mysteryresolved

@thechosenberg Aww 🥰

Many such cases

@AlexFinn How is the token burn ?

Drop what you're doing. It happened. ChatGPT 5.5 is out and it beats Opus 4.7 in almost every benchmark It even beat Mythos in some benchmarks including Terminal-Bench 2.0 This is what you need to do immediately if you want to escape the permanent underclass: • Download the Codex desktop app and start using this model. Codex now has computer use so it can act as an agent • Upgrade your OpenClaw to ChatGPT 5.5. A lot of the team has been saying they have been building this model for OpenClaw (I will verify this soon) • Everything you do on your computer for the next 24 hours, describe it to ChatGPT 5.5 and ask how it can do the task better • It's by far best in class for knowledge work tasks. Every document, spreadsheet, presentation you create should go through 5.5 • Take a moment and be grateful you are alive during the greatest tech explosion in history When new tech drops, you have to take advantage of it. That's the only way to win Put your phone on Do Not Disturb and get to it

@efariasr @JulianGoldieSEO Correct and let’s be honest nobody wants to run the minimum.

@JulianGoldieSEO This is not complete true. To run Kimi K2.6 you need at least 360GB vram, that infrastructure it cost a lot. The api it's not free either, it cost like $20 p/month. So.. an open weight model it doesn't mean free at all.

China just made Hermes free forever 🚀 You can now run Hermes with Kimi K 2.6 through Ollama in one click. Just install the model, launch Hermes, select Kimi K 2.6 and suddenly you have a powerful AI agent running locally with zero API fees. This might be the easiest free Hermes setup yet.

@AlexFinn The m3 studio max are being sold each for 25k by scalpers. So you are suggesting a 50k setup just to be clear

It happened. An open weights model just dropped that benchmarks higher than Opus 4.6 is out If you have 2 Mac Studios w/ 512gb, you can run Opus 4.6 level intelligence completely for free on your desk I warned you this would happen months ago. Now Mac Studios and Mac Minis are sold out The next Mac Studio has been delayed until Q3/Q4. The price will be significantly higher I told you this was going to happen. Intelligence explosion. Hardware bottleneck. Increased efficiency Luckily I picked up 2 Mac Studio 512gbs, 2 Mac Minis, and a DGX Spark I will be loading this up in the next couple of days and will have completely private super intelligence running for me 24/7 I’m telling you right now by end of year we will have a local version of Mythos. It’s 100% guaranteed You called me crazy but every single prediction I’ve made has turned out to be true These models will only get more efficient and require less hardware. But that hardware is only going to get more expensive Local/open source is so obviously the future and if you’re still denying this now you are delusional

@eng_khairallah1 I believe the issue this article doesn’t address is a significant increase in token usage.

@HazelAppleyard A perfect name!

Grown man wants to call himself Flopsy

@JonStewartIL @grok when did this video first air ?

Wait!!!! What???🚨🚨🚨🚨🚨 Everything is stable in Russia! On state television, they claimed to have made contact with aliens The extraterrestrials will come to Earth and establish direct contact with humanity in 2035, they announced on Channel 1. #ufos #uaps

@nocontextmemes He’s gay

@KILLTOPARTY It’s normal now

Is this normal?? LOL

@sudoingX @pupposandro This is fun to imagine, but it is just that imagination. We need real solutions yesterday.

read this carefully anon. @pupposandro wrote a single fused CUDA kernel for all 24 layers of Qwen 3.5-0.8B. one kernel launch. absolutely zero CPU round trips between layers. the result? a $900 RTX 3090 from 2020 hit 411 tok/s. apple's M5 Max hit 229. the 3090 won on speed AND efficiency 1.55x faster than llama.cpp on the same hardware. the gap between NVIDIA and Apple was never about silicon. it was software. generic frameworks waste cycles on kernel launch overhead, memory re fetches, thread synchronization. when you fuse everything into one dispatch the hardware shows what it actually has. this is the beginning of something bigger. we already proved that a 27B dense model on a single 3090 one-shots what $70K enterprise hardware cannot. now imagine what happens when someone writes kernels optimized specifically for the 3090 and the models that run best on it. not generic inference. hardware specific, model specific fused from the kernel level up. the 3090 is not a relic. it's an untapped research platform. and the people writing these kernels are proving it with data. all open source and reproducible anon.

Scientists connected to our most advanced programs are vanishing under suspicious circumstances. I've already sent a letter to the FBI to investigate. We want answers, and we're going to get them.

@BishopMota7272 @squiggle888 @RealPostFolder This is true, nobody can afford to go out to eat let alone pay for another person.

@squiggle888 @RealPostFolder Young women want a rich man, or else they just sleep around or stay single. Young men know this, so many can’t start dating until they become 38-45(when they finally become richer/more stable). It’s virtually impossible to date on $15/hr, especially if your partner is poor.

There's a narrative among women that if a man really wanted to date, he could. This isn't true, most young men would like to date. The harsh truth today is that the average man isn't good enough for the average woman. You can assign blame wherever you want

@reduxx I hope he doesn't kill again, I guess Indiana gets to hold their breath too.

🚨EXCLUSIVE🚨 A trans-identified male convicted of murdering a baby has been quietly released from prison 30 YEARS EARLY. Jonathan "Autumn Cordellioné" Richardson was turned loose in Evansville, Indiana, with no notice given to prosecutors or the public. reduxx.info/exclusive-tran…

@Interstella4L @ItsCompChannel It’s true a reality of online dating.

@ItsCompChannel TLDR

Why do people keep asking why men aren’t dating? Is it gaslighting or can they just not see the writing on the wall?

@PatrickByrne Let’s just hope they don’t live in Canada 🇨🇦

TL;DR 10% of boy who want their cock & balls cut off are suicidal, but afterwards 60% are. 21% of girls who want a piece of their colon made into a smelly cock are suicidal, but after the operation 55% are. Gosh who knew?

@dom_lucre @Kobe_for_3 This is incredible

🔥🚨BREAKING: A local news company put out a report revealing UFOs fly all over the skies above the city Helsinki, Finland in pure crystal clear footage. This can no longer be denied, we are experience a worldwide phenom.

@renoiseai I'd love to give this a try

Launch week special for early supporters — 40% off. Follow @renoiseai + reply "MAKENOISE" and we'll DM you the code.

Don't make videos — program them. Introducing Renoise = Claude Code + Seedance 2.0. Scale your video ad production 100x. One product photo → hundreds of finished creatives.👇 renoise.ai #Renoise #RenoiseAI #CreateWithRenoise #Seedance2

@renoiseai MAKENOISE

@DeanTTraining They also are afraid it will make them a butch lesbian.

This is what women think they’ll look like after lifting weights and eating more protein for a month

@AlexFinn Really wish I could afford/justify one to partner

If you have your OpenClaw working 24/7 using frontier models like Opus, you're easily burning $300 a day. That's $100,000 a year. I have 3 Mac Studios and a DGX Spark running 4 high end local models (Nemotron 3, Qwen 3.5, Kimi K2.5, MiniMax2.5). They're chugging 24/7/365. I spent a third of that yearly cost to buy these computers I'll be able to use them for years for free On top of that they're completely private, secure, and personalized. Not a single prompt goes to a cloud server that can be read by an employee or used to train another model I hope this makes it painfully obvious why local is the future for AI agents. And why America needs to enter the local AI race.