https://bsky.app/profile/vfarcic.bsky.socialhttps://bsky.app/profile/vfarcic.bsky.social/post/3myavvh36pr25Keep your AI agents local, rent the overflow. I tested running agents on cloud VMs without leaving Claude Code — here's what worked, what didn't, and why the tool you work in matters. 🧵 https://youtu.be/s-XCTNf06XQ19 Oct 2026 20:00 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3myavvh36pr25https://bsky.app/profile/vfarcic.bsky.social/post/3mxovjghyqr2hPen testing happens once a year (if at all), costs a fortune, and the report arrives after you've shipped 12 more releases. What if an AI did it on every release for pennies? 👇 https://youtu.be/dJv_f4w8ZAA12 Oct 2026 16:05 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mxovjghyqr2hhttps://bsky.app/profile/vfarcic.bsky.social/post/3mx5c7axymk26Heroku shipped your entire platform team's roadmap in 2011. Finished. Priced. Documented. You can still sign up tonight in under a minute. Your platform team is going to build it anyway. 🧵 New video: youtu.be/3CLrqv6ZtW8 #Heroku #DevOps #PlatformEngineering https://youtu.be/3CLrqv6ZtW805 Oct 2026 16:04 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mx5c7axymk26https://bsky.app/profile/vfarcic.bsky.social/post/3mwkdjf5mik2sAutoscaling LLM inference isn't reacting to traffic; it's forecasting it. Your replica takes 10+ min to arrive. By then, the spike is history. https://youtu.be/wwrPwU-JCMw28 Sep 2026 03:07 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mwkdjf5mik2shttps://bsky.app/profile/vfarcic.bsky.social/post/3mw23qutnqc2tStack Overflow taught a generation to copy, paste, and take the credit. Now it's fading. The story of how it rose, why it worked, and what killed it. New video 👇 youtu.be/muT3BZQmLhI #StackOverflow #AIcoding #techhistory https://youtu.be/muT3BZQmLhI21 Sep 2026 16:06 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mw23qutnqc2thttps://bsky.app/profile/vfarcic.bsky.social/post/3mviorgnu7a2hInference is a memory management problem, not a compute one. Your GPU almost never runs out of arithmetic first. It runs out of room to hold conversations. And your engine already tells you the exact ceiling at startup — before a single request arrives. 🧵 https://youtu.be/g_5g1hBmAzA14 Sep 2026 17:58 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mviorgnu7a2hhttps://bsky.app/profile/vfarcic.bsky.social/post/3muwv6acrss24Jenkins never said no. Not once. That's why it's still running in your company right now, and why nobody can switch it off. The nightmare isn't that it died. It's that it didn't. 🧵🕯️ #DevOps #Jenkins #ContinuousIntegration youtu.be/LbxQqAuQ4Xk https://youtu.be/LbxQqAuQ4Xk07 Sep 2026 16:05 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3muwv6acrss24https://bsky.app/profile/vfarcic.bsky.social/post/3mufburfk4r2eContinuous batching. Paged attention. Prefix caching. Speculative decoding. 12 inference ideas, a couple of minutes each, one pass. 🧵👇 https://youtu.be/MVo3P-D7eSc31 Aug 2026 16:04 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mufburfk4r2ehttps://bsky.app/profile/vfarcic.bsky.social/post/3mttpgk3g7b2gWhat do CFEngine, Puppet, Chef, Ansible, Terraform & Crossplane all have in common? Same job. Different name. Five arguments. Five generations certain they were inventing something new. New video — go watch. 🏰 https://youtu.be/TF5iJbAb6Xc24 Aug 2026 16:19 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mttpgk3g7b2ghttps://bsky.app/profile/vfarcic.bsky.social/post/3mtjpoxrb222nGoing live... https://youtube.com/live/qNcHJ_ktyz020 Aug 2026 16:57 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mtjpoxrb222nhttps://bsky.app/profile/vfarcic.bsky.social/post/3mtebvpvrjs2bStrongly recommend checking out the Observability in the AI-Native Era book (packt.link/aYRZy). When it comes to observability, Hilliary, Andreas, and Robert know what they're talking about. https://packt.link/aYRZy18 Aug 2026 13:07 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mtebvpvrjs2bhttps://bsky.app/profile/vfarcic.bsky.social/post/3mtcdihuife2lA bad test doesn't fail. It passes. And now you're sure about something that isn't true. This is the hidden danger of AI-generated tests that will bite you. 🧵 https://youtu.be/6yp-JrbZYYg17 Aug 2026 18:30 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mtcdihuife2lhttps://bsky.app/profile/vfarcic.bsky.social/post/3msy4mlrngk2aGoing live... https://youtube.com/live/n3XvYOY5TmA13 Aug 2026 17:00 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3msy4mlrngk2ahttps://bsky.app/profile/vfarcic.bsky.social/post/3msqjqvqzi425Docker won the internet. Every cloud, every pipeline, every deployment runs on its idea. But the company that built it? A ghost. The scariest stories aren't about failing; they're about winning so completely your victory floats away without you. 