Vehicles, SQL Server and Virtualisation...and maybe a touch of cooking.
London
Joined March 2012
- Tweets7.7K
- Following1.4K
- Followers91
- Likes11.7K
Owen Barford retweeted
Claude Code 2.1.307 has been released.
43 CLI changes, 1 system prompt change
Highlights:
• Added /claude-api api-version to switch Claude API code to 2026-10-21, enabling updated API behavior
• Stop double HTTP MCP sends on disconnect; only idempotent/read-only tools retried to avoid duplicates
• The /clear command now makes cleared conversations persist across restarts, preventing them from reappearing
Full details are in thread ↓
Owen Barford retweeted
AI agents are writing more code. How can developers ensure that code is correct?
Microsoft Research’s Proof-Driven Development (PDD) Kit explores a more rigorous approach: it translates a developer’s intent into a formal specification, then uses formal verification to prove that generated code meets it.
PDD Kit works with Verus for Rust and is integrated with @GitHubNext’s Chopin, bringing formal methods into an AI-assisted development workflow for teams.
See the work in action at @github Universe, Oct. 28–29, 2026.
Owen Barford retweeted
My report makes six key recommendations:
Fix the broken understanding of how the gas market works. Policymakers should recognise that British gas production is not sold on global markets at a global price. The GB gas market uses marginal pricing and additional domestic production displaces more expensive LNG imports, thereby reducing British gas prices. The report argues that claims that additional UK production cannot affect domestic prices are simply wrong.
Increase UK Continental Shelf gas production. Domestic gas should be preferred to imports wherever possible. UKCS gas is both cheaper and cleaner than imported LNG and provides a secure source of supply directly connected to the British gas network.
Reduce reliance on electricity imports. Britain is increasingly depending on electricity imports during periods of low domestic renewable generation. However, highly correlated weather patterns mean low wind generation in Britain can coincide with shortages elsewhere. The report warns that Norway and France cannot be assumed to provide unlimited electricity to their neighbours during periods of stress.
Model gas and electricity security together. The gas grid transports far more energy than the electricity network. Electrifying heating will take decades while gas-fired generation will remain critical to electricity security for years to come. The report argues that planning should recognise the interdependencies of gas and electricity to a greater extent.
Focus on cheap energy. Rapidly rising network costs are overtaking fuel costs as the main driver of energy bills. The report calls for tighter control of network expenditure and for the suspension of the Connect & Manage regime, arguing that consumers should not be required to fund expensive infrastructure whose output is frequently constrained or wasted.
Treat energy security as national security. The government should subject energy policy to an explicit national-security test, prioritising resilience, diversity of supply, sufficient domestic energy capacity and the preservation of strategically important industrial capability alongside affordability and sustainability.
watt-logic.com/wp-content/up…
Owen Barford retweeted
Duet vs. Dot
Full vibe check on @AnthropicAI's Duet: every.to/vibe-check/vibe-che…
Owen Barford retweeted
Microsoft.UI.Reactor: a C#-first way to build #WinUI apps: devblogs.microsoft.com/ifdef…
Owen Barford retweeted
Anthropic just destroyed all proactive agent startups.
That's what you'll see on your timeline.
That couldn't be further from the truth.
Personal agents, unlike other agent types, will exist in different flavors and personalities.
It's nice that Claude Duet runs on Opus 5.5.
Unlike other agent types, people will really think carefully about which personal agent to pick. Here, people think more carefully about trust, personality, intent understanding, continual learning, etc. The best personal agent is the one you can trust, not just the fastest one that gets the work done effectively.
But I think people will use multiple personal agents for different types of tasks/work. I think we are about to see an explosion of vertical personal agents.
Which one do I use? I am still testing a bunch of them (dots, Muse, and Grok Bot). But I have actually just built my own with Pi Durable. I like mine better because it is hyper-personalized to how I use personal agents.
Owen Barford retweeted
Want to learn more about agent memory?
We're hosting a virtual workshop on November 3rd! events.langchain.com/registe…
Owen Barford retweeted
Yes, folks, Damian is correct. The playbook is right there waiting for you.
Head of sales asking where to start with agents? Send them this.
