Topic
AI Workflows
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.
376
breakdowns
Page 1 of 38
Machine Learning Street TalkEnterprise voice agents fail. Here's the fix most teams miss.
Speech recognition is not solved. Mistral's research lead breaks down why enterprise voice agents fail at scale and why customization, not generalization, is…
AWS DevelopersContext Engineering: The Real Lever for Agent Cost and Accuracy
Context engineering—compression, externalization, selective retrieval, and sub-agent isolation—can slash token costs and improve accuracy. But is one…
AI EngineerYour AI agent harness is overengineered. The model got better.
Agents-as-files: Google DeepMind shows how markdown instructions replace Python agent loops. Cursor replaced 12,000 lines of TypeScript with 200 lines. But…
AI EngineerDurable execution is the real agent infrastructure challenge
Giselle van Dongen demonstrates why durable execution infrastructure, not agent SDKs, is the real bottleneck for production agent systems. Concrete failure…
Theo - t3․ggAI didn't kill React Native. Shopify just found a different bet.
Shopify drops React Native for native, crediting AI agents. But the real story is about Expo, OTA updates, and whether this bet generalizes beyond Shopify's…
InfoQAI is hollowing out junior engineers; preceptorship is the fix.
Scott Hanselman argues AI is destroying the junior developer pipeline by eliminating routine coding tasks that build foundational skills. His proposed fix: a…
InfoQRoblox's fix for the trust gap between AI code and production shipping
Roblox's engineering director reveals that the hardest part of shipping AI-generated code isn't the models — it's trust infrastructure, policy changes, and…
David OndrejPi's creator on why less tooling is smarter agent engineering
Pi agent's creator explains why bash-first minimalism beats complex tool harnesses, why cloud agents aren't ready for real dev work, and what enterprises are…
IBM TechnologyGPT-6 solved a Millennium problem—does your team need that?
GPT-6 solved a Millennium math problem with 10,000 agents and massive compute. A security startup used AI to create a WeChat worm. Engineering leaders must…
Hugging FaceStop Prompting: Build an Environment, Train a Small Agent in Hours
Two practical experiments show how to turn any coding task into an RL environment and train small models to specialize fast. The real takeaway: start with…
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.