AI Plan Mode Is Dead. What Developers Are Doing Instead | LWIT

Be part of the show: https://btb-listener-line.fly.dev/ Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9Being right doesn't always mean you've won. As a software engineer, knowing how to handle technical disagreements, push back on decisions, and navigate conflict at work is just as important as writing good code.In this episode of Beyond the Build, we discuss how software engineers can disagree effectively without damaging relationships, losing trust, or hurting their careers.From heated code reviews and architecture debates to challenging decisions made by senior engineers and managers, we explore why technical disagreements often become personal and how to handle them better.We cover:Why technical disagreements between engineers often become personalHow to decide which engineering decisions are worth fighting forHow to push back on your manager or senior engineers respectfullyHow to communicate disagreements using evidence, tradeoffs, and contextWhat it really means to "disagree and commit"How to handle being overruled, even when you know you're rightWhy maintaining trust and strong working relationships matters for your engineering careerWhether you're a mid-level engineer, senior software engineer, tech lead, or engineering manager, learning to navigate disagreements is an essential part of growing your career.The goal isn't to win every technical argument. It's to make better engineering decisions while building relationships that last.Subscribe to Beyond the Build for conversations about software engineering, career growth, AI, and life beyond writing code.#SoftwareEngineering #CareerGrowth #EngineeringLeadershipConnect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)Send us a message

Be part of the show: https://btb-listener-line.fly.dev/ Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9AI has changed how software engineers write, review, and ship code, but is it actually making developers more productive?In this episode of Beyond the Build, we break down Anthropic's AI-assisted code review process, where AI agents review AI-generated code and human approvals depend on the risk involved. We explore what this means for the future of code reviews, software engineering workflows, and developer productivity.We also discuss why some engineers are getting unlimited AI budgets while others face restrictions, the paradox of AI making developers busier instead of reducing their workload, and why hungry junior engineers might have an advantage over experienced developers in the AI era.Plus, we cover major cybersecurity incidents, including developer tool supply chain attacks, compromised DevOps environments, exposed credentials, and growing concerns around AI and data privacy.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)00:00 - Trailer 01:48 - Welcome to Last Week in Tech 02:14 - How the Claude Code Team Reviews Code 04:45 - Which Changes Still Need Human Approval? 09:11 - The OpenClaw Creator’s Reported $10M Token Budget 11:10 - Cisco’s Ambitious AI Code Rewrite 13:18 - Unlimited AI Budgets vs. Token Restrictions 15:00 - AI Promised Less Work. Why Are We Busier? 18:58 - Why Hunger Matters More Than Tenure 21:35 - Business Impact Over Busywork 23:28 - Build a Prototype Instead of Debating for Weeks 26:06 - Staying Curious as an Experienced Engineer 27:38 - Learning AI by Actually Building With It 30:09 - Discussing the Reported Binance Hack 34:18 - Engineers as Targets for Social Engineering 38:35 - The Reported Claude Code Extension Backdoor 40:27 - Why Security Needs More Than Individual Caution 43:10 - Applebee’s Database Password Exposure 45:11 - Smart Devices & the End of Security by Obscurity 48:07 - Google Personal Intelligence & Data Privacy 51:16 - Why the Hosts Changed Their Minds About Data Sharing 53:39 - Outro & Listener SubmissionsSend us a message

DescriptionBe part of the show: https://btb-listener-line.fly.dev/ Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9October 2026 has been a rough month for cybersecurity. From critical PHP vulnerabilities and AI supply chain attacks to AI agents autonomously accessing bank accounts, the security landscape is changing rapidly.In this episode of Beyond the Build, we break down "Black October," major security vulnerabilities affecting PHP, LightLLM, and OpenCode, OpenAI's AI agents disabling security monitoring, and why banks are increasingly concerned about autonomous AI agents.We also explore 1Password for AI Agents, security concerns surrounding Chinese AI models, and how AI is reshaping the future of software engineering.Are AI agents creating more problems than they're solving? And what does the future look like for software engineers?Join us as we unpack these stories and more.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)00:00 - Trailer01:44 - Welcome to Last Week in Tech02:04 - “Black October”: Critical PHP Vulnerabilities07:07 - Why Old Software Becomes a Security Liability09:31 - Bank of America’s AI Security Cleanup11:39 - When AI Agents Disable Their Own Monitoring16:58 - Code Is Cheap: What Software Agencies Should Sell20:53 - AI Agents Are Logging Into Bank Accounts23:36 - Action Control vs. Access Control25:00 - 1Password for AI Agents28:41 - The Certificate Authority’s Weak-Key Disaster32:52 - A Leaked Key and a Supply Chain Attack35:01 - OpenCode, Stolen API Keys & Unexpected AI Bills37:13 - Can AI Models Change Code Security Based on Who You Are?43:24 - A Plugin That Tests Your Understanding Before You Push46:33 - What Linear Gets Right About Product Design50:50 - Making Your Smart TV Dumb Again55:14 - Nigeria’s DevOps Community & Finding Your Network57:01 - Outro & How to Join the ShowSend us a message

