Arfux

Computer guy. I like startups.
Deus Ex Machina
AI, ML, Data Science, Python.
EE Masters Student | UFMS
25y🇧🇷

[Arfux @SafeMantella]

2025 foi o ano da construção. Plantar o máximo de sementes possível, com o máximo de recursos que eu tinha, no máximo de lugares que alcanço.

2026 será o ano da ACELERAÇÃO

[Arfux @SafeMantella]

2024 foi o ano da presença. Me colocar e fazer presente em tudo o que eu quis e propus a fazer e colocar mais foco em mim e em meus objetivos

2025 será o ano da CONSTRUÇÃO

[Arfux @SafeMantella]

@Caio__Sandim Rock n roll

[rari @0xwhrrari]

Jev Founder, Diogo Almeida, just released a 12-page PDF on how to use Jev with LLMs

It is more useful than most paid AI courses:

this is a 10-step blueprint on how to build a faster, cheaper and more controllable AI system around Claude, Codex, Grok or any other LLM:

step 1 → split the responsibilities: the LLM generates, Jev makes bounded semantic decisions and deterministic code keeps authority

step 2 → build the state: give Jev the current request, relevant evidence, policy and proposed action instead of sending the entire conversation

step 3 → choose the right primitive: Choice selects a route, Score evaluates an ordered rubric and Noul returns the probability that a statement is true

step 4 → replace giant evaluation prompts with atomic questions: intent, urgency, evidence, risk and scope become separate typed decisions

step 5 → put Jev before the LLM: select the context, tools, provider and workflow before paying for an expensive generative call

step 6 → give the LLM a bounded job: once Jev selects the route, the model receives only the instructions, files and tools required for that branch

step 7 → put Jev after the LLM: check whether the result answers the request, uses sufficient evidence and stays inside the permitted scope

step 8 → route by confidence: high-confidence low-risk cases proceed automatically, uncertain cases request more context and consequential actions go to review

step 9 → batch independent decisions: ask multiple Choice, Score and Noul questions over one shared state instead of creating another LLM call for every judgment

step 10 → record the complete decision receipt: state version, question, probabilities, selected route, model, latency, outcome and human override

most AI courses teach you how to write a bigger prompt

this 12-page guide teaches you how to build the control system around every prompt

the result: smaller contexts, fewer unnecessary LLM calls, safer tool execution and decisions you can actually inspect, test and improve

Send this PDF and the original Jev article to Claude Code or Codex and start rebuilding one expensive LLM decision at a time ↓

[codila @0xCodila]

Send this Jev prompt to any LLM or AI agent

It sets up Jev → analyzes you → finds where you waste time and money → upgrades your AI setup beyond 95% of people...

Copy this now. Thank me later:

[Arfux @SafeMantella]

@dsmzin @thevideoseed

[Arfux @SafeMantella]

@dsmzin @thevideoseed Raíz. Eu uso o Claude

[Teknium 🪽 @Teknium]

Welcome back to Hermes Agent, Claude

New official plugin that uses Claude SDK without the tradeoffs to enable Claude Code subscriptions to work in Hermes Agent again!

Check it out and install it here: https://t.co/r5YghWTwiY

[codila @0xCodila]

Jev + GrokBot is the best AI agent system I’ve built in my life

It just made my setup CHEAPER and FASTER than what 95% of people are running...

setup takes literally 7 minutes:

prompt → GrokBot → Jev decision → GrokBot execution → result

step 1 → open @typesafeai , create API key (keep it off chat paste)

step 2 → tell Grok Bot: store TYPESAFE_API_KEY in the secure field

step 3 → prompt Grok Bot: install typesafe-sdk on Agent Computer + smoke system_one (Choice)

step 4 → tell Grok Bot: build the usage lab (router, dry-run, config, logs) - or clone Github below

step 5 → add skill jev-usage-router: before browser / research / retry / extra bot → call the router, honor action

step 6 → stay shadow first, read logs, then active when you trust it - kill switch: bypass jev or enabled: false

step 7 → flip active: GrokBot obeys route - Jev decides - GrokBot executes - humans control irreversible actions

the result: Jev + GrokBot the best and fastest agent running directly on your computer rn, I’ve already tested it on routine tasks - and the results are genuinely incredible

