Topic
Coding Agents - Page 2
Practical shifts in agentic coding, review, and delivery. Curated tldw.news briefings about coding agents, with practical engineering takeaways from long-form AI and developer-tool videos.
110
breakdowns
Page 2 of 11
Y CombinatorHarness, not model, now decides agent performance and cost
How much agent performance comes from the harness, not the model? YC's harness night shows huge gains—and the governance costs that follow.
InfoQShipping faster is compounding performance debt faster
AI agents are accelerating shipping—and hidden performance debt. OpenAI says the bottleneck isn't just GPUs; it's the entire pre-inference path.
Theo - t3․ggGPT-6 Astra Changes What Automation Means—But You Can't Use It Yet
GPT-6 Astra delivers revolutionary computer use and 3D capabilities, completing tasks in a third of the time of previous models. But limited launch access…
IBM TechnologyAI Agents Need Four Knowledge Layers, Not Just One Big Context Window
Don't just dump context into your AI agent. Skills, MCP, RAG, and Memory each solve a different problem. Learn which to use when – and the hidden tradeoff…
Theo - t3․ggFable 5.1: The merge manager generation has arrived in AI coding
Fable 5.1 shifts AI coding from generation to autonomous merge management—89 PRs in 24 hours. But verbose output means one-shot tasks may cost more than…
Latent SpaceCerebras CTO: 200 TPS is the new batch mode—ultra-fast inference changes everything
Cerebras CTO Sean Lie on why 200 TPS is becoming 'batch mode,' how CS4 is already inside OpenAI for real-time incident response, and why CS5 will push…
David OndrejStop letting managed AI tools own your workflow infrastructure
David Andre's agentic engineering setup reveals a hard truth: managed AI agents create ecosystem lock-in. His VPS-based alternative cuts costs but demands…
All About AIReal-Time AI Video Streaming Works, But Costs Crush the Hype
Real-time AI video streaming is technically feasible—but at $14+/hour for low-res, the cost barrier is the real story. A hands-on demo reveals the tradeoff…
AI EngineerWhy AI-generated code needs mathematical proof, not just tests
AI coding agents generate PRs faster than humans can review. Formal verification with Lean mathematically proves correctness for all inputs—something tests…
AI EngineerWhy Frontier LLMs Still Can't Write Fast Multi-GPU Kernels
LLMs solve only a third of multi-GPU kernel tasks despite excelling on single-GPU benchmarks. The bottleneck has shifted to communication, and reasoning…
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.