🐳 https://youtu.be/kmLztKueTcI10 Aug 2026 16:34 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3msqjqvqzi425https://bsky.app/profile/vfarcic.bsky.social/post/3msgj3345g22tGoing live... https://youtube.com/live/XC5A4upgIgk06 Aug 2026 16:55 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3msgj3345g22thttps://bsky.app/profile/vfarcic.bsky.social/post/3ms6uwgal6g25AI agents can do your ops work. But a non-deterministic swarm with full cloud credentials and no guardrails? That's a loaded gun pointed at prod. Here's how to put it on a leash 🧵👇 https://youtu.be/G6J2Z2fhlUo03 Aug 2026 16:06 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3ms6uwgal6g25https://bsky.app/profile/vfarcic.bsky.social/post/3mruvsfvlvs2rGoing live https://youtube.com/live/7q0CgMe0lTA!30 Jul 2026 16:55 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mruvsfvlvs2rhttps://bsky.app/profile/vfarcic.bsky.social/post/3mrnbepdz3q2iThere's no patch for prompt injection. It's not a bug—it's how the models work. The real question: when it happens, how much damage can it do? New video on sandboxing AI agents so you can walk away and still sleep at night. 🔒 https://youtu.be/tWb7v7Nq80827 Jul 2026 16:01 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mrnbepdz3q2ihttps://bsky.app/profile/vfarcic.bsky.social/post/3mrfrf5p75o22What if your tests read like a spec doc AND never needed babysitting? DevAssure lets you write plain-English YAML, commit it to your repo, and an AI agent clicks through your app like a real user. Zero selectors. Zero page objects. https://youtu.be/bNJoeSXUdQg24 Jul 2026 16:26 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mrfrf5p75o22https://bsky.app/profile/vfarcic.bsky.social/post/3mrdjcxf4b22aGoing live with AMA (after a few weeks break)! Ask anything. https://youtube.com/live/OBG4MJDVJHA23 Jul 2026 18:56 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mrdjcxf4b22ahttps://bsky.app/profile/vfarcic.bsky.social/post/3mr3oarjazw2hThe hardest part of fleet-scale inference isn't the model — it's the matchmaking. Which model runs on which GPU, across which cluster? Modelplane's scheduler handles all of it automatically. New video out now 👇 #AI #DevOps #Kubernetes https://youtu.be/Mc0BM63Pv0020 Jul 2026 16:03 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mr3oarjazw2hhttps://bsky.app/profile/vfarcic.bsky.social/post/3mqk2w5phtg2nI review entire AI-built features without reading a single line of code. My agents record their own tests as video clips. I watch a short reel, confirm it works, hit merge. Two gates. Total autonomy in between. 🧵 https://youtu.be/03VwVUadsRM13 Jul 2026 16:02 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mqk2w5phtg2nhttps://bsky.app/profile/vfarcic.bsky.social/post/3mpyonj6t422kMy last task before bed isn't wrapping up. It's kicking off the NEXT round of work for my AI agents. They build while I sleep. I ship while they work. The cycle never stops. 🌙➡️☀️ youtu.be/DxZHsMu3NU0 #AIAgents #DevAutomation #AgentDeck https://youtu.be/DxZHsMu3NU006 Jul 2026 18:07 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mpyonj6t422khttps://bsky.app/profile/vfarcic.bsky.social/post/3mpgucuqtgf2tThe AI agent server stack that actually works: ✅ Cheap PC (~$900, one-time) ✅ Ubuntu Server ✅ Terminal agents (Claude Code, Codex) ✅ Tailscale + tmux ✅ Devbox + vals Full video breakdown 🎥 https://youtu.be/tCEhU9bQ-XY29 Jun 2026 16:01 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mpgucuqtgf2thttps://bsky.app/profile/vfarcic.bsky.social/post/3movb5jbfy72kA dummy is a dummy, no matter whether they're using AI or not. AI agents are amplifiers. If you're good at your job, they make you better. If you're not, they help you cause a shitstorm at scale in minutes. https://youtu.be/_j4epp_MqF422 Jun 2026 16:03 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3movb5jbfy72khttps://bsky.app/profile/vfarcic.bsky.social/post/3modnrduetp2pYou're not a coder anymore. You're the CTO of a company where everyone else is a model. Your job: write tight PRDs, set direction, approve the big calls. The agents handle the rest 👀 https://youtu.be/ZIWWDDu02Ik15 Jun 2026 16:00 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3modnrduetp2phttps://bsky.app/profile/vfarcic.bsky.social/post/3mnzscbtdls2yGoing live... https://youtube.com/live/ru3iXH-TIsI11 Jun 2026 17:55 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mnzscbtdls2yhttps://bsky.app/profile/vfarcic.bsky.social/post/3mns2ofa7ox23The fix for broken code review isn't hiring more reviewers. It's flipping the ORDER. AI first → humans second. By the time a person opens the PR, the noise is already gone. Only the real judgment calls remain. Full breakdown in my latest video: https://youtu.be/KyodvaYemxM08 Jun 2026 16:04 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mns2ofa7ox23https://bsky.app/profile/vfarcic.bsky.social/post/3mni6znzqks27Going live... https://youtube.com/live/vpNWz8mADrQ04 Jun 2026 17:55 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mni6znzqks27https://bsky.app/profile/vfarcic.bsky.social/post/3mnahgnwlqf27I run multiple AI agents with different models — Opus as orchestrator, GPT as coder, Kimi as reviewer. OpenRouter makes this effortless. One gateway, full flexibility, real cost visibility. Here's the setup 👇 https://youtu.be/YKCJwk6xLwA01 Jun 2026 16:04 +0000at://did:plc:flpc3odxtjtxq4ph4ba7tdl5/app.bsky.feed.post/3mnahgnwlqf27