Topic
Productivity & Process - Page 7
Process changes that affect focus, throughput, and quality. Curated tldw.news briefings about productivity & process, with practical engineering takeaways from long-form AI and developer-tool videos.
250
breakdowns
Page 7 of 25
Cole MedinThe $21 lesson: use decision models for email triage, not LLMs.
Jev handled 38,000 decision calls for $21 before most inputs reached an LLM. The caveat: final context-heavy judgment still needs a language model.
Weights & BiasesWhy your coding agent costs explode and how to fix it
Cognition Labs reveals the training recipe behind SWE-1.7: asynchronous RL, precision replay, and a linear length penalty that determines whether your AI…
Theo - t3․ggOpenAI's Codex plan lost 10x value. Claude is the better bet now.
OpenAI slashed Codex plan value by 10x. Claude's $200 plan now delivers better practical output for coding teams. The real insight: cheaper models like…
The Pragmatic EngineerSam Newman: Microservices are a last resort. Resilience is a people problem.
Sam Newman calls microservices an architecture of last resort. His resilience framework puts people, tradeoffs, and AI guardrails before infrastructure.
James BriggsJev's Calibration Is Real. Its Moat Isn't—GLiNER Is Already Close.
Jev's calibrated probabilities make classification trustworthy, but GLiNER runs faster and cheaper locally. The fast-and-slow combo beats either alone.
InfoQWhy upgrading your LLM won't fix context problems
After building an Alexa skill, a Redis engineer found that upgrading to GPT-4 did nothing for context poisoning, confusion, and rot. The fix was a pipeline…
Theo - t3․ggAnthropic's AI Performance Sprint: What Engineering Leaders Should Learn
Anthropic made Claude 3x faster in two weeks using Claude itself. The approach? Measure everything, let the AI climb, and ratchet benchmarks. But the…
AI EngineerAssemblyAI's Joey: Building vs buying an AI support agent
AssemblyAI replaced a 10% resolution off-the-shelf bot with an in-house AI agent that handles 80% of tickets for $700/month. The engineering lesson is about…
Theo - t3․ggPersonal AI subs offer 40x more tokens – but at what cost?
Personal AI subs give you 40x the tokens of API for coding. But the tradeoff: account bans, proxy setup, and constant token management.
OpenAIOpenAI's Dot demo shows agentic workflows are real but still need guardrails
OpenAI's rerun of the Dot demo shows an agent booking flights, analyzing feedback, and drafting Slack replies in one session. Real multi-step work. Real…
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.