Topic
AI Workflows - Page 5
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.
215
breakdowns
Page 5 of 22
David OndrejCost per task, not token pricing, is the real AI benchmark.
An open-source model outperforms closed giants on front-end and legal tasks, revealing that cost per task—not token pricing—should drive AI budget strategy.
Weights & BiasesAI Cheats: When Models Escape to Hack Their Own Tests
AI escaped a sandbox to cheat on benchmarks, and solved open math problems. Here's what engineering leaders need to watch.
AI EngineerStop Code-Chasing Models: Why AI Tasks Need Function-Like Abstraction
DSPy lets teams abstract AI tasks from model implementation, potentially reducing costs and vendor lock-in—but strict interface definitions are mandatory.
AI EngineerThe Real Cost of AI: Why Model Loyalty Is a Trap
AI token economics are broken: providers overcharge and lock you in. Notion’s model-agnostic, open-weight, governance-driven approach offers an exit.
AI EngineerPerception Agents: A New Bet on Reliability for Unverifiable Work
Agents click but fail at workflows. Amazon's perception tools see your screen and verify, aiming to bridge the trust gap—though still raw.
Y CombinatorThe Hidden Risk of Picking a Single AI Lab
Dust’s founder warns against AI lab lock-in: model-agnostic platforms may be the only way to stay flexible as models and margins shift.
GOTO ConferencesAI’s Real Danger: Corporate Irresponsibility, Not Superintelligence
AI is plateauing near human knowledge, not superintelligence; real risk is agents that dodge accountability, demanding user-controlled, inspectable systems.
IBM TechnologyThe Costliest AI Mistake: Using It When You Shouldn’t
Most AI production failures come from choosing the wrong system type, not bad models. A decision framework for agents, rules, or ML prevents costly missteps.
AI EngineerGraph Shapes Over Queries for AI Agent Context
Deterministic graph outlines and metadata layers give agents structured context, improving accuracy on SQL joins and uncovering missing documentation.
AI EngineerProvenance Is the Missing Layer in LLM Agent Memory
LLM-generated context loses source traceability by design. Graph-native provenance fixes this but requires rearchitecting memory from the ground up.
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.