You can come up with endless ways to use Jev + GrokBot - but the most important thing is to install it as soon as possible

Copy this 2028 setup, explore my repo below - then read the full Jev deep dive ↓

[seeco @seeconvm]

Andrej Karpathy spent 8 years at OpenAI and Tesla

Last week, he compressed everything he knows into one free 2-hour lecture

Prompts → Harness → Loops → Graphs → Self-Improving Systems

This is not about tweaking text in a chat box

This is about understanding the core machinery and wiring the execution loop around it

People pay $15K for bootcamps that teach half of this

This single lecture beats almost every paid AI engineering course on the market

You probably don't have 2 hours right now

Don't let this get lost in your feed

Watch it first

Then read the step-by-step guide below and build your first loop ↓

[codila @0xCodila]

SpaceXAI team just compressed 1 month of GrokBot learning into 3-hour course: from "What is GrokBot?" to automating your entire life 24/7:

0% → 0:35 - what is GrokBot from scratch
30% → 34:17 - first Grok Bot team with workflow from team
45% → 42:40 - run +20 GrokBots in graph & loop
75% → 57:51 - Chief of Staff and PM: delegate the delegation
100% → 1:08:09 - full 24/7 GrokBot company that automate 100% of life + real case on building from SpaceXAI

Most courses teach an agent to answer. GrokBot’s creators teach an entire team to keep executing after you leave - and this is the course worth returning to again and again

Watch SpaceXAI replace people with GrokBots - then learn every detail of launching your first system below ↓

[FanPu Zeng @FanPu_Zeng]

the fly has learned to play blackjack (it's currently up)

[DHH @dhh]

THAT'S A LOT OF TOKENS FOR OMARCHY!!

Thanks again to the awesome team at @AIatMeta for supporting us as Founding Corporate Patrons for the Omacom Foundation. We will put these tokens to great, endless use 🙏

[Arfux @SafeMantella]

FINALMENTEEEEEE

[banteg @banteg]

super smash bros melee is fully decompiled, this project started in july 2020, so it took over 6 years. the progress was hugely accelerated by llms and finished off with astra. it's a very large game with 3.88mb of compiled code.
https://t.co/RKmrtwYZWl

[ashe @ashebytes]

since you guys loved the exploding tesla..

I used GPT-6 Astra to create a 3D website that pulls apart the male anatomy into 2,234 modeled pieces!

we are in a renaissance of learning

[Arfux @SafeMantella]

@marithemariana Zorin é muito bom. Recomendo particionar o seu HD pra deixar seus arquivos separados da partição do SO pra não precisar fazer tanto backup.

Isso porque pode ocorrer de você quebrar o seu Linux sem querer (não me pergunte como eu sei disso) ou querer testar outras distros.

[Arfux @SafeMantella]

@dsmzin É muito feio pprt

[Arfux @SafeMantella]

@rodrigo1galeano É a tropa do 6 a 8 reps

[Sabrina Ramonov 🍄 @Sabrina_Ramonov]

Here's the exact setup to build a one-person company with Grok @bot. Starting with what every founder struggles with: marketing.
I took the system behind my 41 million views in 30 days, rebuilt them inside Grok Bot, and launched a marketing team. https://t.co/upBN3DP9tz

[Arfux @SafeMantella]

@johnternus Hello!

[Kat ⊷ the Poet Engineer @poetengineer__]

imagining a few small gestures to edit/write with ai:
word: spin synonyms
sentence: shift the tone (cold <-> warm)
paragraph: shorten/expand

[Dutch1777 @dutch1777real]

Some heroes do wear capes.