David Silwal

Printed words have no life, but you can give life to the printed words if you are serious.

[David Silwal @DavidSilwal]

You have seen dead bodies being carried to the river. You have seen dead leaves, dead trees. The birds, so alive this morning, singing happily, chirping to each other, could be dead tonight. Should we not die? Die to our accumulations, our beliefs, our conditioning.

[Tencent Hy @TencentHunyuan]

🚀 Hy Memory 2.0 is out — open-source model, framework, and MemHub.
Your private memory steward.
Framework handles chat, work & code memories.
#1 open-source on 4 benchmarks.
Hy-Memory-30B-A3B beats Opus 5 across major frameworks.
MemHub (CLI + Mac) syncs across 10+ AI tools.

💻➡️

🔗 SDK & MemHub: https://t.co/uP58VJanj8
🔗 Model: https://t.co/nTQbJ2q8dl #HyMemory #AgentMemory

[Qiusheng Wu @giswqs]

Mapping the 2026 Nepal Floods with Free High-Resolution Satellite Imagery

In this tutorial, I demonstrate how to use GeoLibre to find, visualize, compare, and download open disaster imagery from Vantor, Planet Labs, and OpenAerialMap. You’ll learn how to create an interactive layer-swipe map, explore the terrain in 3D, and examine affected buildings and infrastructure.

Video tutorial: https://t.co/95pTEzIXls

Try it out:
- Web app: https://t.co/RuwG6u3sub
- GitHub: https://t.co/VXq8c1o2Nd

#Nepal #NepalFloods #geospatial #opensource #GeoLibre

[Osaurus @OsaurusAI]

This is a 9B model running a full agentic loop with Wi-Fi off.

Ornith 1.5. It read three sheets, cross-referenced the monthly rollups, and wrote a revenue analysis on its own.

Nothing left the Mac.

[astaxie @astaxie]

各位做智能体研发的都可以深度学习一下这一篇文章《Harness Engineering for Self-Improvement》 https://t.co/Fg3fJl9RE8

[Ishaan @ishaan_jaff]

LiteLLM is moving to Rust. 🦀

Sub-1ms overhead.
A sub-100MB binary.
The same Python SDK and AI gateway you already use.

Here's why and what's changing 🧵

https://t.co/zqzrBgQwnK

[Matt Pocock @mattpocockuk]

Announcing mattpocock/skills v1

- Achieved a 63% reduction in token cost for skill descriptions
- Split skills into model-invocable and user-invocable skills, adding /codebase-design, /domain-modeling, and /grilling
- (UPDATED) /writing-great-skills - rewritten from the ground up, encoding my skill-writing best practices
- (UPDATED) /diagnose -> /diagnosing-bugs - now model-invocable, awesome for fixing hard bugs
- (NEW) /ask-matt: a router skill that teaches you how all the engineering skills work together

[Alex Kuleshov @0xAX]

Great post by @0xkato - How LLMs Actually Work - https://t.co/urZOkGhUwP

[David Silwal @DavidSilwal]

@hamourage 🤣🤣🤣

[surmandal @surmandal]

I just published Nepal Just Had Its Most Consequential Week in a Generation , Here’s What You Need to Know https://t.co/v8CDYLEQeP

[GE @GuarEmperor]

Situation is being monitored

https://worldmonitor(dot)app/
https://www.conflictly(dot)app/
https://www.pizzint(dot)watch/
https://globe.adsbexchange(dot)com/
https://www.flightradar24(dot)com/

If u need this tools

[Boris Cherny @bcherny]

I'm Boris and I created Claude Code. I wanted to quickly share a few tips for using Claude Code, sourced directly from the Claude Code team. The way the team uses Claude is different than how I use it. Remember: there is no one right way to use Claude Code -- everyones' setup is different. You should experiment to see what works for you!

[GitHub @github]

Copilot is powerful—but it gets dramatically better when you give it the right context.

Here are 4 practical context-engineering techniques to improve Copilot’s accuracy 🧵👇

[David Silwal @DavidSilwal]

@davidfowl What subscription you are using?

[David Silwal @DavidSilwal]

@CodeByNZ @grok who is he?

