Franklin Castillo

Software Engineer ☀🌴

[Franklin Castillo @fkcastillo18]

@FlyaKiet @superset_sh OMG!!!! 🫡

[Franklin Castillo @fkcastillo18]

@ephraimduncan @telemetry @telemetrydev Very nice! I just gave it a try, and it's awesome what you have built so far! 👏

[Franklin Castillo @fkcastillo18]

@aidenybai yeah, same expression🤯🤯

[Franklin Castillo @fkcastillo18]

I did something similar to /explain me stuff after a point in a branch or PR, but tried this one today and the output looks awesome! Will integrate this into my workflow indeed.

[dex @dexhorthy]

https://t.co/L0G15QT1Tv

[Franklin Castillo @fkcastillo18]

Take 📝

[Uncle Bob Martin @unclebobmartin]

The ability to wrangle these immensely powerful, yet dangerously capricious, agents into a productive harness that produces high quality systems — is the software engineering challenge of this decade.

[Franklin Castillo @fkcastillo18]

Nos vemos en JConf2026!

[JConfDominicana @jconfdominicana]

¡Nos complace anunciar la participación de Franklin Castillo como conferencista de #JConfDominicana2026!
Desarrollador con experiencia en Java, Spring Boot y React, especializado en diseñar soluciones end-to-end que combinan un backend robusto con experiencias de usuario fluidas.

[Franklin Castillo @fkcastillo18]

@shadcn Imagine if we could have some kind of animation for this... it will be entertaining xD

[Franklin Castillo @fkcastillo18]

Would be great to know more about these best practices.

Also, since models/token usage are getting expensive, we have found of "optimize" these resources, seen this now is a reminder of that.

[Brian Armstrong @brian_armstrong]

How to keep AI spend flat while token usage grows exponentially: Not with friction and spend alerts. With better defaults, routing, and caching.

Better Defaults (not Usage Caps) – Engineers can choose any model they want, but defaults matter. We’re experimenting with defaulting to open weight models like GLM 5.2 and Kimi 2.7 through our LLM gateway, while still encouraging engineers to choose the right model for the task. 91% of our employees were never hitting their usage caps, so instead of lowering caps and driving up alerts, we're moving to cheaper defaults. Note that code reviews use a diversity of models, so they can check each other's work.

Better Routing – In our custom harnesses, we preprocess prompts and route to the best model for the job, considering cache hits and model pricing. For instance, you may want a frontier model for planning, but not for execution where they can be overkill. Ultimately, humans shouldn't be choosing models - AI can automate this task.

Better Caching – Cache misses are the easiest way to drive your cost up. All of our requests are cache aware, so we’re reusing a warm cache wherever possible. For example, our cache hit rate went from 5% → 60% in LibreChat once properly implemented.

Keep Context Lean – Start fresh sessions when switching tasks. Scope file context narrowly. Disconnect unused tools. Don't just compact. The goal isn't fewer tokens used, it's fewer tokens wasted.

Better Visibility – Our engineers can use as many tokens as they want, from whatever model they want, but we’ve made usage visible – and the more you spend on AI, the more impact we expect.

The goal isn't to suppress usage. It's to build the infrastructure that makes exponential growth sustainable.

Putting this into practice has cut our AI spend nearly in half, while our token usage continues to grow.

[Franklin Castillo @fkcastillo18]

@jahirsheikh8 A. Resource paths (/users/profile, /users/settings) give each resource its own cache key, clean routing, and dedicated handler. B looks clean until it grows - ?type= is for filtering, not selecting different resources. One handler, endless switch statements. CDNs cache A, not B.

[Franklin Castillo @fkcastillo18]

@github @impeccable_ai Wao!!! Congrats @pbakaus!
You've been doing a great job there, and this is for sure a kind of recognition of your effort. Keep rocking!

[Franklin Castillo @fkcastillo18]

This is huge! GitHub should come with something now...

[swyx @swyx]

Cursor/Graphite’s @TomasReimers just announced Origin

@cursor_ai’s long awaited Git competitor, scalable for agent workloads, extensible with api and mcp, and built in merge conflicts and co failure agent resolution

[Franklin Castillo @fkcastillo18]

@robinebers That's exactly what I understand when reading this... Paying for Fable 5 and getting responses from Opus 4.8, what a convenience, ah!

[Franklin Castillo @fkcastillo18]

Looks promising! But also consider new pricing on these (2x Opus):

Claude Fable 5/Mythos
Input -> $10 / MTok
Output -> $50 / MTok

*MTok = Million tokens.

[Claude @claudeai]

Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use.

Its capabilities exceed those of any model we’ve ever made generally available.

[Franklin Castillo @fkcastillo18]

Wao! This is huge 😯

[OpenAI @OpenAI]

Building apps has never been easier.

With Sites, Codex can turn your work, ideas, and plans into an interactive website or app your team can explore, use, and share with a URL.

Rolling out to Business and Enterprise plans, before expanding more broadly.

[Franklin Castillo @fkcastillo18]

@FlyaKiet @superset_sh Awesome!

[Franklin Castillo @fkcastillo18]

Interesting!

[Microsoft Learn @MicrosoftLearn]

We’re introducing a new GitHub Certified: Agentic AI Developer (GH-600).
As AI agents become part of modern development workflows, this role-based certification focuses on how developers and teams operate, supervise, and integrate agents across the SDLC.

If you’re already working with tools like GitHub Copilot or exploring agent-driven workflows, we’d love your input.

Learn more and get involved. https://t.co/ruiYtlsYnj

[Franklin Castillo @fkcastillo18]

@RakibullHassa13 I don't know 🤷🏻‍♂️
But as you see that one was first and he (the link a copied) is the face behind @AgenticUi.

If the person who post this (Zayden) at least could have created their own and change the "Agentic UI" text or mentioned the original. I wouldn't even commented in here.

[Franklin Castillo @fkcastillo18]

@RakibullHassa13 This is not even yours. I saw that first time here:
https://t.co/mFfnMv4StV

Taking somebody else's work, ah...

[Alex @alexgilev]

Guys, it's happening🤩!
Agentic UI is AVAILABLE for pre-order 👇.

→ https://t.co/zMwj1PojMw

[Franklin Castillo @fkcastillo18]

@FlyaKiet @superset_sh @vercel You've been doing a great job man 👏 👏 👏