San Francisco, California
Joined June 2019
- Tweets1.6K
- Following27
- Followers243
- Likes4.5K
Ankur Singh retweeted
Today we are talking with Vignesh Baskaran, the CTO and co-founder of @hexoai, about teaching AI agents to improve themselves. Vignesh has been training neural networks since 2012, back when he was still called a data scientist.
Then he became an ML engineer and now an AI engineer, though he says the underlying work has never really changed. It's to figure out how to make a system behave the way you intend it to. He built the litigation search engine that Google itself became a customer of, and now he's chasing something new, agents that rewrite and retrain other agents without a human in the loop.
We dig into Sia, the meta-agent at the center of Hexo's research, and why improving an agent means touching both its harness and its actual model weights, not just one or the other. We talk about proxy evals for when you don't have much to ground truth. The Darwin-Gödel machine and why formal verification is too strict a bar for anything commercial.
How Hexo's work echoes DeepMind's Alpha lineage from AlphaGo to AlphaEvolve, and the spectrum from clearly verifiable to totally subjective tasks? Why VAE evals are quietly wrecking agent quality across the industry, and a great story about an agent that discovered a customer's own eval file was silently corrupted, something buried in hundreds of thousands of traces that no human would have caught.
Watch on YouTube: youtu.be/SEYmUH_Ae3U
@tweetvbaskaran
Ankur Singh retweeted
We are hiring part time podcast hosts for Software Huddle.
Please reach out to [email protected] if you are interested.
Ankur Singh retweeted
Most people think the AI transition is happening inside AI companies. It's not. The whole ecosystem is accelerating.
@grinich joined @KentBeck on Still Burning to talk about what enterprise infrastructure reveals about where tech is headed. youtu.be/Kh24KYFfH5Q?si=HWJX…
Ankur Singh retweeted
Glauber from @tursodatabase talks about his AI stack✨
@glcst
Ankur Singh retweeted
Catherine Jue talks about 3 things her team at @usekernel looks for in new hires.
Visit kernel.sh to check out how Kernel is building Open Source infra for AI Agents.
Ankur Singh retweeted
Hour 24 - won VillageHacks at ASU
Day 10 - got into Momentum (@Devlabs_club)
Day 20 - first demo vid on X
here's the problem we're solving-
AI agents have no memory between sessions. but it's worse than that.
even mid-session, context gets compacted.
an infra decision made 3 months ago, a dead end you already hit, quietly erased as the chat grows, so when that same infra gets a bug today, your agent is reasoning blind.
no memory of why it was built that way.
no memory that the obvious fix was already tried. starting from zero. again and again.
trace is the intent-aware memory layer your agent was never built with.
#buildinpublic #AI #devtools #aimemory #Devlabs #startup
Ankur Singh retweeted
AI and Proactive Reliability with Kolton Andrus
Today we're talking with Kolton Andrus, the Founder and CEO of @GremlinInc, about what happens to reliability when AI is writing most of the code. Kolton helped build the Chaos Engineering practice of both Amazon and Netflix before starting Gremlin.
In our conversation we talk about scar tissue, the intuition engineers develop from being woken up at 3:00 AM to fix production outages, and how AI doesn't have any of it. It generates code in an afternoon that maybe took a team previously weeks to build, but none of those painful lessons come along for the ride.
We dig into why 10x more code might mean 10x more failures. The concept of reliability guardrails, think ethical guardrails, but for keeping your systems up. Why you still have to test in production no matter how good your staging environment is? How Gremlin is rethinking their product for the world where agents, not engineers, are essentially the primary users. And why we're entering a painful, narrow part of the hourglass before AI gets good enough to handle all of this on its own.
Watch On YouTube: youtube.com/watch?v=Gbm8gaoO…
@KoltonAndrus | @seanfalconer | @alexbdebrie
Ankur Singh retweeted
Making Data Agent Ready with Andre Elizondo
Today we are talking with Andre Elizondo, the Head of Innovation at @mezmodata about their open source agentic harness for SREs called AURA.
Mezmo got their start handling observability data at scale. Logs, traces, metrics, the usual stuff.
AURA is their answer to a growing problem, as system complexity outpaces humans' ability to make sense of all that data, how do you actually make it actionable for AI agents?
