Sign in

O'Reilly

@oreilly.bsky.social
942 followers 24 following 875 posts

The premier learning platform for technology professionals. Sign up for your free 10-day trial now. www.oreilly.com

PostsRepliesMedia
O'Reilly @oreilly.bsky.social · 11h
That’s a wrap on six weeks of Software Architecture! Participants explored patterns, distributed systems, evolutionary architecture, and more with Neal Ford and Mark Richards. Get updates on future cohorts: bit.ly/4ym4WDQ
bit.ly
Become a Software Architect with Neal Ford and Mark Richards - O'Reilly Media
Learn software architecture directly from top experts with O'Reilly's immersive six-week cohort.
020
O'Reilly @oreilly.bsky.social · 13h
AI agents are becoming cheaper, more specialized, and more autonomous but accountability can’t be delegated. “AI has infinite patience and is fundamentally probabilistic.” Read Mike Loukides’s October #Radar roundup: bit.ly/4hIx2BL
bit.ly
Radar Trends to Watch: October 2026
Developments in hardware, privacy, software development, and more
020
O'Reilly @oreilly.bsky.social · 13h
Over 20 sessions with instructor Kesha Williams, you’ll build one thing: an AI code reviewer that runs in your CI pipeline, reads real pull requests, and posts inline comments at the exact file and line. Register to attend: bit.ly/4zfEM54
bit.ly
Lunch & Learn: Claude Edition
Turn your lunch break into an AI productivity boost
020
O'Reilly @oreilly.bsky.social · 05/10/2026
“You don’t need to replace the systems that already handle your application logic to help them work with agents.” Bruce Hopkins shows how to add an MCP layer around a stock-data API. Read Michelle Smith’s #Radar article: bit.ly/3W7Kbgi
bit.ly
Zero to Agent in 30 Minutes: Build Your First Agent with MCP
Turn existing APIs into tools an AI assistant can use
010
O'Reilly @oreilly.bsky.social · 05/10/2026
“Prompt tuning and stronger models can improve the agent’s responses, but can’t provide guarantees for actions.” Reliable agents need enforceable policies, narrowly scoped authority, and recoverable state. Read Angie Jones’s #Radar article: bit.ly/4j1doDe
bit.ly
How to Build Reliable AI Agent Systems for Production
The following article was originally published on the Agentic AI Foundation blog site and is being republished here with the author’s permission.A
030
O'Reilly @oreilly.bsky.social · 02/10/2026
Five weeks down, one to go! This week, our Software Architecture cohort dove into evolutionary architecture and Architecture as Code as they prepare for the final session. Interested in future opportunities? Add your name: bit.ly/4ym4WDQ
bit.ly
Become a Software Architect with Neal Ford and Mark Richards - O'Reilly Media
Learn software architecture directly from top experts with O'Reilly's immersive six-week cohort.
000
Reposted by O'Reilly
Andrew Stellman 👾 @andrewstellman.bsky.social · 02/10/2026
From my @oreilly.bsky.social Radar article, “The AI Teaching Toolkit: Practical Guidance for Teams” www.oreilly.com/radar/the-ai...
011
O'Reilly @oreilly.bsky.social · 02/10/2026
Coding agents need project context without a courtroom transcript. “Each governing ADR should describe the decision currently in force.” Read Duncan Davidson’s article on keeping decision records useful for agents and humans: bit.ly/4rGXPD7
oreilly.com
Coding Agents Love Decision Records
The following article originally appeared on Duncan Davidson’s blog and is being republished here with the author’s permission.Decision records give
000
O'Reilly @oreilly.bsky.social · 02/10/2026
“Deploying an agent means taking responsibility for the systems around it.” As agents move faster and act with more autonomy boundaries become critical design choices. Read Michelle Smith’s latest article: bit.ly/3Vt0tjF
oreilly.com
This Week in AI: Agents Are Outrunning the Systems Around Them
Cyberattacks, power constraints, faster model releases, and consumer agents put pressure on the systems built to support them
010
Reposted by O'Reilly
Excel Cookbook @theexcelcookbook.bsky.social · 01/10/2026
On October 7th, I’m running a new #OReilly course: AI-Powered Excel Charts. Find out more and register: learning.oreilly.com/live-events/... @oreilly.bsky.social
learning.oreilly.com
AI-Powered Excel Charts
Create effective charts and dashboards using Copilot, Claude, ChatGPT, and other generative AI tools
111
Reposted by O'Reilly
techupskills.bsky.social @techupskills.bsky.social · 02/10/2026
Coming up in October from @techupskills.bsky.social , our popular @oreilly.bsky.social courses on #GitHub #Copilot & Implementing #AI #Agents in #Python. Also NFJS ones on Fine-Tuning Small AI Models, AI #Security & #Prompt Eng. Details in video & at techskillstransformations.com/training-cal... !
