Manish Sharma

CTPO CoFounder Caladrius | Founder, Director, Yajur Healthcare | |

[Manish Sharma @msharmas]

Be
Patient.

Progress
Takes
Time.

[CaladriusHealth.AI @CaladriusHealth]

https://t.co/QI0McE0fMh

[CaladriusHealth.AI @CaladriusHealth]

One of the most common misconceptions about ABHA: that it stores your health records. It doesn't.
86.64 crore numbers created. Here's what they actually do. 🧵#ABDM #CaladiusHealthAI

[Google @Google]

Today we’re introducing Gemma 4 12B — our latest open model that brings advanced agentic reasoning, vision and audio directly to your laptop.

It delivers performance nearing our larger Gemma models with a much smaller total memory footprint, while being small enough to run locally with just 16GB of VRAM. It’s open and accessible for everyone to use under a permissive Apache 2.0 license.

This is all made possible by our new, unified architecture that removes separate multimodal encoders. Here’s how we did it 🧵

[Movez @0xMovez]

Claude Code creator:

"Now I don’t prompt Claude anymore - I have loops that are running. My job is to write loops."

In this 30-min speech, Boris revealed his actual Claude setup for daily coding.

Claude Code + loops + dynamic workflow

Worth more than a $500 vibe-coding course

[CaladriusHealth.AI @CaladriusHealth]

86.64 crore ABHA numbers created.
Only 35% of patients in one study knew what ABHA was.
A thread on what India's health ID actually does and what it doesn't. 🧵
#ABDM #CaladriusHealthAI

[Khairallah AL-Awady @eng_khairallah1]

Boris Cherny, the creator of Claude Code at Anthropic, just explained why single-agent workflows are already dead

in this talk he breaks down exactly how the future is teams of agents, not better prompts:

- the 14% you lose to CLAUDE.md before typing a word
- one agent researching. one building. one reviewing. one orchestrating
- the architecture that separates hobbyists from real builders
- the 3 properties every agent team needs to actually survive

if you've been using Claude for more than a month and never left the chat window, you've been using one agent when you could be running a team of them

instead of another show tonight, watch this

make sure to bookmark it before it gets lost in your feed

the guide is in the article below

[darkzodchi @zodchiii]

Anthropic engineer showed how one person can run 5 AI agents, that code, test, review, and deploy at the same time.

In 30 minutes they built the whole thing live in one session.

Here's what they cover:

> when to use one agent vs a full team
> how to split work so agents don't step on each other > the exact framework for deciding what each agent handles

that's exactly why, I put together a guide on building agent teams that actually work.

full guide in the article below 👇

[Andrew McCarthy @AJamesMcCarthy]

This is probably the best look at the shockwaves I’ve seen from the latest Starship flight.

Captured from a GoPro I clamped onto a proper camera to record simultaneous video. (I’ll show you the photo the better camera took in the reply)

[Perplexity @perplexity_ai]

Today we're open-sourcing Bumblebee, a read-only scanner for macOS and Linux.

It checks developer machines for risky packages, extensions, and AI tool configs.

Connected to Computer, it can trigger deeper scans whenever a new supply-chain risk emerges.

https://t.co/FOaWnF1yQy

[Avid @Av1dlive]

instead of watching 1 hour of Netflix tonight, watch this MIT Lecture

it's the clearest explanation I've seen of how to use Claude Code like a 100x Engineer

by minute 30 you'll understand Claude better than 99% of people paying for it

this builder took the key ideas and turned them into a practical guide on how to get started with Claude

bookmark and save it no matter what.

[Khairallah AL-Awady @eng_khairallah1]

https://t.co/nAovtRGY14

[Aakash Gupta @aakashgupta]

This guy literally broke down how to master Claude Code (even if you haven't coded before):

05:28 - Level 1: Why you start with Lovable
08:04 - Level 2: The Lovable + Claude Code bridge
28:37 - Level 3: Cursor + Vercel for real production
41:17 - Level 4: Agents, skills, and CLAUDE.md
42:50 - The CLAUDE.md memory file explained
45:24 - The PM orchestrator agent pattern
53:26 - How AI-native teams spend 50% of their time
01:01:33 - Why 90% of European PMs are still non-technical
01:07:45 - The Monday morning move

[CyrilXBT @cyrilXBT]

🚨 ANTHROPIC JUST KILLED THE DEMO AGENT ERA.

Their Agents team showed exactly what production grade looks like.

Not theory. Not a tutorial. A four layer framework for multi agent systems built to actually work in the real world.

30 minutes.

This is the video I wish existed 6 months ago.

[CaladriusHealth.AI @CaladriusHealth]

The primary NHCX beneficiary is not insurers or hospitals.
It is the infrastructure layer connecting all of them.

Here is our analysis of what that means for every participant in India's health claims ecosystem. 👇
https://t.co/MMgWx4ZOmV
#NHCX #CaladiusHealthAI

[CaladriusHealth.AI @CaladriusHealth]

Full breakdown in our first ABDM series piece, article and video both linked below.
Read - https://t.co/FzTQmSvhTU
Watch - https://t.co/I3293W75ra
#DigitalHealth #CaladriusHealthAI

[CaladriusHealth.AI @CaladriusHealth]

By March 2026: 86.64 crore ABHA numbers created, 90.70 crore health records linked.
Software integration across facilities and FHIR-compliant record generation are the next layer being built out.

[CaladriusHealth.AI @CaladriusHealth]

One distinction worth keeping clear:
NHCX standardises claims exchange between hospitals, insurers, and TPAs.
HIE-CM enables consent-based sharing of clinical records between providers.
Two different gateways. Two different problems.

[CaladriusHealth.AI @CaladriusHealth]

Four components make up that infrastructure:
ABHA: A unique health identifier for every resident
HFR: A verified directory of health facilities
HPR: A registry of health professionals
HIE-CM: The consent-based exchange layer for clinical records

[CaladriusHealth.AI @CaladriusHealth]

India has 1.69 lakh public health facilities, hundreds of thousands of private providers, and a large, diverse diagnostic ecosystem.
Each operates largely as its own information unit.
ABDM was built to create the shared infrastructure that connects them. A thread. 🧵#ABDM

[ClaudeDevs @ClaudeDevs]

Useful tip to cut time-to-first-token on longer prompts in the API: pre-warm the prompt cache.

Send your system prompt before the user prompt. Claude writes it to the cache, but skips generating any output.

When the real user request lands, it'll hit a warm cache.