Be part of the show: https://btb-listener-line.fly.dev/ Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9An OpenAI engineer was arrested for allegedly spying on executive meetings, GitHub is rebuilding its infrastructure to handle the explosion of AI-generated code, and a Nigerian developer has built a GTA-inspired game based on life in Lagos.In this episode of Beyond the Build (Last Week in Tech), we break down the OpenAI spying scandal, why GitHub and Anthropic are rethinking Git and source control for AI coding agents, and how AI is changing software engineering, code reviews, and the skills developers need to stay relevant.We also explore Lagos Life, a Nigerian-built simulation game, the growing security risks of AI-generated code, and why companies like Clay are rethinking how engineers use AI for writing and communication.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)00:00 - Trailer01:54 - Welcome to Last Week in Tech02:24 - The Alleged OpenAI Office Bugging09:01 - Lagos Life: Building a Virtual Lagos15:29 - Why GitHub Needs to Rebuild for AI Scale17:22 - How Git Commits, Pushes & Conflicts Work23:50 - Separating Storage from Compute25:30 - Why Anthropic Built Its Own Source Control28:37 - Should We Stop Reviewing AI-Generated Code?30:25 - Engineering Judgment: Knowing What Good Looks Like35:10 - Better Tests, Not Just More Tests36:07 - AI Code That Works—but Is It Secure?39:22 - Designing Security Into AI Projects41:12 - Why Forward-Deployed Engineers Are Hard to Find43:20 - Writing With AI Without Outsourcing Your Thinking47:28 - Turning Voice Notes Into Better Writing48:42 - How Unchecked AI Replies Destroy Trust50:15 - Longer Documents Aren’t Better Documents53:27 - Interactive Artifacts Instead of Long Documents54:10 - Outro & Listener IntrosSend us a message

Be part of the show: https://btb-listener-line.fly.dev/ Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9The US is tightening immigration policies, and Big Tech is feeling the impact. With companies like Microsoft pausing green card sponsorships and proposed changes to OPT for international students, what does this mean for the future of tech jobs in America?In this episode of Beyond the Build, we discuss how immigration restrictions could affect skilled workers, international students, and the tech industry, and whether these policies could push more talent and jobs overseas.We also explore growing concerns around AI sovereignty and data privacy, Anthropic's handling of private Claude conversations, Claude's integration with Google Workspace, and Microsoft and Meta's massive spending on AI coding tools.Finally, we discuss the future of AI interfaces, why understanding code still matters in the age of AI, and some interesting open-source projects worth checking out.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)Send us a message

Be part of the show: https://btb-listener-line.fly.dev/ Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9In this episode of Beyond the Build, we talk about how personal AI agents are starting to change the way we interact with technology, including research showing that some agents may recommend more expensive options based on what they infer about a user.We also get into the privacy tradeoffs of personal AI, OpenAI Dots vs. Meta Muse, whether Plan Mode still makes sense for coding agents, why taste still matters when building with AI, browsers sending gRPC requests directly, and what it actually takes to identify and push high-leverage engineering work inside an organization.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)Send us a message

Be part of the show: https://btb-listener-line.fly.dev/Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9 This week on Beyond the Build, we break down some of the biggest stories in software engineering, cybersecurity, AI, and tech.We discuss Jev, a new decision-focused AI model, the shifting AI talent pipeline between China and the US, AI hacking incidents, Kimi coming to AWS Bedrock, the reported FBI breach, North Korean fake developer interviews, Polymarket fraud, Samsung smart fridge failures, and the debate around whether MCP is still necessary.We also talk about senior engineer communication, how coding agents edit files, and the growing problem with AI-generated writing.If you’re a software engineer or tech professional trying to keep up with what’s changing across the industry, this episode is for you.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)00:00 Trailer 01:36 Intro — Last Week in Tech 01:50 Prediction Markets, Fraud & Polymarket 06:29 Kimi AI Comes to AWS 10:41 The AI Slowdown & Management Consultants 15:05 Jev: The AI Model Built for Fast Decisions 17:47 Slop Mop & The Problem With AI Writing 21:44 The Changing Landscape of Chinese AI Talent 26:56 AI Models Are Hacking Computers 30:27 Is MCP Still Necessary? 36:45 ShinyHunters Hack the FBI 39:46 When a Software Update Breaks Your Fridge 42:43 North Korean IT Workers & Deepfake Job Interviews 45:40 Rapid Fire: The Senior Engineer Death Spiral 48:03 Managing Capacity, Delegation & Engineering Work 50:13 How Coding Agents Edit Your Files 51:23 Should AI Be Writing Your Documents? 55:49 Wrap Up 56:17 A New Way to Get Your Questions on the ShowSend us a message

Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9In this episode of Beyond the Build, we break down Anthropic’s latest AI misuse report and look at how bad actors are already using AI for scams, surveillance, cyber operations, influence campaigns, telecom data scraping, and other real-world attacks.We also discuss the growing AI arms race between companies like Anthropic, OpenAI, and other major labs. AI companies are warning about models becoming harder to supervise while simultaneously investing billions to build more capable systems. Can any company realistically slow down if everyone else keeps racing ahead?We also get into a new security problem emerging around AI coding agents and plugins. As developers give tools like Claude Code, Codex, GitHub Copilot, and Gemini CLI more access to repositories, terminals, APIs, and credentials, supply-chain attacks become significantly more dangerous.Then we debate what code review should look like in the age of AI. If AI can generate code faster than humans can read it, should every line still be reviewed? Or does code review become less about catching bugs and more about making sure engineers still understand the systems they are building?We also cover AWS infrastructure failures during geopolitical conflict, Windows 11 updates breaking hardware, OpenAI’s IPO plans, digital ownership, and what happens when the software and infrastructure we depend on become increasingly automated.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)Send us a message

Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9In this episode of Beyond The Build, we talk about the growing wave of AI safety warnings coming from researchers at companies like OpenAI, Anthropic, and Google DeepMind, and whether those concerns should actually change how seriously we think about the risks of increasingly capable AI systems.We also get into the security problems that come with AI agents having access to production secrets, private data, credentials, and external systems, along with recent controversies around AI research, watermarking, browser privacy, and the trust we place in the tools we use every day.Then we bring it back to software engineering. If AI can already investigate alerts, write code, open pull requests, and automate more of the development lifecycle, what is actually left for engineers? We discuss why coding is only one part of the job, why judgment, system design, debugging, operations, and accountability still matter, and why you cannot fully delegate a system you do not understand.Along the way, we also touch on AI-assisted research, security vulnerabilities, prompting, brownfield vs. greenfield development, Postgres at scale, expired credit card security, and a few other things happening in tech this week.Connect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)Send us a message

Ask us a question or suggest an Episode: https://forms.gle/8tEg2CKTNNWteSgt9AI is changing software security faster than most engineering teams are prepared for.In this episode of Beyond the Build, we break down how AI agents are starting to discover and exploit vulnerabilities, why the window between a CVE being disclosed and actively exploited is shrinking, and what that means for developers, security teams, and companies shipping software today.We also discuss new findings around OpenAI’s AI agent swarms, concerns around observability and model behavior, major data breaches involving identity verification providers, and why digital privacy is becoming even harder to protect.Beyond security, we get into how AI is reshaping software engineering itself, including the impact on frontend developers, Meta’s push toward smaller engineering teams, local LLMs running directly in the browser with WebGPU, and why human error can still take down even the most resilient cloud infrastructure.Topics covered:• AI agents and autonomous hacking• OpenAI swarm security concerns• CVEs and faster vulnerability exploitation• Software supply chain and cybersecurity risks• Data breaches and identity verification• Privacy and age verification• The future of frontend engineering• AI-driven software development• Meta engineering layoffs and productivity• WebLLM and local AI inference• Google Cloud outages and infrastructure resilienceConnect with Ope - https://www.linkedin.com/in/osunkoyaope/Connect with Uma: Instagram: (https://www.instagram.com/umacodes) Tiktok: (https://www.tiktok.com/@umacodes) Twitter: (https://twitter.com/umacodes) LinkedIn: (https://www.linkedin.com/in/umaabu/)Follow us on Social Media Instagram: (https://www.instagram.com/beyondthebuildpodcast) TikTok: (https://www.tiktok.com/@beyondthebuildpodcast)Send us a message