021
Reposted by O'Reilly
brentclaster.bsky.social @brentclaster.bsky.social · 02/10/2026
Coming up in October from @techupskills.bsky.social , our popular @oreilly.bsky.social courses on #GitHub #Copilot & Implementing #AI #Agents in #Python. Also NFJS ones on Fine-Tuning Small AI Models, AI #Security & #Prompt Eng. Details in video & at techskillstransformations.com/training-cal... !
031
O'Reilly @oreilly.bsky.social · 01/10/2026
“For decades, people have adapted to computers. It now seems possible that software may finally start adapting to people instead.” Check out this #Radar article by Robert Englander to learn more: bit.ly/4rEy85Q
oreilly.com
The Future of Software May Be Conversational Rather Than Autonomous
The following article originally appeared on Robert Englander’s blog site and is being reposted here with the author’s permission.The software industry
000
O'Reilly @oreilly.bsky.social · 01/10/2026
We'll be at Gartner IT Symposium/Xpo in Orlando, Florida, October 19–22, talking with technology leaders about the skills their teams need to keep pace with AI. Add the O'Reilly booth to your agenda and bring your questions.
000
O'Reilly @oreilly.bsky.social · 30/09/2026
On October 5, Rohit Krishnan will join @timoreilly.bsky.social to share what has experiments reveal about human-agent coordination and how organizations should divide work between people and agents. Register here: bit.ly/4chZk4H
010
O'Reilly @oreilly.bsky.social · 30/09/2026
What’s the data scientist’s role when agents can run the analysis? “AI-native data scientists build and direct an analytical process in which agents can investigate, receive feedback, and return evidence for review.” Read more: bit.ly/4AGrMqV
oreilly.com
The Agentic Data Science Playbook
How to build and direct data science agents, and make each investigation improve the next.
020
O'Reilly @oreilly.bsky.social · 30/09/2026
“AI-generated UI should not be trusted because it looks complete. It should be trusted because the team has checked the right things.” Read the #Radar article Niharika P. Pujari to learn more: bit.ly/4jxix68
oreilly.com
Evaluating AI-Generated Frontend Code: What Should We Actually Test?
