Divy Yadav

https://github.com/dvy246

How to Crack an AI Engineer Interview in 2026 When Meta and Canva Hand You an AI Assistant

Oct 3, 2026

•

5 min read

How to Crack an AI Engineer Interview in 2026 When Meta and Canva Hand You an AI Assistant

Interviewers use that assistant to watch how you think, and AI engineer questions push on what breaks. Prep for both.

Divy Yadav

I Compared Opus 5.5 and GPT-6 Astra. Here's the One You Should Actually Use.

Sep 27, 2026

•

4 min read

I Compared Opus 5.5 and GPT-6 Astra. Here's the One You Should Actually Use.

Both companies published their own benchmark tables. They don't agree with each other, and they don't agree with anyone running independent tests either.

Divy Yadav

7 Claude Tricks That Make You Look 10x Smarter (Most Users Never Touch These)

Sep 20, 2026

•

3 min read

7 Claude Tricks That Make You Look 10x Smarter (Most Users Never Touch These)

You're using 10% of what Claude can do. Here are 7 specific techniques that separate power users from everyone typing basic questions into the chat box.

Divy Yadav

AI Sandbox Networking: Only One Platform Proved Its Numbers

Sep 20, 2026

•

3 min read

AI Sandbox Networking: Only One Platform Proved Its Numbers

L4 vs L7 ingress architecture across Tensorlake, E2B, Daytona, and Fly.io, and why documentation alone doesn't prove a redesign worked

Divy Yadav

GPT-6 Astra just launched. Here's what you actually need to know

Sep 15, 2026

•

3 min read

GPT-6 Astra just launched. Here's what you actually need to know

OpenAI's calling it a step toward AGI. I went through the system card, the pricing, and the benchmarks so you don't have to guess what's real.

Divy Yadav

Claude Fable 5.1 Isn't About Intelligence

Sep 2, 2026

•

3 min read

Claude Fable 5.1 Isn't About Intelligence

Anthropic's newest model got smarter. The bigger story is what happened to Claude API pricing for AI agents, and why that matters more than the benchmark chart.

Divy Yadav

AI Document Processing Tools: My Top 5 Picks

Sep 1, 2026

•

2 min read

AI Document Processing Tools: My Top 5 Picks

One of the five tools I ranked stopped being an independent company halfway through writing this, and almost nobody noticed

Divy Yadav

Your AI agent's sandbox doesn't need forever-access

Aug 31, 2026

•

3 min read

Your AI agent's sandbox doesn't need forever-access

A simple pattern for shrinking network permissions the moment untrusted code starts running, without tearing down the sandbox.

Divy Yadav

Nvidia's $12.9B Hugging Face deal has one problem: Nvidia

Aug 29, 2026

•

3 min read

Nvidia's $12.9B Hugging Face deal has one problem: Nvidia

The platform Nvidia is buying was built specifically so developers wouldn't need Nvidia. That's exactly why Nvidia wants it.

Divy Yadav

I Thought kTLS Made It 2x Faster. I Was Wrong.

Aug 23, 2026

•

3 min read

I Thought kTLS Made It 2x Faster. I Was Wrong.

A staged benchmark caught the real source of the gain before the wrong technique got the credit for it.

Divy Yadav

SpaceX just bought Cursor for $60B (here's what actually changes for developers using Claude inside it)

Aug 15, 2026

•

3 min read

SpaceX just bought Cursor for $60B (here's what actually changes for developers using Claude inside it)

A rocket company now owns the editor a lot of us code in every day. The real story isn't the price tag, it's who cut who off first.

Divy Yadav

5 Claude AI tricks that make you look smarter (most people still get these wrong in 2026)

Aug 6, 2026

•

3 min read

5 Claude AI tricks that make you look smarter (most people still get these wrong in 2026)

5 Claude AI tricks Anthropic's own team confirmed in 2026, including which 2023-era prompting habits are now quietly hurting your results.

Divy Yadav

Claude Opus 5 Just Beat Fable 5 on 7 of 12 Benchmarks. At Half the Price.

Jul 26, 2026

•

3 min read

Claude Opus 5 Just Beat Fable 5 on 7 of 12 Benchmarks. At Half the Price.

Anthropic's own $25 model just made its $50 flagship hard to justify. Here's exactly when to still pick the expensive one.

Divy Yadav

I Gave OpenCode Full Shell Access—Tensorlake Changed Everything

Jul 23, 2026

•

2 min read

I Gave OpenCode Full Shell Access—Tensorlake Changed Everything

OpenCode can run any command on your machine, no approval needed. Here's the one change that made me stop worrying about it.

Divy Yadav

Context Engineering

RAG vs. Long Context: The 333x Cost Difference Nobody's Prompt Admits

Jul 15, 2026

•

4 min read

RAG vs. Long Context: The 333x Cost Difference Nobody's Prompt Admits

Someone on your team wants to delete the RAG pipeline. Here's the invoice that argument doesn't account for.

Divy Yadav

Memory Checkpointing

Jul 15, 2026

•

3 min read

Memory Checkpointing: Fork Parallel AI Sandboxes Without Reinstalls

Eight parallel experiments. Eight identical 40-second setups. You're paying for the same work eight times.

Divy Yadav

AI Agent Drift: Why Your Agent Gets Worse Without You Changing Anything

Jul 10, 2026

•

4 min read

AI Agent Drift: Why Your Agent Gets Worse Without You Changing Anything

The silent degradation killing production agents in 2026, and the six mechanisms behind it

Divy Yadav

AI document processing

Jul 7, 2026

•

4 min read

AI Document Processing: Why 95% Accuracy Fails

The four production gaps a passing demo never tests, and how a six-agent system closes them

Divy Yadav

ai agents memory

Your AI Agent Isn't Broken. It's Forgetting Everything Between Runs.

Jul 4, 2026

•

2 min read

Your AI Agent Isn't Broken. It's Forgetting Everything Between Runs.

One engineer's automation racked up a $600 overage before anyone noticed why.

Divy Yadav

Claude Managed Agents Need Persistent State

Jun 28, 2026

•

3 min read

Claude Managed Agents Need Persistent State

State management is the infrastructure problem nobodytalks about until it breaks at 9am on a Tuesday.

Divy Yadav

Claude

Jun 24, 2026

•

3 min read

The person who built Claude Code doesn't prompt it anymore

Harness engineering. Loop engineering. Four layers that rewrote how engineers work with AI agents in 2026. Here's where you are in that stack

Divy Yadav

Context Engineering

Jun 21, 2026

•

1 min read

RAG Is Not Context Engineering (And Confusing Them Is Breaking Your AI in Production)

You filled one of six context slots. No wonder it keeps breaking.

Divy Yadav

Your AI Agents Aren't Slow Because of Concurrency

Jun 16, 2026

•

2 min read

Your AI Agents Aren't Slow Because of Concurrency

The real-time sink happens before any agent even starts working

Divy Yadav

Fable 5 is gone. The US government took it.

Jun 13, 2026

•

4 min read

Fable 5 is gone. The US government took it.

Three days after Anthropic's most powerful model launched, a federal export control directive forced it offline for every customer on earth. Here is exactly what happened.

Divy Yadav

Jun 6, 2026

•

4 min read

ChatGPT is building a profile on you. You never wrote most of it.

OpenAI's Dreaming V3 dropped June 4. The memory upgrade is real. So is what it stores about you without asking.

Divy Yadav