Tech + Local AI Own your weights ⚖️ 4x GB10 - 4x AMD MI50 - 1x 3090ti

Joined May 2026
The only thing that stops a bad guy with an abliterated LLM is a good guy with an abliterated LLM.
29
63
15
639
12,720
Replying to @NVIDIAAI
@NVIDIAAI GB300 🔥
21
3
194
6,976
Absolutely fascinated by this computer stuff. I time travel each time.
1
1
41
14 year old Dells are still being used in prod Hopper GPUs aren’t going anywhere for a while
a year later and I think they may be still running for 20 years the way GPU rental prices are going.
4
2
31
1,128
I told Deepseek V4.1 Flash 1017 to build a exploit that escapes Chrome's V8 Sandbox After 12 hours, it had a multi stage memory corruption exploit that achieves full process read and write.
45
74
11
2,003
111,872
People dunking on this have a kind of Stockholm Syndrome from the difficulty of using computers. Being able to just say what you want or need and have it happen was always the dream of the Computer Revolution. The original pioneers would be elated the difficulty has melted away.
My 12 year old son just made this @Tesla Roadster game from scratch by himself using AI. AI is nuts.
36
66
1
1,765
29,006
The funny thing is everyone was saying AI slop code will cause a cyber crisis but it’s actually all the old human slop causing it and the AI is just cleaning it up
100
599
72
6,338
127,930
This dude MADE UP a story about me after ripping my video pretending I use some second brain grok bot bullshit 😭 I am not affiliated with this guy or his grift I use Hermes on a dual spark cluster and of course it scrapes my email for leads but not through some obsidian BS FFS
25-year-old developer copied 6 years of his emails, client calls and notes, pasted them into Grok Bot and told it to build a brain that thinks exactly like him. 20 minutes later - a complete second brain. Then he boarded a 3-day train across America with no Wi-Fi. In his backpack: a laptop and a $4,000 box the size of a sandwich running a 200B-parameter model. One Ethernet cable between them. The whole brain lived inside that box. Somewhere in Nebraska, zero signal, he typed “what am I forgetting?” It found 3 client follow-ups he’d dropped months ago, the exact price he’d quoted each one, and wrote every reply in his own voice. Sent them at the next station. Two paid before Denver. $6,400 from a train seat with no internet. Then he built a machine. The brain now reads every email and call as it happens, finds him new clients, writes his proposals, makes his decisions and plans his week. Zero cloud, zero subscriptions, nobody ever sees his data. Month one - $6,400 from a train. Month six - it runs his business for him Most people still use AI to fix typos in their emails. A second brain makes you money, remembers everything and solves problems before you even notice them, and almost nobody has built one yet.
1
1
53
A large model Q2 is stronger than a small model Q8.
37
6
2
207
15,662
The guy who gave us QLoRA, says DeepSeek's inference system is on par with OpenAI's stack and better than what Anthropic runs, at least at their scale. Now check the license. Apache 2.0. Until today a production stack at that level existed inside a handful of companies. It was the thing that made their API fast and their margins fat, and none of them ever showed it to anyone. Today any startup, any university, any cloud in any country can download it, read it and run it. It runs on NVIDIA Blackwell and on Huawei Ascend, so it isnt tied to 1 chip vendor either. This is what I mean when I say open weights are about more than downloading a chatbot. DeepSeek is giving away the knowledge that only a few labs had, and that changes who can build an AI company at all. Respect @deepseek_ai
This is a very big deal. DeepSeeks inference system is on par with OpenAIs stack and better what Anthropic is running (at least for their user size).
20
158
8
1,721
57,036
all the cves today were just a taste of ablit 1017 btw
6
6
189
5,637
deepseek v4.1 flash abliterated going live on @morphllm in ~1hr dm me if you want access, it will be application only i feel like this is important to society to serve. idt mythos the correct choice. you need to be playing defense with the same model that's on offense
the recent security incidents are going to 100x the demand for open source models the software security game is now: the side that wins is the one that can deploy the most tokens so every organization will rush to harden their software, the demand for tokens will 100x because if you don’t want to get pwned, you *have* to use ai now
36
10
3
285
19,431
Toying w 5090 placement Will likely swap riser cable. This one only supporting x8. The last pic is a crazy mess. I had to have an extrnl psu for a bit. I was buying ups’s for the new 220v 3kw psu and apparently I can’t read too gud Running: @wrldsuksgo2mars glm5.3 recipe on the 2x 6k’s with the @BrandonMusicKy K4 weights & @MiaAI_lab qwen3.8:27b on the 5090 Everything feels fast af
1
2
84
GLM5.3 Flash is nice! DS 4.1 Flash is supercool! But bro... Strata + Qwen 3.8 Next Flash SPEED... It's addictive.
17
4
232
16,086
Genuinely the greatest purchase I’ve ever made in my life so far has been the Dual-DGX sparks. I’ve had a cybertruck, I’ve bought expensive gear, guns, max cloud subscriptions But local AI has changed my life Free, unlimited, unrestricted private AI forever?? Life changing.
1
1
43
being able to run AI at home is such a nice quality of life upgrade. bank statements, tax forms, governments papers... I can work on all of these without anything leaving the house.
32
12
6
462
33,819
GPUs will keep going up and inference is going to come down to match it at the cheapest power available anywhere, the same as crypto mining
Teortaxes▶️ (DeepSeek 推特🐋铁粉 2023 – ∞)
@teortaxesTexOct 20
Insane alpha, must read, might well redefine this economy. Everything me, Zephyr etc have been saying about the real profitability of the frontier inference is powerfully vindicated
4
5
3
161
5,282
How it feels getting DeepSeek to run on a ddr3 workstation.
Project Maya v1.1.18 is out 🫡 - DeepSeek: faster long prompts on one GPU, smarter use of PCIe - Strix Halo on Windows: decode back to full speed - GLM on Tesla P100 + Responses API - DeepSeek respects anti-repetition settings; steady speed meter github.com/mw00/project-maya…
2
2
23
1,169
Me and Claude
5
28
1
406
6,110
people on here have no idea how behind even the startup bros are
4
4
5
191
9,288