Ubuntu 26.10 #StonkingStingray is now available.
Read our announcement for more details: ubuntu.com/blog/canonical-re…
#Ubuntu #Linux #OpenSource
Owen Barford retweeted
Do You Still Need an IDE If Agents Write Your Code? youtu.be/AHFGMkzrfwM?si=MW-9… via @YouTube
Owen Barford retweeted
🎥 SQL Server Performance Consulting for the AI Era youtube.com/watch?v=WDab9PXr… 🎥
Owen Barford retweeted

ElevenLabs Developers@ElevenLabsDevsAug 25
United States
United StatesConnected via WebAccount-level information, not a live location or per-post device.
Introducing the ElevenLabs MCP, now available in Claude.
Your team can manage your voice and chat agents where you already work - review recent performance, create new agents, update configurations, and even estimate LLM costs before changes go live.
Owen Barford retweeted
Less about which hypervisor to run, more about operating consistently everywhere.
Azure Local and Azure Arc are built for that, and Microsoft has been named a Leader in the 2026 Gartner® Magic Quadrant™ for Server Virtualization Platforms. msft.it/6016aaf9n
Owen Barford retweeted
Opus 5.5 is the best work estimator model i've ever used. This is calibration that is increasingly important as we delegate more and more work — don't tell me that it's going to take 2-3 working days (what a human would do) when for you, an enthusiastic, indefatigable, and embarrasingly parallelizable AGI, can get it done in 2-3 hours.
〰️ HAPPENING TODAY at 10AM PT 〰️
.NET Data Community Standup
Teach your AI agent database design with T-SQL static code analysis
See you LIVE here ➡️ msft.it/6013as6bL
Owen Barford retweeted
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to.
Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code.
Here's what that means for you:
Owen Barford retweeted
Agent Skills started as an experiment in Claude Code. Many across the industry have come to adopt it, so we at Anthropic found it more fitting to donate it to the @AgenticAIFdn, next to MCP.
We're donating Agent Skills to the Agentic AI Foundation (@AgenticAIFdn), the same foundation we donated MCP to.
Since December 2025, 70+ agent platforms have integrated the standard, including ChatGPT, Cursor, GitHub Copilot, and VS Code.
Here's what that means for you:
Owen Barford retweeted
5 AI Building Blocks Every Engineer Should Know
- LLMs
- Embedding Models
- RAG
- Agent Harnesses
- World Models
DuckDB 2.0 was released yesterday with a large set of core extensions. But one of the things that make DuckDB stand out is its extensive Community Extensions ecosystem.
Many of our amazing contributors have already migrated their extensions, while others are in the process of doing so. To help users monitor this transition, Community Extensions now have a compatibility matrix that shows the availability of an extension for a given platform and DuckDB version combination.
See for example the DuckPGQ extension's matrix at duckdb.org/community_extensi….
Owen Barford retweeted
Jensen closed his GTC Berlin 2026 keynote with this Hermes Agent demo as the finale.
He introduced it by saying the way to build an agent is to ask an agent to build it for you, so he installed and set up a customized Hermes in one prompt.
Then he used Hermes, running on @nvidia RTX Spark, to create a simulated training environment for the @huggingface Microduck. Hermes planned an obstacle course with Nemotron and had GPT-6 Astra build it using FreeCAD, Omniverse libraries, Blender, Newton, and Isaac Lab. Hermes trained thousands of simulated ducks on that course until the validated policy was ready to run on the real robot in the physical world.
At Nous, we believe open source is a practical tool as much as a philosophical ideal. It gives users the ability to build powerful, complex workflows chaining numerous local+cloud models, devices, and tools themselves instead of waiting for a company to enable them.
Owen Barford retweeted

Claude Code Changelog@ClaudeCodeLogOct 21
Austria
AustriaConnected via Austria App StoreAccount-level information, not a live location or per-post device.
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

Microsoft Research@MSFTResearchOct 21
United States
United StatesConnected via WebAccount-level information, not a live location or per-post device.
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…
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…
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

Salesforce@salesforceOct 21
United States!
United StatesConnected via WebLocation may be affected by a proxy or VPN.Account-level information, not a live location or per-post device.
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



























