini 2.5 Pro generated CoPJ items aligned with all 28 topics in Turkish national ethical declaration. Faculty evaluation demonstrated high overall suitability, particularly for Gemini 2.5 Pro, suggesting that LLMs may help reduce the resource burden associated with developing professionalism and ethics assessment materials.

Guidelines 2024: Emergency intubation of an adult outside the operating room and intensive care unit CCR Journal Watch criticalcarereviews.com/latest-evidenc…