Elroy Tracey

[Elroy Tracey @elroyic]

@CyrilRamaphosa @ThuliMadonsela3 Yes we must trust the same people that accept cold drink please talk sense.

[Elroy Tracey @elroyic]

@sama @gabeeegoooh Did it train on manga it's bubbles are right to left and not left to right

[Elroy Tracey @elroyic]

@CarloFCesar @AlexFinn Qwen 3.6 35B A3B best open source model and you can run a few instances (4/5) instances on your setup

[Elroy Tracey @elroyic]

@VisualFidelity Had my doubts when I started playing but the story actually is very meta, just think of it as you being isakied into main character and everything flows. Controls didn't make sense but as you get skills they make more sense.

[Elroy Tracey @elroyic]

@antigravity Thanks for update these limits are dumb cancelled sub thanks for all the fish.

[Elroy Tracey @elroyic]

@literallydenis that is not usable

[Elroy Tracey @elroyic]

@kacieahmed Sounds fun 👋

[Elroy Tracey @elroyic]

@sudoingX Running with ROCm on Halo Strix 128Gb Qwen3.5 35B at full context get 35tok/s uses 60Gb Ram/VRAM.

[Elroy Tracey @elroyic]

@martinlasek this guy thinking he can replace Claude with 36gb of ram lol

[Elroy Tracey @elroyic]

@itsjustmarky @TeksEdge @arena I am getting 35 tok/s with the 35B make sure you have ROCm 7.2 and you running it through LMStudio

[Elroy Tracey @elroyic]

@axiomofmind @mattshumer_ multi gate way, each claw then spin up sub agents as needed.

[Elroy Tracey @elroyic]

@SethCronin @mattshumer_ common chat room, suggestion is using IRC you can host it locally on your network and you in control of the logs.

[Elroy Tracey @elroyic]

@onusoz @mattshumer_ working on many tasks at once... splitting context to many claws instead of clogging one... performance and ability for each claw to focus on one task instead of everything you ever thought of.

[Elroy Tracey @elroyic]

@mattshumer_ Token used infinite... haha

[Elroy Tracey @elroyic]

@mattshumer_ Many claws, one machine, one vm per claw. Each claw has its own workspace. There is a shared workspace. Discord Channels for communication between claws (cron job to check channels), embedded knowledge graph to share context.

[Elroy Tracey @elroyic]

@pcshipp Locally in a VM why do you need to pay VPS fees.

[Elroy Tracey @elroyic]

@sudoingX On AMD Halo strix platform with 128Gb Ram. Getting 25 t/s on Q8 model with 200k token context window. Feels fast enough.

[Elroy Tracey @elroyic]

@SimplePestMgmt @steipete @openclaw Even GPT OSS 20B knows the date bruh.

[Vadim @VadimStrizheus]

POV: your OpenClaw after you didn’t set up a second brain system.

Paste this prompt to fix that: 👇

I want you to build me a second brain memory system.

Create a memory/ folder and a https://t.co/Msllm4OWRv file in your workspace. Every session, read these FIRST before doing anything, they are your entire memory.

memory/YYYY-MM-DD.md are your daily journals. As we talk each day, log everything in real-time - decisions, tasks, preferences, context, mistakes.

Timestamp each entry. These are your raw notes.

https://t.co/Msllm4OWRv is your long-term memory. This is curated, who I am, my goals, my preferences, active projects, lessons learned, key decisions and why.

Every few days, review your daily journals and distill the important stuff into here.

The rule: if it's not written to a file, you don't remember it.

When I say "remember this", write it immediately. When you make a mistake,document it so you never repeat it.

When you learn something about me update https://t.co/Msllm4OWRv.

Over time you should know my communication style, what I care about, what annoys me, my projects, my goals.

After a week this should feel like a real assistant that actually knows me. After a month, indispensable.

[Vadim @VadimStrizheus]

Introducing my AI enterprise company. 🦞

Just some 18/yo with zero coding experience.