Deschide articolul original într-un tab nou Schimbarea acestei opțiuni se aplică imediat și reîncarcă pagina.
LECTURA
Înapoi la articole →

Think and Act as One

blog.fnil.net/atom.xml
Vizitează site-ul

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 17

  1. LLMs Already Understand Observability. What Is Left for the Database?

    (Think and Act as One)

    The last post in this series.

  2. Twenty Years of S3: How It Became the Default Persistence Layer for Modern Data Infrastructure

    (Think and Act as One)

    S3 launched twenty years ago as a simple object store with eventual consistency.

  3. Bigtable at Twenty: What Stayed and What Got Rebuilt

    (Think and Act as One)

    SIGMOD Companion '26 has a 13-page paper by 50+ Google authors revisiting Bigtable two decades on. 10 EB, 7 billion QPS, and an architecture that barely moved.

  4. Why Now: The Eight-Year Wait for Unified Observability

    (Think and Act as One)

    An idea someone had fully worked out back in 2018, yet it took eight years before it could actually be built.

  5. When Agents Go to Production: What Actually Breaks

    (Think and Act as One)

    When agents go to production, they break the four assumptions today's infrastructure was built on: deterministic, human-driven, request-response, stateless.

  6. I Burned 23 Billion Tokens to "Rewrite" Langfuse

    (Think and Act as One)

    A migration retro: forking Langfuse to swap its analytics store from ClickHouse to GreptimeDB, run mostly by two AI agents.

  7. The Three Pillars of Observability: The Unification That Never Quite Arrived

    (Think and Act as One)

    Part 1 was about how the three pillars split apart.

  8. The Three Pillars of Observability: A History No One Planned

    (Think and Act as One)

    Today we treat metrics, logging, and tracing as the natural structure of observability.

  9. When Systems Turn Uncertain: How Datadog Sees Observability in the AI Era

    (Think and Act as One)

    Datadog's Investor Day deck quietly redefines observability: the object of observation turns probabilistic, AI agents become operators, and the reader of the data shifts from human to model.

  10. TMA1 v2: Making the Agent Loop actually loop

    (Think and Act as One)

    TMA1 v2 adds an MCP server, enhanced hooks that auto-inject build/session/anomaly context, and cross-agent context sharing between Claude Code and Codex.

  11. Observing my coding agents without leaving localhost

    (Think and Act as One)

    TMA1: a local observability tool for AI coding agents with full session trace, tool decision breakdown, latency tracking, and SQL-queryable storage.

  12. Six Ways to Make Your Infrastructure Agent-Friendly

    (Think and Act as One)

    Have we been building infrastructure for humans this whole time, without ever treating agents as users?

  13. Is Database MCP Just Unnecessary Overhead?

    (Think and Act as One)

    My colleague called Database MCP 'pulling your pants down to fart.'

  14. My AI Coding Experience: Three Principles

    (Think and Act as One)

    AI Coding doesn't fundamentally make you a better programmer.

  15. Using AI ≠ AI Native: What It Really Means to Transform How Teams Work

    (Think and Act as One)

    The difference between using AI as a tool you pick up occasionally versus treating AI as infrastructure you don't know how to work without.

  16. Rethinking Software Design Principles in the Age of Vibe Coding

    (Think and Act as One)

    When AI can rewrite an entire module in seconds, do the design principles built for 'humans maintaining code' still apply?

  17. The AI Productivity Divide: From 10x to 100x Engineers

    (Think and Act as One)

    AI's real value isn't in producing the final output—it's in creating Builders.