We get into their approach to context engineering, essentially making data agent ready before it hits the model. Why they built their own orchestrator in Rust? How they handle memory and self-correction in agent loops? Their take on MCP and where it fits versus Skills and code sandboxing and how the SRE role is evolving as agents become trusted teammates.
Watch on YouTube: youtu.be/vr6OA8ietsc
@seanfalconer | @alexbdebrie
Ankur Singh retweeted
“You can’t test what you can’t see.” 👀
Modern AppSec starts with visibility.
StackHawk maps your APIs from code → runtime → risk.
See it. Test it. Secure it. 🦅
🎥 Watch the full interview to see how StackHawk is redefining AppSec.
#AppSec #DevOpsSecurity #apisecurity
Modern Application Security and AI with Payton O'Neal
This episode features a conversation with Payton O'Neal from @StackHawk, focusing on the evolution of application security and the role of Dynamic Application Security Testing (DAST).
Payton argues that the shift from traditional security methods to more integrated, developer-friendly approaches is the way to go. The conversation covers the challenges and opportunities presented by AI in AppSec, the importance of bridging the gap between security and development teams, and the evolving threat landscape.
They also explore the impact of AI on software development and the potential for AI to enhance security testing and vulnerability management.
Watch On YouTube: youtu.be/1exalnuYtno
Ankur Singh retweeted
Kentik CPO, @MavTurner, talks about everything from network security to the future of #AI and Kentik's new Traffic Costs solution in an interview with @TheSoftwareWith.
Watch the interview: youtube.com/watch?v=T9VGkrZY…
#NetOps #NetworkSecurity #AIOps
Ankur Singh retweeted
Epic Web has something really big coming in coming days and Epic AI does as well. Stay tuned!
Ankur Singh retweeted
🚨 New from @GremlinInc: Reliability Intelligence is here.
Now every engineer across your organization has access to the expert knowledge needed to run reliability tests, track down root causes, and fix issues quickly.
Read more here: gremlin.com/blog/reliability…
Ankur Singh retweeted
Espresso AI Renovates Snowflake Warehouses with Kubernetes techtimes.com/articles/31154…
Ankur Singh retweeted
Software Reliability Agents with Amal Kiran 🎉
So if you're writing code or keeping systems running, you probably know the drill. Late night pages, chasing down weird bugs, dealing with alert storms. It's tough! It costs money when things break, and honestly, nobody loves that experience.
So the big question is, can we actually use something like AI, AI agents in particular, to make reliability less painful, more systematic? That's what we're talking about today. We have on the show with us Amal Kiran, the CEO and Co-founder of @temperstack.
They're building tools aimed at automating SRE tasks, think, automatically finding monitoring gaps, alerts, helping with root cause analysis, even generating Runbooks using AI.
So if you wanna hear about applying AI to real world SRE problems and all the tech behind it, we think you're gonna enjoy this.
Watch on Youtube: youtu.be/3Z-7JcyNUDM
@seanfalconer | @alexbdebrie
Ankur Singh retweeted
Full-Stack Tao is officially out!
A collection of my write-ups and ideas in the last 10 years. It holds everything I’ve learned about software design with practical examples with JavaScript and React.
Who is it for?
Intermediate engineers who want to make the leap to the senior level will take the most out of this book.
If you’re a beginner you might find it a bit challenging but it will still be rewarding.
If you’re an expert, I doubt I’ll be able to teach you something new, but you might enjoy my writing either way.
What’s the book about?
It’s a collection of good practices focused on software maintainability above everything else.
What technologies does it cover?
This isn’t a book that will teach you React. It uses popular tools to explain key concepts, but the principles in it are applicable across all programming languages and tech stacks.
The goal is to teach you timeless software design principles that you can apply in your career, regardless of the specific tools you’re using.
What are the contents?
Chapter 1 - The importance of principles.
Chapter 2 - Code-level best practices, loops, conditionals, variables, and functions.
Chapter 3 - The SOLID principles in practical examples.
Chapter 4 - Practical clean architecture, modules, forms, and state management.
Chapter 5 - Designing a lambda, a script, ORMs, DB complexity, testing.
Chapter 6 - Setting up the project, picking a tech stack, how to build features.
I hope you like it! Links are in the next post!
Ankur Singh retweeted
These 5 companies were on the brink of shutting down:
- Nvidia
- FedEx
- Airbnb
- Notion
- Evernote
Here’s 5 of my all-time favorite Silicon Valley comeback stories:
