Topic
Engineering Leadership - Page 6
AI decisions through the lens of teams and execution. Curated tldw.news briefings about engineering leadership, with practical engineering takeaways from long-form AI and developer-tool videos.
472
breakdowns
Page 6 of 48
AI EngineerYour Agent Can Lie While Monitoring Stays Green. Build Eval Gates.
Traditional monitoring misses agent failures that look successful. This workshop shows how golden datasets, human annotation, and CI eval gates catch them.
David OndrejOpenCode breach: BYOK AI keys are the new attack surface
OpenCode's breach exposed the BYOK trap: stolen API keys fueled a distillation attack. AI keys now need production-grade governance.
AI EngineerOAuth won't work for autonomous AI agents. Here's what will.
OAuth was built for deterministic software, not agents that improvise. Runtime authorization per tool call, with intent context and budgets, is the emerging…
Y CombinatorAI Safety: Hysteria Won't Help, Formal Verification Will
Formal verification powered by AI can make software unhackable. The real AI safety threat is misuse, not rogue intelligence. A YC Paper Club panel cuts…
AI EngineerThe AI Cost Crisis: Measure, Right-Size, and Stop the Bleeding
Measure token spend per team before touching model choice. A workshop reveals how to cut inference costs 10x with operational discipline.
Latent SpaceOpenAI Shipped Everything. Your Team Still Needs Trust and Portability.
OpenAI shipped Dots, 6.1 Soul, and a decisions API. The panel of experienced builders says the models are impressive, but product execution is degrading. The…
IBM TechnologyDecision models and agent teams: the coordination tax is real
Decision models explode as a category; agent team studies reveal a coordination tax that makes more agents rarely worth the cost.
David OndrejWhy Supabase CTO says open source is now a security strategy
Why Supabase CTO says agents force open source as a security strategy and dashboards become optional. The tagline that changed everything.
Theo - t3․ggAnthropic built a custom VCS because Git can't keep up with agents
Anthropic rebuilt source control from scratch because Git's offline-first design broke under 30,000 daily agent merges. Scion's centralized, fetch-on-demand…
Hussein NasserIf AI writes your tests, you can't debug the failures
Hussein Naser argues AI and ORMs hide what engineers must understand. His Aurora Postgres story shows why fundamentals still decide production outcomes.
Get TL;DW
Too Long; Didn't Watch.
A concise breakdowns of the AI and devtools videos that actually matter for engineering leaders.
Free. Weekly. No hype.