000
O'Reilly @oreilly.bsky.social · 29/09/2026
As AI takes on more of the work of writing code, human judgment matters more, not less. “Human taste and judgment still matter. They’re going to continue to matter.” Read @timoreilly.bsky.social article: bit.ly/4db2ZkC
bit.ly
Superpowers for Humans
I’ve known Jesse Vincent for more than 20 years, since the days when I was still editing and publishing Perl books and organizing the Perl Conference and he
020
O'Reilly @oreilly.bsky.social · 29/09/2026
“AI is great at finding facts, organizing facts, and even writing about the things it finds, but what does it mean to possess that knowledge, to incorporate it into our thinking?” AI should build our understanding, not replace it. Read more: bit.ly/3Vo1pG0
oreilly.com
Not About Navier-Stokes
Using AI productively
001
O'Reilly @oreilly.bsky.social · 29/09/2026
A fully built data center still isn’t ready for production until its services come online in the right order. “Without that end-to-end view, every team can report that its own work is on track while the region as a whole remains blocked.” Read Ankur Gupta’s #Radar article: bit.ly/3VhFX5G
oreilly.com
A Data Center Is a Dependency Graph Before It Is a Building
The buildings and physical infrastructure for a new hyperscale data-center region are complete. Power is live and redundant, the cooling loops are balanced,
020
O'Reilly @oreilly.bsky.social · 28/09/2026
“Graph modeling asks the question before that: What should the nodes and edges be?” In today’s #Radar article, Ammar Mohanna, PhD explores why graph modeling should be a first-class stage of AI development. Read to learn more: bit.ly/4dIT2uV
oreilly.com
From Raw Data to Graph-Native AI
Why graph modeling deserves as much attention as graph learning, GraphRAG, agents, and graph foundation models
000
O'Reilly @oreilly.bsky.social · 28/09/2026
“In effect, you’re giving your agents a computer of their own.” Remote sandboxes let agents run code, install software, and use browsers, without touching your machine. Read Michelle Smith’s #Radar article: bit.ly/4y0KBmg
bit.ly
Zero to Agent in 30 Minutes: Give Your Agent Its Own Computer
How sandboxed computers let agents run code, use browsers, and work independently of your machine
030
O'Reilly @oreilly.bsky.social · 26/09/2026
An enormous share of LLM-powered components in AI applications today are being asked to make decisions: pass/fail, route A or B, etc. That’s something that LLM-as-a-judge evaluations are doing all the time, so it really made our ears perk up at Arize AI: bit.ly/3Tus7vU
bit.ly
Will TypeSafe's Jev Change How We Build AI Applications?
The following article originally appeared on Arize’s blog and is being reposted here with the author’s permission.This week the AI community was in uproar
010
O'Reilly @oreilly.bsky.social · 26/09/2026
Steven Hayes' conversation with Dan Gookin started as a publishing reunion. It ended with a much larger question: What happens when the software you rent becomes infrastructure you can’t leave? Read on #Radar: bit.ly/4hIXPip
bit.ly
When Software Subscriptions Become Public Policy
My conversation with Dan Gookin, the original For Dummies author and now mayor of Coeur d’Alene, Idaho, started as a publishing reunion. It ended with a much
000
O'Reilly @oreilly.bsky.social · 26/09/2026
AI systems are gaining access to more tools and data, raising new questions about oversight and accountability. This Week in AI Christina Stathopoulos examined how those questions are playing out in model safety, government oversight, and digital marketing bit.ly/4hgtt6I
000
O'Reilly @oreilly.bsky.social · 25/09/2026
"A software factory is a repeatable loop around software work. If you’re building a software factory, code good enough to ship still needs human taste and ownership. We’ll discuss this including whether you need a factory just yet." @addyosmani.bsky.social bit.ly/4y9Jnps
bit.ly
Human Judgment Doesn't Leave the Software Factory, It Relocates
A field guide to building a software factory that still has an owner.
010
O'Reilly @oreilly.bsky.social · 25/09/2026
"Ask most engineers what MCP is and you’ll get the same answer: a way to plug tools into an LLM. Fair enough, as far as it goes. But that description treats MCP like plumbing, and I don’t think plumbing is the right metaphor." #Radar bit.ly/4dVxYRW
bit.ly
MCP Is Not Just Another API Standard
What Model Context Protocol actually changes for agentic systems, and what it doesn’t
020
O'Reilly @oreilly.bsky.social · 25/09/2026
Week 4 of our Software Architecture cohort went deep into distributed architectures. With Neal Ford & Mark Richards, participants explored communication, consistency, coordination, and how these forces come together in approaches like transactional sagas. bit.ly/4ym4WDQ
bit.ly
Become a Software Architect with Neal Ford and Mark Richards - O'Reilly Media
Learn software architecture directly from top experts with O'Reilly's immersive six-week cohort.
