Topic
AI Workflows - Page 56
How engineering teams turn AI tools into repeatable work. Curated tldw.news briefings about ai workflows, with practical engineering takeaways from long-form AI and developer-tool videos.
583
breakdowns
Page 56 of 59
Cole MedinYour AI Model Is Only 10% of the System
Google’s agentic guide: harness (rules, workflows, evals) is 90% of the system, model just 10%. Vibe coding burns tokens; engineered harnesses flip economics.
The Pragmatic EngineerAI Didn't Kill Coding Interviews—It Exposed What Actually Matters
NeetCode says coding interviews persist because they measure thinking, not syntax—the real risk is engineers losing the ability to reason without AI.
AI JasonMerging, Not Writing, Is the New Bottleneck for AI Coding
When AI coding agents multiply, the real bottleneck shifts to verifying and merging changes. Crabbox runs isolated cloud sandboxes to prevent test collisions.
IBM TechnologySocial Engineering Won’t End; It’s Shifting to Your Agents
Social engineering won’t stop; it’ll target AI agents instead of people. The threat surface is moving, and your IAM isn't ready.
InfoQStop Prompt Hacking: Architect for Deterministic AI Agents
Prompt engineering won’t make AI agents reliable. Build a skill store: codify successful outputs as deterministic code to skip reasoning for known problems.
InfoQDurable Agents Need Workflow Engines, Not Whole-Loop Sandboxes
Separating agent reasoning from tool execution in a durable workflow engine prevents state loss, eliminates idle waits, and provides an audit trail.
AWS DevelopersThe System Prompt Is Your Agent's Real Strategy, Not the Model
Tools turn an LLM into an agent, but the system prompt is the real strategy. MCP aims to turn internal APIs into agent capabilities without custom code.
The Pragmatic EngineerSlow Down Your AI Coding Before It Breaks Your Engineering Culture
Meta’s AI-written, AI-reviewed code caused a security disaster. The lesson: without human oversight, AI coding tools destroy trust and reliability.
InfoQCommunity and Maturity Model, Not Tools, Drove Meta’s AI Gains
Meta’s team tripled code coverage with AI using a self‑assessment maturity model and grassroots community—but the speed exposed a looming code‑review crisis.
Machine Learning Street TalkThe Real AlphaFold Lesson: Kill Your Darlings, Not Just Scale
AlphaFold 2's 30-point leap came from ruthless ablation, not SE(3) equivariance. The 100x efficiency gain is a wake-up call for scale-obsessed teams.
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.