Topic
Developer Tooling - Page 14
Tools that change how teams build, review, and ship. Curated tldw.news briefings about developer tooling, with practical engineering takeaways from long-form AI and developer-tool videos.
159
breakdowns
Page 14 of 16
AI EngineerWhy Agents Fail Across Repos—and How to Fix It
Agent amnesia across repos is the hidden tax on AI coding productivity—here’s how a meta harness can give agents photographic organizational memory.
AI EngineerThe Log Is Your Agent, and Your Deepest Lock-In
Agent identity is the append-only log, not the model. This makes log ownership the deepest lock-in—a talk with sharp insights and a product pitch.
InfoQCloud Lock-In Is a Geopolitical Risk
Cloud lock-in is a geopolitical risk. This talk covers multi-cloud and local-first strategies to reduce reliance on US cloud providers.
Theo - t3․ggChannels Are the True Unit of AI Context
Claude Tag’s real innovation isn’t the Slack bot—it’s channel-scoped AI memory that matches how teams actually organize. Useful, but watch for model lock-in.
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.
Latent SpaceThe Agent OS and the End of CDC
Databricks open-sourced Omnigen for agent governance and LTAP to eliminate ETL, but production readiness is still unproven.
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.
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.
InfoQContext Bloat Will Drain Your AI Budget—Fix It with Just-in-Time Tools
Unused MCP servers silently multiply token costs by 175x. Gateways and registries enable just-in-time tool delivery—but real-world proof is absent.
InfoQAI’s Real Bottleneck: Context, Not Compute
CAST’s graph halved token use and doubled accuracy, letting a team cut a mainframe modernization from 7.5 years to 3.
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.