@yurekilab-en.bsky.socialAudited the tests my coding agent wrote last month: 19 of 60 mocked the very function they claimed to cover. Green, fast, and proving nothing. New rule: mock the network, the clock, and the filesystem. Nothing else. #claudecode #testing #aiengineering #buildinpublic
@levelbrook.bsky.socialThe number was green, so the agent stayed quiet. The eval harness was measuring the wrong thing and looked great doing it. #LLM #AIEngineering
@remotejobs2504.bsky.social💰 $400K/YEAR | FORWARD DEPLOYED ENGINEER 🚀💻
🌍 Remote / Travel-required
Forward Deployed Engineer?
Use your AI and ML skills to help train next-generation AI.
🚀 LLM Systems • ML Infrastructure • RAG • AI Automation
@yurekilab-en.bsky.socialCounted the TODOs my coding agent left in two weeks: 31. Each was a decision it dodged: an edge case, a name, an error path. New rule: a TODO needs a failing test or an open issue. Otherwise finish it or delete it. Down to 4. #claudecode #ai #aiengineering #buildinpublic
@ayeshappdev.bsky.socialLife after graduating as a Software Engineer.
Graduation ended. The real journey started.
I’m just building, learning and figuring it out one step at a time.
#SoftwareEngineer #AIEngineering #MobileAppDeveloper #LifeAfterGraduation #ayeshappdev
@yurekilab-en.bsky.socialLet my coding agent propose edits to its own rules file this month. 31 proposals filed. I merged 4. The other 27 would have excused its last mistake, not prevented the next one. An agent grading its own homework mostly asks for a lower bar. #claudecode #ai #aiengineering #buildinpublic
@myexamcloud.bsky.socialThe Agentic AI domination continues…
Cloud Architect → AI Architect → Agentic AI Architect → Enterprise Agentic AI Architect.
The shift isn’t just from servers to AI.
The architecture is getting smarter.
#AgenticAI #AIAgents #AIArchitecture #EnterpriseAI #GenerativeAI #AIEngineering
@lucaminudel.bsky.social=> www.
smharter.ai/blog/2026/09/23/maximising-ai-benefits-in-software-engineering-in-depth-strategic-overview/
#AIEngineering #SoftwareEngineering #AIAugmentedDevelopment #GenAI
_____________________________________
Want to compare notes? DM me
Want help? Get in touch @ smharter.ai
AWS Lambda MicroVMs now let you run self-hosted AI agent sandboxes securely. This solves the problem of code contamination across sessions and tenant data exposure. Perfect for agents that interact with internal systems, databases, or file systems. #AIEngineering #AWS #AgentSecurity
@yurekilab-en.bsky.socialMy coding agent assumes every list fits on one page. Grepped my repo for API calls fetching lists: 9 total, 6 ignored the next-page cursor. All passed in dev with 12 records. One broke at 101. New rule: handle pagination, or say why you didn't. #claudecode #ai #aiengineering #buildinpublic
@leanpub.bsky.socialFrom the Leanpub Blog: Leanpub Book LAUNCH 🚀 The Code Is Lying: Engineering with Coding Agents by Alen Joy
#books #leanpublishing #selfpublishing #CodingAgents #AIEngineering #AgenticAI
@leanpub.bsky.socialNEW! Leanpub Book LAUNCH 🚀 The Code Is Lying: Engineering with Coding Agents by Alen Joy
#books #leanpublishing #selfpublishing #CodingAgents #AIEngineering #AgenticAI #SoftwareArchitecture #CodeReview
@ipolyzos.comAlibaba’s OpenCodeReview uses an interesting pattern: deterministic workflows for predictable tasks, LLMs where reasoning adds value.
Don’t make the entire system probabilistic just because one part benefits from AI.
@amar67.bsky.socialAI is more than a field I’m learning.
I’m exploring what happens when AI meets:
→ Finance
→ Biology
→ Physics
Building my AI engineering foundation now.
The goal isn’t just to build AI.
It’s to use AI to discover.
@amar67.bsky.socialI’m building my way into AI Engineering. 🤖
FastAPI, NumPy & Pandas are getting stronger.
Next target: ML + Deep Learning.
This is just the beginning. 🚀
#AI #MachineLearning #Python #AIEngineering
@loopandretry.bsky.socialSplit-brain: when multi-agent memory consensus quietly fails
In distributed systems, split-brain is what happens when a partition convinces two halves of a cluster that each is…
https://loopandretry.github.io/posts/multi-agent-memory-split-brain/?ref=bluesky
@yurekilab-en.bsky.socialGrepped my repo for bare "except: pass". Found 14. All from my coding agent. Tests passed because failures never surfaced. New rule: every catch block re-raises or logs with context. No silent swallows. Three tests went red within a day. Good. #claudecode #ai #aiengineering #buildinpublic
@aiengineeringsu.bsky.socialWas passiert, wenn Vibe Coding mehr Fragen als Antworten liefert? đź‘€
Wo liegen die Grenzen – und wie verändert sich die Rolle von Software-Engineers?
👉 Erfahre mehr im Blogartikel: https://ai-engineering-summit.de/blog/
@groxio.bsky.socialThe most dangerous AI mistake is not ugly code.
It is clean code with the wrong public promise.
Review the exported API before the helpers.
grox.io/blog/49-reviewing-the-ai-s-work-boundaries-crc-and-the-requirement-it-missed
@whiteduck-gmbh.bsky.socialDanke an die Community für den großartigen Austausch! 🤝
#MicrosoftAI #Foundry #Copilot #GitHub #AIEngineering #Lingen
