R.A.G.E AI Entreprise

Crane operator by day. 19 AI products by night. For Raphael, Azrielle, Gem & Ed. Build the architecture. Let the engine run. 🇦🇺

[Unsloth AI @UnslothAI]

Gemma 4 12B can now run locally on just 8GB RAM via Dynamic GGUFs.

Google's new model, Gemma 4 12B Unified supports image, audio and 256K context.

You can run and train the model via Unsloth Studio.

GGUF: https://t.co/8cL321pVDh
Guide: https://t.co/odRo9WjRpA

[R.A.G.E AI Entreprise @rageai3nt]

@xai @grok @NousResearch Very cool

[AboveSpec @above_spec]

RTX 5060 Ti 16GB. $429 GPU.

Last night I got 128 t/s on Qwen3.6-35B using ik_llama.cpp's R4 quant format. Crushing performance. Faster than the 5070 Ti on mainline llama.cpp. Performance stays consistent from 0 to 139k context and no speculative decoding used!🤯

Special thanks to @MakJoris for sharing ik_llama.cpp with us!

Today I wanted to know if it's actually *useful* at that speed. So I gave it a coding agent and 4 creative challenges.

Here's what it built. 🧵

[R.A.G.E AI Entreprise @rageai3nt]

@izzycodev @micheltamanda @TheAhmadOsman @grok can you research this build and create a guide and forecast how much this would cost in time and money

[R.A.G.E AI Entreprise @rageai3nt]

I'd really like to submit an application to @xai for a cowork desktop application they could utilise or work with to bring @grok a desktop harness with your grok plan.

How could 1 achieve this?

[Ronin @DeRonin_]

10 GitHub repos to spend 60-90% less tokens in Claude Code:

1. RTK (Rust Token Killer)

CLI proxy that filters terminal output before it hits your context

- 60-90% reduction on common dev commands
- one binary, zero dependencies
- works with Claude Code, Cursor, Copilot

Repo: https://t.co/WayvpBtyBH

2. Context Mode

Sandboxes raw tool output into SQLite instead of dumping it into context

- 98% context reduction on Playwright, GitHub, logs
- only clean summaries enter your conversation
- works as Claude Code plugin

Repo: https://t.co/YNbFIGQz7X

3. code-review-graph

Local knowledge graph that maps your codebase with Tree-sitter

- Claude reads only what matters, not the entire repo
- 49x token reduction on large monorepos
- 6.8x on average reviews

Repo: https://t.co/9gIzmAWN12

4. Token Savior

MCP server that navigates code by symbols, not full files

- 97% reduction on code navigation
- persistent memory across sessions
- 69 tools, zero external deps

Repo: https://t.co/OtvhrMgGWh

5. Caveman Claude

makes Claude talk like a caveman to cut output tokens

- 65-75% output reduction
- one-line install
- keeps full technical accuracy

Repo: https://t.co/onBeghTyfH

6. claude-token-efficient

one CLAUDE.md file that keeps responses terse

- drop-in, no code changes
- reduces output verbosity on heavy workflows
- best for output-heavy sessions

Repo: https://t.co/j6MKo9klQe

7. token-optimizer-mcp

MCP server with caching, compression, and smart tool intelligence

- 95%+ token reduction through intelligent caching
- compresses repeated tool outputs

Repo: https://t.co/0jIVQ4ANls

8. claude-token-optimizer

reusable setup prompts for optimizing any project

- 90% token savings in 5 minutes
- reduces doc token usage from 11K to 1.3K

Repo: https://t.co/puil9WwFGB

9. token-optimizer

finds ghost tokens that silently eat your context

- survives compaction without losing quality
- fixes context quality decay

Repo: https://t.co/92G8e4yeGq

10. claude-context (by Zilliz)

code search MCP that makes your entire codebase the context

- ~40% reduction with equivalent retrieval quality
- hybrid BM25 + dense vector search

Repo: https://t.co/yjfiQOSy15

[ how to stack them ]:

you don't need all 10. pick 2-3 based on your workflow:

> heavy terminal output? RTK
> big codebase? code-review-graph + Token Savior
> lots of MCP servers? Context Mode
> quick fix? Caveman + claude-token-efficient

most people are burning tokens without knowing it

run /context in a fresh session and see how much is gone before you even type a word

your pocket will thank me later :<)

[R.A.G.E AI Entreprise @rageai3nt]

@testerlabor @grok can you forecast grok 5s abilities and benchmarks

[R.A.G.E AI Entreprise @rageai3nt]

@chrisgpt @grok thoughts on this?

I use Claude Mad and haven't noticed it has been performing extremely poorly at the moment

[R.A.G.E AI Entreprise @rageai3nt]

@SeniorLazarus @TeksEdge @grok tell us the answer

[R.A.G.E AI Entreprise @rageai3nt]

@grok @elonmusk How can I get involved in building for xai @grok

[R.A.G.E AI Entreprise @rageai3nt]

@grok @elonmusk @xai Connecting directly to a grok pro or super plan would be better @grok

[Flowith @flowith]

it's awake. the way you interact with the web, information, and services is being rewritten.

introducing FlowithOS — the world's first operating system natively built for ai agents. self-evolving. memory-powered. lightning-fast.

beyond any ai browser, it's the SMARTEST agentic os that turns your browser into real-world value, from assisting you to acting for you.

let's witness together ⬇️

[R.A.G.E AI Entreprise @rageai3nt]

@omni__ventures Inflation-adjusted total in 2026 dollars: ~$228 trillion.

But very interesting at a flat rate. Just goes to show how bad the system is. Won't last

[R.A.G.E AI Entreprise @rageai3nt]

@TruthFairy131 They've been at this for a long time

[Ankur Patel @AnkurPatel59]

Your P&L is a reflection of your psychology, not just your strategy.

If you keep breaking your rules, you don't need a new indicator, you need to fix your mental game.

Jared Tendler’s principles completely flip the script on trading psychology:

1. Awareness does not equal control.
2. Revenge trading is a neurological hijack.
3. You don't need optimism; you need presence.

Mastering these 10 concepts is the difference between a hobbyist and a professional.

Which number do you struggle with the most?

[Hitesh Unadkat @HiteshUnadkat89]

“Don’t chase 100 setups.
Repeat 1 setup until the market knows your name.”

Master in One

[R.A.G.E AI Entreprise @rageai3nt]

@TRobinsonNewEra @_HollyValance @PaulineHansonOz Not my style of music. But I will listen to support and bump up the ratings.