000
O'Reilly @oreilly.bsky.social · 25/09/2026
Join @timoreilly.bsky.social at the O’Reilly booth on Wednesday morning before his keynote with Eric Reis. Stop by to chat about building AI companies that matter or just to say hi. Where: The O’Reilly booth #118 When: September 30, 8:30am–9:00am
000
O'Reilly @oreilly.bsky.social · 22/09/2026
"The clearest live adversarial problem involving AI is much more ordinary: humans using AI against other humans. Criminal applications are already real and deserve serious attention." Read #Radar article by Venkatesh Rao to learn more: bit.ly/4yggPuI
bit.ly
The Accelerationist Case for Frontier Pacing
Slow AI is smooth AI, smooth AI is fast AI
000
O'Reilly @oreilly.bsky.social · 22/09/2026
"AI sovereignty doesn’t necessarily imply total control of your AI stack. It holds the promise of having more localized security and privacy, better adherence to local jurisprudence, more dependable service, and more culturally specific outputs." bit.ly/4AoHUx2
bit.ly
AI Sovereignty: Bargaining with Big Tech and the Promise of Full Stack Open Source AI
021
Reposted by O'Reilly
Excel Cookbook @theexcelcookbook.bsky.social · 22/09/2026
On September 30th, I’m running my Generative AI for Excel class for #OReilly. The course includes Copilot, the Claude for Excel add-in, and browser-based tools such as ChatGPT and Claude. Do join me! Register here: learning.oreilly.com/live-events/... @oreilly.bsky.social
learning.oreilly.com
Generative AI for Excel
Using Claude, Copilot, and other AI tools to save time and work more efficiently
111
O'Reilly @oreilly.bsky.social · 22/09/2026
In this episode of Zero to Agent in 30 Minutes, Chester Ismay, Ph.D. built a sports concierge agent to surface the games he should watch. It reads his preferences and current schedules, then sends a weekly summary to his phone. Check it out: bit.ly/3T1xe6S
010
O'Reilly @oreilly.bsky.social · 21/09/2026
"It’s time to explore what post-training has actually accomplished in the frontier models you know and love." This is the third post in a four-part series about post-training by Sharon Zhou, PhD. Check it out: bit.ly/4xBx0RQ
bit.ly
The Post-training Process OpenAI Used for ChatGPT
Walk through the pipeline that made ChatGPT such an improvement over GPT-3
010
O'Reilly @oreilly.bsky.social · 21/09/2026
In his keynote at Ai4 2026, @timoreilly.bsky.social explains why grappling with the bitter lesson is the forge of effective AI corporate strategy, as companies figure out what to embrace and what to let go of. Check it out: bit.ly/3T0DyLT
bit.ly
How to Get from AI-Assisted to AI Native
AI as an Enterprise Operating System, a keynote from Ai4 2026
010
O'Reilly @oreilly.bsky.social · 19/09/2026
OpenAI expanded into software control, scientific reasoning, and financial services this week, and investors committed billions more to AI companies across the stack. This Week in AI host Christina Stathopoulos looked at what those developments mean: bit.ly/4AkrENF
000
O'Reilly @oreilly.bsky.social · 19/09/2026
Week 3 of our Software Architecture cohort took us from logical to physical architecture. Participants explored different architectural styles, how they work, when to use them, and when to avoid them, and more. Sign up for future learning opportunities: bit.ly/4ym4WDQ
bit.ly
Become a Software Architect with Neal Ford and Mark Richards - O'Reilly Media
Learn software architecture directly from top experts with O'Reilly's immersive six-week cohort.
000
O'Reilly @oreilly.bsky.social · 18/09/2026
"Robots are fine operating in the dark, but humans need to see what they’re doing. If everything on the factory floor is dark, and you can’t see anything, and you can’t even find the light switch, that’s where the danger is." #Radar @addyosmani.bsky.social bit.ly/4dodCk6
bit.ly
Software Factories, Light and Dark
The following article originally appeared on Addy Osmani’s blog and is being republished here with the author’s permission.A software factory harnesses
001
O'Reilly @oreilly.bsky.social · 17/09/2026
"Every company describes the landscape from wherever they happen to be standing. But when six vendors do that to the same word, practitioners are left translating between six versions of it before a design conversation can even start." bit.ly/4ybpChh
bit.ly
Navigating the Modern Data Lexicon: A Working Vocabulary for the Semantic Era
The way we talk about data is changing faster than the way we build it. Every quarter a vendor ships a new approach, coins a new term for it, or quietly adopts
000
O'Reilly @oreilly.bsky.social · 17/09/2026
"Organizations continue to improve retrieval over collections that omit some of their most valuable operating knowledge. Better ranking can help people find what was recorded; it can’t recover the expertise that never entered the collection." bit.ly/4dqGfNB
bit.ly
Architecting for the Knowledge You Can't Capture
Tacit knowledge is the hardest requirement in enterprise AI. Here's how a data and knowledge architect designs, and evaluates, for it.