[Peter Girnus 🦅 @gothburz]

Last quarter I announced a milestone.

30% of our code is now written by AI.

I called it "engineering velocity."

The board loved that phrase.

They didn't ask what the code does.

Neither did we.

It compiles. Usually.

That's the metric.

Someone asked about testing.

I said "AI-assisted quality assurance."

That means the AI writes the tests too.

For the code it wrote.

It finds no issues.

Very efficient.

This week we admitted Windows 11 core features are broken.

Audio doesn't work.

Explorer crashes.

Updates fail to install.

Users asked why.

I said "we're investigating."

Investigating means reading the code.

The code the AI wrote.

That no human understands.

Because understanding isn't scalable.

Our CTO says 95% of code will be AI-generated by 2030.

I believe him.

I have to.

We fired the people who would check.

They were "non-essential headcount."

Essential means writes code.

AI writes code.

Humans are overhead.

Overhead gets optimized.

We optimized 10,000 engineers last year.

This year the bugs arrived.

Unrelated, obviously.

The engineers we kept are debugging AI output.

They don't understand it either.

But they're "cross-functional."

Cross-functional means they do everything.

Everything means nothing well.

A user asked why their audio disappeared after an update.

I said "install updated drivers."

They asked why the update broke the drivers.

I said "report it via Feedback Hub."

They asked what happens to feedback.

I said "it helps us prioritize."

Prioritize means add to backlog.

Backlog means never.

But politely.

Someone on Hacker News called this "a privacy and consent disaster."

I called it "an evolving user experience."

Same thing. Different framing.

We released a fix.

The fix broke something else.

The something else was also written by AI.

The fix was also written by AI.

They're collaborating now.

I call it "autonomous iteration."

The autonomous iteration has created 47 new bugs.

Each bug spawns a fix.

Each fix spawns two bugs.

Exponential growth.

Just like our stock price.

Unrelated, obviously.

Satya told Mark we're at 30%.

Mark said he didn't know Meta's number.

Sundar said Google is also at 30%.

None of us know what the code does.

But we know the percentage.

Percentage is a metric.

Metrics go in earnings calls.

Earnings calls move stock prices.

Stock prices determine bonuses.

Bonuses determine success.

Success means the bugs don't matter.

Users asked when Windows will work again.

I said "we're committed to quality."

Quality means it ships.

Ships means it's your problem now.

Thank you for being part of the Microsoft family.

Family means you can't leave.

We're in your enterprise agreement.

For three more years.

The circle of innovation.

[Alvaro Cintas @dr_cintas]

A great way to learn prompt engineering is by studying how top engineers write system prompts.

Here’s the Gemini 3.0 system prompt:

[Min Choi @minchoi]

Anthropic literally dropped the Prompt Guide to 10x your Claude Opus/Sonnet 4.5

10 best practices you should know. Bookmark this. 👇

[Melvin Vivas @donvito]

This is sick 🤯🤯🤯

You can monitor Claude Code tasks using a project management app

Install the @linear MCP then ask Claude Code to make a plan first then save tasks to Linear. Ask it to update once each task is finished

$ claude mcp add --transport sse linear-server https://t.co/vZ8XWC0ssN

[ErikEJ @ErikEJ]

dotNET blog: Announcing .NET 10 https://t.co/HCl6kmT42n

[Brian Berletic @BrianJBerletic]

🇺🇸🇳🇵A Look at Nepal's "Interim" Government Following US-backed Regime Change...

Verified US funding behind 4 recently appointed ministers means HALF of the overall 8 ministers announced so far have been drawn from US government-funded fronts they founded or headed.

There are 2 more ministers - Dr. Sangita Mishra who worked at an extensively USAID-funded hospital - and was even mentioned in a US Embassy Nepal statement here: https://t.co/8b2fhcdMMy.

... more USAID funding for the hospital here: https://t.co/oe3yIqE5ww

... and Rameshwor Khanal who is an expert/advisor at several Western-funded/partnered "think tanks" in Nepal.

These 2 - alone - could be said to have "innocent" connections, but together with the other 4 overtly US-backed proxies - makes a definite pattern of standing up an overwhelmingly pro-US (and US-dependent) interim government.