Jeffrey Davidson
938 posts

Jeffrey Davidson
@jdavidsonwebdev
Editor: VS Code | Font: Operator Mono | @laravelphp Jeffrey is a husband, father and software engineer navigating through life.
Davenport, FL Katılım Eylül 2009
909 Takip Edilen226 Takipçiler
Jeffrey Davidson retweetledi

Laravel AI SDK now supports sub-agents. 🤝
Return an agent from another agent’s tools() method and the parent agent can delegate focused tasks to it, just like any other tool.
Sub-agents can have their own instructions, tools, provider config, and isolated context.
#sub-agents" target="_blank" rel="nofollow noopener">laravel.com/docs/13.x/ai-s…

English

@PovilasKorop can you checkout the satis url for FilamentExamples. URL is erroring out for Filacheck Pro
English
Jeffrey Davidson retweetledi

The most dangerous thing you can do right now is NOT use the latest AI tools. Period.
Every day a new company is laying off thousands of people who don't know how to use the most modern AI tools
If I were in the 9-5 world right now, this is every step I'd take:
1. Download Codex and build your first app. Learn how to implement a front end and database. AI can teach you all of this
2. Download OpenClaw or Hermes agent. Tell the agent about your entire life. Career, goals, and ambitions. Ask it what workflows it can implement to get you closer to those goals
3. Get Claude Design. Keep an eye out on X for visual language and designs you like. Feed this inspiration into Claude Design and get comfortable designing beautiful interfaces
4. Get the ChatGPT Pro plan. Feed GPT 5.5 Pro your hardest problems. Burn as many tokens as humanly possible with this model
5. Constantly look at your limits in all your AI plans. If you're ever above 50% on your limits, get angry that you're not burning enough tokens.
6. Learn how to use Claude Code side by side with Codex. Learn both their strengths. These are the only 2 coding tools that matter. Master these and you're golden
If you do these 6 things you are in excellent position to not only be safe in your career, but also dominate those that don't pick up these skills.
English

@DavidOndrej1 Don’t be a troll. @AlexFinn knows what he’s talking about.
English

this guy has ZERO idea what he's talking about
Alex Finn@AlexFinn
Hermes Agent has been EXCELLENT lately Reliable and 0 broken updates. It just works They've also added some new features that have BLOWN my mind In this video I cover EVERYTHING Hermes, and give you a workflow that will 10x your productivity:
English
Jeffrey Davidson retweetledi
Jeffrey Davidson retweetledi

If you didn't see last week, Laravel officially adopted @enunomaduro 's PAO package. That means the original package set up by Nuno is marked as abandoned and requires switching over in composer.json dependencies. 🙃
This is one of the reasons I use my composer-upgrade skill when I want to install or upgrade packages in a project. It does it with precision, in this case detecting the abandoned package, requiring the alternative without any effort on my part.
Then, to top it off, it bumps the composer.json file with what's in the lock 😎 so there are no accidental package regressions in the future.
Perfection.

English
Jeffrey Davidson retweetledi

If you’re working with Laravel and find yourself struggling to understand your app’s lifecycle or how your code connects, then Laravel Brain is built for you! 🧠✨
🎯 Laravel Brain gives you a live visual map of everything happening inside your application — from execution flow down to the smallest details 👀
✅ Real-time AST parsing
✅ Visual lifecycle tracking
✅ Deeper understanding of your code instead of guessing
💻 Imagine seeing everything happening in real-time right in front of you!
No more confusion. No more blind debugging 🔥
📌 Try the package here:
github.com/laramint/larav…
🎥 Watch how it works:
youtube.com/watch?v=e4Fp-M…
📌 The package is still evolving — this is just the beginning…
We’re building a tool that helps every Laravel developer understand their project in seconds!
👇 What feature would you love to see next?
Share it with any Laravel dev you know — and let them see their code like never before 😉🚀

YouTube

English

@aarondfrancis Are you able to send a link to the discord. Now that I've bought into the project I'd like to join the group.
English

Just picked up Solo Pro by @aarondfrancis! 🚀 soloterm.com
English
Jeffrey Davidson retweetledi

The Local LLM cheat sheet for your 16GB RAM device
I pulled together a lineup of small models that can run comfortably on a Mac Mini or personal laptop while still leaving room for context without melting your machine.
Models for Daily Use
Qwen3.5 9B / GGUF / Q4_K_M
Daily driver. General chat, drafting, research, translation. If you're keeping only one, keep this.
DeepSeek-R1 Distill Qwen 7B / GGUF / Q4_K_M
Reasoning engine. Math, logic, step-by-step problems. Slower, but worth it when you need actual thinking.
Models for Specialty Work
Qwen2.5 Coder 7B / GGUF / Q4_K_M
Code specialist. Completions, refactors, debugging, repo Q&A. Better than a generalist when the task is code.
Llama 3.1 8B / GGUF / Q4_K_M
Long context worker. RAG, doc chat, codebase Q and A. The output isn't top tier, but the context is strong for its size.
Phi-4 Mini Reasoning / GGUF / Q4_K_M
Compact thinker. Logic, structured answers, math, and short coding bursts. Smaller context is the catch.
Models for Efficiency
Gemma 4 E4B / GGUF / Q4_K_M
Light all-rounder. Writing, chat, light agents, structured output.
Phi-3.5 Mini / GGUF / Q5_K_M
Pocket sidekick. Summaries, extraction, background doc chat. Easy to pair with a bigger model.
Qwen3.5 2B / GGUF / Q4_K_M
Useful for summaries, tagging, rewrites, and lightweight sidekick work.
Micro Models
Qwen3.5 0.8B / GGUF / Q5_K_M
Classification, keyword routing, binary decisions, triage.
Gemma 4 E2B-it / GGUF / Q4_K_M
Lightweight chat, quick Q and A, summaries, tiny agents.
My personal choice for a single model is Qwen3.5 9B
For two models use Qwen3.5 9B + Qwen2.5 Coder 7B for code, or Qwen3.5 9B + Phi-3.5 Mini for support tasks.
Let me know in the comments your experience with these models, or any I have left out.

English
Jeffrey Davidson retweetledi
Jeffrey Davidson retweetledi

Handy trick for @filamentphp resource badges: use the Laravel flexible cache to stop hitting the database on every load. Shows the old count while the new one updates silently. ✨

English
Jeffrey Davidson retweetledi

Just joined Vibe Code Academy from @AlexFinn! AI has been here and everyone should at least try to understand it.
English
Jeffrey Davidson retweetledi
Jeffrey Davidson retweetledi

Quick ui.sh demo — generating multiple design ideas to choose from, no matter what tech stack you use:
English