020
O'Reilly @oreilly.bsky.social · 17/09/2026
"Machines can produce results that withstand verification while the understanding needed to explain them remains out of reach. Developing that understanding takes time, access, and collaboration. Whoever controls those conditions gains power. " bit.ly/3Tdqbb3
bit.ly
Beyond Navier-Stokes: Who Controls Scientific Discovery?
What AI’s mathematical breakthroughs mean for human understanding, corporate power, and the future of knowledge work
000
O'Reilly @oreilly.bsky.social · 16/09/2026
"My guest on this past week’s Live with @timoreilly.bsky.social was Emmanuel Ameisen, a researcher on Anthropic’s AI interpretability team. I wanted him to reprise the talk on Anthropic’s research into what is going on inside an LLM while it is processing and then go deeper." #Radar bit.ly/4rjajRd
bit.ly
What AI Can Teach Us About Being Human
My guest on this past week’s Live with Tim O’Reilly was Emmanuel Ameisen, a researcher on Anthropic’s AI interpretability team. I’d heard him give a short talk
020
O'Reilly @oreilly.bsky.social · 16/09/2026
If cybersecurity is part of your work, please answer these 11 short questions about the risks you’re seeing, the policies and resources guiding your organization, and how AI supports your work. It should take less than 10 minutes. Thanks in advance! bit.ly/3UPIS5f
000
O'Reilly @oreilly.bsky.social · 16/09/2026
This article represents a reference architecture for LLM-powered enterprise analytics agents that coordinate purpose-built, heterogeneous data stores through intelligent orchestration while preserving security, performance, and auditability. bit.ly/4AxYR8z
bit.ly
Enterprise Analytics Beyond Dashboards: Intelligent Data Orchestration with LLMs
How LLMs enable reasoning across heterogeneous enterprise data without centralized data consolidation
010
O'Reilly @oreilly.bsky.social · 16/09/2026
On 9/24, we’re hosting a live webinar showing O’Reilly Expert Intelligence in action. You’ll explore three AI workflows that your teams can use right now to evaluate an architecture trade-off, pressure-test a security design, or build a learning strategy bit.ly/3UUbc6v
000
Reposted by O'Reilly
Andrew Stellman 👾 @andrewstellman.bsky.social · 14/09/2026
From my @oreilly.bsky.social Radar article, “Why Doesn’t Anyone Teach Developers About Context Management?” www.oreilly.com/radar/why-do...
011
Reposted by O'Reilly
Andrew Stellman 👾 @andrewstellman.bsky.social · 14/09/2026
From my @oreilly.bsky.social Radar article, “Your AI Agent Already Forgot Half of What You Told It” www.oreilly.com/radar/your-a...
011
Reposted by O'Reilly
Andrew Stellman 👾 @andrewstellman.bsky.social · 15/09/2026
From my @oreilly.bsky.social Radar article, “So Long and Thanks for All the Context” www.oreilly.com/radar/so-lon...
011
O'Reilly @oreilly.bsky.social · 15/09/2026
On this week’s episode of Zero to Agent in 30 Minutes, Sajal Sharma showed how to set up that shared workspace yourself so that a task added on one tool shows up for all the others: bit.ly/4h8HnXc
010
O'Reilly @oreilly.bsky.social · 15/09/2026
We’re conducting a survey to better understand your concerns and the steps you’re taking to address them. If cybersecurity is part of your work in any way, please answer these 11 short questions. It should take less than 10 minutes. bit.ly/3UPIS5f
bit.ly
Security & AI Practitioner Survey
000