THE INFINITY KRōM

The instruction manual for smart work & success.

👇🏽Automate Your Intentions👇🏽

[THE INFINITY KRōM @InfinityKrom]

Traders do you know these authors?

W.D. Gann
Daniel T. Ferrera
Dr. Jerome Baumring
Sean Erikson
Alexander Straker
Eric Penicka
Hasbrouck
Dr. Alexander Goulden
Gordon Roberts
L. David Linsky
Daniele Prandelli
Catalina Plapcianu
Lorrie Bennet
Robert Rundle

Jim Simons
Ray Dalio

[Machina @EXM7777]

Hermes or Grok Bot... i finally have a clean answer

Grok Bot is stupid easy: pay the sub, open the desktop app, spin up cute little bots that do things for you

Hermes can do all of that and better, but the Grok marketing is genuinely working on people

the difference: Grok Bot is a personal assistant, Hermes is a real harness... even more efficient than Claude Code or Codex sometimes, with a whole other world of capabilities

you can build whatever you want with it, there are no limits to the customization

so here's my honest recommendation...

if you're not into AI, don't know what a harness even is, and just want a little bot that handles things while you get on with your day... get Grok Bot, you'll be happy with it

but if you're building real workflows, if you want a system that grows with you until it's YOUR thing and not just a tool you rent... Hermes, every time (it's also much cheaper to run)

[THE INFINITY KRōM @InfinityKrom]

Why should they?

[Pri @solopribuilds]

does anyone actually use Antigravity?

[Jason Klum @PokemanZ0N6]

The mediocre compositing reminded me how much i love this fire force fight (also in a dark room)

this is just much better fine tuned compositing and even compliments the animation instead of damaging it, absolutely gorgeous

[Jason Klum @PokemanZ0N6]

The bleach fans could've actually just enjoyed their once a decade episode wonder and moved on

But they decided to immediately ride op by comparing someone like Orihime to Nami, and comparing the episode to gear 5, as GV announcement erases that episode existence from TL 😭

[THE INFINITY KRōM @InfinityKrom]

This is obviously someone botting the episode.

Also why I can't trust these ratings platforms

[Buba @BubaReZero]

Mushoku Tensei S3 Episode 9 – Call an ambulance.

Seriously, call an ambulance.
After yesterday's bullying, Mushoku Tensei is in even worse shape today.
I don't know if it'll survive.
Call 911.
It went from 40.8% one-star ratings yesterday to 54.8% today.

Holy shit.

[THE INFINITY KRōM @InfinityKrom]

God Valley pilled

[Wes Winder @weswinder]

ya'll realize skills are just a prompt in a markdown file right?

[Alvaro Cintas @dr_cintas]

The #1 problem with local AI is now solved.

There’s a free tool called https://t.co/yubPHLT3kl that checks your hardware and tells you which models will actually run well before you download anything.

So instead of guessing and hitting out-of-memory errors…it grades every model against your machine.

What it does (right in your browser, no install):

→ detects your setup (RAM / CPU / GPU / VRAM)
→ scores each model for fit, speed, and context length
→ grades every quantization level (Q4_K_M, Q6_K, Q8_0, etc.)
→ labels what runs great vs okay vs too heavy

It covers most of the open-weight stack, Llama, Qwen, Gemma, Mistral, DeepSeek, Phi and more, pulling requirements from llama.cpp, Ollama, and LM Studio.

And it’s fully opensource

[Teknium 🪽 @Teknium]

The connectors catalog in Hermes now has access to a lot more tools!

Access Cloudflare, Datadog, Metabase, GitLab, Railway, DeepWiki and many more services and data sources with just one click!

And with our Tool Search tool, they wont waste any of your context when activated.

Enjoy!

[AJ @ItsmeAjayKV]

Man I wish I had a spark 😭

We are getting qwen3.8-125B tomorrow 🤩

I think i'll be able to run lower quants, but mannn a 128GB unified memory rocks for MoEs.

One day 👆🏻

[Professional Vibe Curator 🦧🥇 @GumboGoon]

I know Rocks used to get tired of Big Mom always being pregnant on his damn ship

[THE INFINITY KRōM @InfinityKrom]

@MrPluhini When these 2 are done I'll probably never watch TV again

[THE INFINITY KRōM @InfinityKrom]

@lujazbik A fellow citizen of Tempest, I see.

[THE INFINITY KRōM @InfinityKrom]

@igetbuccets0095 @lujazbik That's because the characters have personality and the story is really good. Hard not to love it

[Andrew Ng @AndrewYNg]

OpenWorker -- an open source agent that doesn't just chat but completes tasks on your laptop -- just released a new version with many features for security workflows.

After our initial release, many users found it especially useful for cybersecurity. Attackers are already using AI; OpenWorker is committed to giving defenders the same leverage. Running an agent requires both (i) A model and (ii) A harness (the software around the model). Because the OpenWorker harness is fully open source, security teams can audit it to make sure we haven't built any backdoors that exfiltrate your code and data to some company or even a foreign adversary.

OpenWorker now comes with built-in cybersecurity agents for (i) Scanning your code for vulnerabilities. (ii) Scanning dependencies for supply chain injections. (iii) Checking your cloud security configuration for attack surfaces. This enables developers to do much more security work before deployment (part of what's called the "shift left" movement).

You choose the model: you can run open weight models fully locally so sensitive code never leaves your machine. This helps with legitimate security work (like reproducing a known exploit to defend against it) that can trigger refusals in leading closed models. Or use your ChatGPT subscription, or stealth preview models like Ox Alpha, or any model via API key.

Thanks also to all the open source contributors!

Join work with @rohitcprasad so please follow him too to get more frequent updates.

Try it out: https://t.co/QPZLudn7ug
Code: https://t.co/NYCiTD6hSq

[THE INFINITY KRōM @InfinityKrom]

@Superfinity100 @Acceletor4882 Think Mushoku Tensei and Re:Zero has stuff airing next year as well. But am hyped for Tensura S4

[Dr. Émile P. Torres (they/them) @xriskology]

Oh, I believe you. & I believe Altman when he says the only way to "survive" ASI is through human extinction. I believe Yudkowsky when he says he'd sacrifice all of humanity for ASIs "having fun." I believe Amodei when he says he thinks there's a 25% chance of universal death.👇

[THE INFINITY KRōM @InfinityKrom]

The Asimov Cascade

[maria @maria_rcks]

here

[Henry Thurlow @henry_thurlow]

Working in the anime industry would be so much more fun if the deadlines weren't as brutal. I often look down at what I'm drawing & think "Damn, this is like living the dream" only to look at the calendar & realize I have to get it all done in an agonizingly short amount of time.