@salesforce is the one rolling AI out at the biggest companies in the world, so this is the best playbook I’ve found on how an enterprise should approach agents. It shows how much the data matters and how to build the next layers on top of the CRM.
Salesforce refreshed its playbook, Become an Agentic Enterprise. It’s built on what they call Customer Zero, testing everything on their own 80,000 employees first, plus a 2026 study of 2,000+ AI decision-makers.
Six chapters, the best bit from each:
→ Goals. Pilots stall on resistance and low AI fluency.
→ People. 99% of companies running agents keep humans overseeing them.
→ Use case. “Agents that live in the flow of work get used.”
→ Processes. Built-in AI beats bolted-on tools on adoption.
→ Data. Salesforce grades its SDR agent against six million human SDR emails. It generated nearly $120M in pipeline.
→ Coaching. Asymbl’s sales team coaches its agent every week. 3,789% ROI.
Workflows, data and the record of how your best reps sell already live in your CRM. Build the agents there and keep a human coaching them.
Read the full playbook → lnkd.in/e9GUyUqh
---
Join the club → gtmclub.substack.com
Owen Barford retweeted
Microsoft Ignite is 4 weeks out.
Join us in San Francisco or online for interactive labs and learning sessions, plus onsite certifications for in-person attendees.
Register and check out the session catalog here:
aka.ms/ignite
Owen Barford retweeted
#GitHubUniverse kicks off next week, October 28–29.
Grab your pass to join us in person or sign up to tune in virtually.
➡️msft.it/6013aappD
ALT A promotional image for GitHub Universe 26, featuring colorful graphic elements and a cartoon cat logo. Text includes 'Experience GitHub Universe' and event details: 'Fort Mason S F, C A, Oct 28-29, 2026.'
Owen Barford retweeted
We’re opening a research preview of Claude Duet, a new app where Claude works as a proactive agent.
It comes to you with what needs your attention, completes tasks you ask of it, keeps working when you step away, and checks with you before it acts on your behalf.
Owen Barford retweeted
Build on your DevOps expertise with agentic AI.
The new Microsoft Certified: Agentic DevOps Engineer Expert certification is designed for DevOps engineers, developers, and infrastructure administrators who want to deepen their expertise and learn how to integrate AI assistance and AI agents into their everyday work. Earn the Microsoft Certification by passing Exam AZ-401 (beta).
📢 The first 300 candidates who take the exam on or before November 9, 2026 can receive 80% OFF: techcommunity.microsoft.com/…
Owen Barford retweeted
Better PostgreSQL diagnostics, beginner resources, and observability benefit the entire community.
@vyruss is exploring all three at #PGConfEU: hubs.la/Q04BMYtc0
His book is 45% off with code pgconfeu26 through Nov. 3rd: hubs.la/Q04BMYcD0
Owen Barford retweeted
btw at 100k views in 24hrs, @jediahkatz's talk is an early candidate to be THE breakout talk of aie nyc
the bar is set very high for @poteto's keynote at AIE CODE next month hahaha
Inside Grok Bot: is the agent harness dead?
@jediahkatz of @spacexai explains why smarter models let Cursor remove prompts and guardrails, and why Grok Bot is adding them back.
Watch his AI Engineer New York talk:
youtube.com/watch?v=7Y4sbZgB…
ALT Jediah Katz holds a microphone in front of agent-harness diagrams and illustrated agents. The graphic reads "Is the Agent Harness Dead?" and carries AI Engineer New York and SpaceX logos.
Owen Barford retweeted
What’s changed in “the unwritten rules” of engineering management since the 2010s, why are hands-on managers “back”, and what has it done to the engineer-to-CTO career path? With Will Larson (@Lethain). Timestamps:
00:00 Intro
08:20 Stories from Yahoo!
12:47 Digg’s v4 rewrite: the insider story
26:02 Will’s path to eng leadership
30:03 Uber, Stripe, Carta, and Calm
35:11 What does a CTO do?
38:09 Will’s role at Imprint
42:48 How engineering management has evolved
51:08 ZIRP’s impact on tech
57:21 Career ladders
1:01:03 Eng 1 vs Eng 2
1:06:58 How software engineering roles are changing
1:16:25 Revised rules of engineering leadership
1:21:57 The risks of becoming a bureaucrat as an EM
1:25:57 How to become a CTO?
