@_saranshbarua@smallcaseHQ@TickertapeIN INDmoney already has an MCP server, and it’s read-only by design. There are no buy/sell/order tools, so an agent can’t trade even if it tries.
setup: https://t.co/UxL8FEAdql
Just curious, what would “app-layer control” look like for you?
As a general rule, most "regrets" after one is caught's aren't regrets about having committed the action, but regrets about having been caught.
Apologies count only when they are spontaneous, coming out of deep principles. Otherwise they are just an expression of submission.
There are two types of apologies. One by people relieving their conscience. The other is by those who are caught.
Never trust those who apologize after being caught.
You can now train your own Decision model with our free notebook! 💡
Qwen3.5-4B will generate decisions instead of text on just 8GB VRAM locally.
Learn to data prep (state, questions, gold answers), train, serve.
Notebook: https://t.co/avk6G2zyob
Guide: https://t.co/eNy4Ue0btG
i'm obsessed with this idea of "vibe coding physical devices" right now
even hardware noobs (like me!) can now finally turn our weird little ideas into gadgets that actually work
you just describe the gadget you want, then schematik (basically cursor for hardware) picks the correct parts, writes the code to run them and walks you through building it.
for example, here are 10 templates you can start with and make your own:
1. a plant that throws a disco
a soil sensor warns you when it’s thirsty. water it and the LED ring celebrates with rainbow lights and a victory tune lol
2. a morning receipt printer
turn it on and it prints today’s forecast onto a little paper briefing, with optional calendar events and blank lines for handwritten to-dos.
3. a digital hair clip
a tiny wearable screen that displays your own messages. press a button to cycle through them.
4. a weather display that tells you what to wear
checks the weather over wi-fi, then tells you whether to grab a jacket, umbrella, sunglasses, shorts or scarf. updates every 10 minutes.
5. a tiny desk companion
tap its face to change expressions, tilt it to move its eyes, and swipe through the clock, weather and stock price.
6. a lamp you control with your hand
swipe sideways to change color, up or down to change brightness. it saves your settings for the next time you power it on.
7. a pet treat dispenser
press a button and it weighs the bowl before opening the gate. it blocks another serving if the bowl’s already full or the cooldown hasn’t finished.
8. a live flight radar
a tiny round display that plots nearby aircraft and their callsigns, using live flight data fetched over wi-fi every 5 seconds.
9. a dedicated touchscreen chess game
tap pieces to move and play against a small chess engine running on the device. the screen and processor are already on one board.
10. an air monitor for your room
measures CO₂, temperature and humidity, then tells you when rising CO₂ means it’s time to air out the room.
well folks if you are interesting in understanding how to generate synthetic pretraining data I got a nicely edited 1h30 min tutorial with @joelniklaus from huggingface/nvidia just for you
in it we go through the result of their 90 experiments and contemplate what it means frfr
Claude Code now has a screen reader mode.
Running `claude --ax-screen-reader` swaps the visual terminal UI for plain, linear text that screen readers (like VoiceOver and NVDA) can follow.
Andrew Ng just released a 1-hour course on building agentic knowledge Graphs from scratch:
• 00:00 - Introduction to agentic knowledge Graphs
• 03:07 - Construction of agentic Graphs
• 14:00 - Architecture of multi-agent systems
• 23:00 - Building agentic graphs with Google ADK
• 01:06:03 - Why Graphsare the future of agentic AI
Worth more than 10 articles on loop engineering.
Watch it today, then read how to become a graph engineer in the article below.
Day 14/90 of Inference Engineering
I didn't finish the MNIST in CUDA project today, which made me hesitant to post since I didn't want to put out some slop.
But in the spirit of being consistent and showing up, here's a concept I've revisited today now that I've started writing CUDA again. This is an animation on the CUDA memory life cycle.
Generally speaking, when writing CUDA, memory management goes through the following stages:
1. Allocate memory on the host
2.Initialize / populate the memory
3.Allocate device memory
4.Copy host data to the device
5. Launch the kernel
6. Copy device data back to the host
7. Free the memory
-
On a brief reflection, I'm starting to write the matmul kernels in CUDA instead of in C. So this in itself is another paradigm shift in thinking. Excited to hone my technique over the coming week.
I'll update you guys when I've completed the project; otherwise I'll just make a post like usual on what I've learned during the day!
Introducing OpenShip.
An open-source application platform for building, deploying, operating, and scaling applications on infrastructure you own.
Replace deployment tools, managed services, and infrastructure workflows with one open-source platform.
Available today:
- Mail Server (Built in. One click).
• Runs on your own VPS
• Unlimited domains
• Unlimited mailboxes
• Modern webmail included
• Connect with Gmail, Outlook, Apple Mail, Thunderbird, or any IMAP/SMTP client
• Send email directly from your applications using SMTP
• No mailbox subscriptions or API fees
• High email deliverability
- Deployment:
• Deploy any stack
• Git-based deployments
• Zero-downtime deployments
• One-click rollbacks
• Development, Staging, and Production environments
• Multi-branch deployments with isolated environments • Deploy to VPSs, dedicated servers, cloud VMs, or your homelab
- Services:
Provision the services your applications need in one click.
Replace multiple managed providers with services running on your own infrastructure.
• Supabase
• PostgreSQL
• MySQL
• MariaDB
• MongoDB
• Redis
• MinIO
• Meilisearch
• Qdrant
• RabbitMQ
• Kafka
• ClickHouse
• Elasticsearch
...and deploy any other service alongside your applications.
- Operate:
• Live deployment logs
• Live request logs
• Real-time traffic analytics
• Automated backups
• Monitoring
• Secrets management
• Domains
• Automatic SSL
• Environment variables
• Scheduled jobs
• Health checks
-Multi Environments:
• Separate Development, Staging, and Production environments
• Deploy every branch independently
• Test changes before production
• Isolated services, secrets, and configuration per environment
- Security & Teams:
• Team management
• Role-based access control
• IP allow/block rules
• Rate limiting
• Security rules
- Developer Experience:
• Web dashboard
• Native desktop application
• CLI
• REST API
• MCP support for AI agents, just add the mcp and your agent can do the work for you
• Manage your infrastructure without living in SSH
- Coming Soon:
• Multi-server clustering for applications and databases
• One-click load balancing
• Horizontal scaling across multiple servers
• Built-in high availability and failover
• Scale from a single VPS to a cluster with the same workflow
• Just add servers. OpenShip handles the rest.
Open source.