1:31:33 Middle management vs. line management
1:41:36 Will’s writing
1:52:13 Book recommendations
Brought to you by:
• @turbopuffer – vector and full-text search built on object storage: fast, 10x cheaper, and extremely scalable. turbopuffer.com/v3
• @EntireHQ – Git hosting, rebuilt for the agentic era. Entire hosts your code in-region, and is up to 89x faster than any other competitor. entire.io/pragmatic
• What if you only needed a single test to harden your system? Get a free introduction to property-based testing: through a live, online webinar hosted by Hillel Wayne, author of Logic for Programmers and Developer Educator at @AntithesisHQ. RSVP here: pages.antithesis.com/webinar…
Two sage observations from Will on how engineering management changed:
1. ZIRP shaped engineering management practices in the 2010s, Will believes. As he put it:
“Back then, your ability to hire and close and retain became the differentiator between successful companies. The less successful ones simply couldn’t retain great people.
[This dynamic on hiring and retaining] pulled leverage back into the engineer’s hands and created a very different environment. So, companies were pitching themselves as a more relaxed environment, more focused on you, and offering more career development. And I think in ways that I think were often kind of self-defeating.”
2. Blunt message for middle managers: retire or re-skill.
Will left a team of 250 at Carta to head up 25 tech people at Imprint. He purposely took a “step back” in his leadership career because he believes things are changing so radically that the engineering leadership profession that we know will not exist in three years.
Amid all this, Will says that line management can be a lot more engaging for executives these days because the tools for line management and the tools for writing software are really good. Plus, the tech industry has always been volatile: during the 2010s most of us simply forgot about this!
Owen Barford retweeted
So @AkkaDotNET v1.6 is already an order-of-magnitude improvement for networking and serialization performance over v1.5, but the next beta of it is about to be even faster:
Looking at about a ~20% throughput improvement across the board and significant reductions in CPU / mem resources per message.
All from simple mechanical fixes plus some experimental IActorRef compression on the receiving side of the wire.
ALT Akka.NET v1.6.0-beta4 vs 1.6.0-beta3 throughput numbers
ALT Akka.NET v1.6.0-beta3 vs. v1.6.0-beta4 CPU per message
Owen Barford retweeted
Chopin + Proof-Driven Development Kit from @GitHubNext and @MSFTResearch enable teams to ship AI-generated code to production without reviewing it line by line, with stronger assurance than code review and testing alone.
Now in research preview ⬇️
How do you _guarantee_ your agent's code is correct? You prove it.
Introducing Proof Driven Development Kit (PDD Kit) from @MSFTResearch.
PDD Kit helps turn your plan into a formal spec, then proves the agent's code meets that spec for every input. No vibe verification. PDD Kit is integrated with @GitHubNext's Chopin, so you can plan as a team.
PDD Kit takes an app's login flow from intent to a verified pull request:
It discusses your code, infers your intent as it goes, and proposes a formal spec in Verus, a proof language for Rust.
Once you approve the spec, the Verus verifier automatically proves the code meets it.
Where proof isn't possible, it falls back to empirical verification with tests and computer-use agents (CUAs).
It works on Rust today. No new language, no change in how you produce the underlying code, making formal methods more accessible.
The goal is a verified software factory, where engineers review specifications instead of code.
Come see it in action at GitHub Universe, Oct 28–29. Swing by the Speakeasy and ask for GitHub Next!
Owen Barford retweeted
For decades, a key question about the challenges of high-dimensional computation resisted proof. New research resolves the KLS conjecture, removing a major barrier to understanding the efficiency of randomized algorithms used throughout science and computing.
msft.it/6011aar01
Owen Barford retweeted
Claude Security now keeps up with your code as it changes.
Connect your repositories once. Claude runs a deep first scan, then re-scans as changes land, so findings stay close to the current state of your code.
In public beta on Claude Enterprise.
Owen Barford retweeted
We are cooking up something kind of incredible. Here is a sneak peak of our team Canvas we collaborated on.
Going to @GitHub Universe?
Join myself, @pierceboggan, @Jujujuliakasper, @okatiesavage and @JamesMontemagno for a look at how your team can work seamlessly with @GitHub Copilot...pretty much everywhere.
reg.githubuniverse.com/flow/…
