0xSero's banner
0xSero's profile picture

0xSero

@0xSero • 51,738 subscribers

Dad | Open Source | Back to Pleroma | ⵣ https://t.co/aSLDkVhImo

Shorts

Codex nooooooo I can't close this popup

Codex nooooooo I can't close this popup

135,750 views

Asking Codex (GPU) to find and kill Codex (Cerebras)

Asking Codex (GPU) to find and kill Codex (Cerebras)

24,131 views

Videos

LIVE
1.2k

Anya Rossi

sweetdream.ai

SweetDream.aiSponsored•Livecam
Streaming Now

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

HD live stream
Exclusive private shows
1.2k viewers online

Free preview available • Premium content

I yapped about LLM Compression for 40 minutes, how much misinformation did i spread this time (,:
39:49
0xSero's profile picture

I yapped about LLM Compression for 40 minutes, how much misinformation did i spread this time (,:

0xSero

34,805 views • 5 days ago

Vibe coding 101 How I work on 8 projects at a time. Granted right now I use codex app a lot, but this still holds. I might make another video about my codex app setup
24:56
0xSero's profile picture

Vibe coding 101 How I work on 8 projects at a time. Granted right now I use codex app a lot, but this still holds. I might make another video about my codex app setup

0xSero

21,514 views • 4 days ago

Kimi IS COOKING holy mackerel this is way better than anything I can get out of opus or GPT Has some bugs.. but looks soooo unique and well into my brand, for 1 shot I can't complain.
0:41
0xSero's profile picture

Kimi IS COOKING holy mackerel this is way better than anything I can get out of opus or GPT Has some bugs.. but looks soooo unique and well into my brand, for 1 shot I can't complain.

0xSero

235,591 views • 4 months ago

I promise this is the last pleometric video I drop on you.
1:04
0xSero's profile picture

I promise this is the last pleometric video I drop on you.

0xSero

131,544 views • 2 months ago

OAI has to be prioritising low/no thinking GPT-5.5 inference, it's so fast. I think this is better than high thinking, so much less annoying, so much more token efficient.
1:52
0xSero's profile picture

OAI has to be prioritising low/no thinking GPT-5.5 inference, it's so fast. I think this is better than high thinking, so much less annoying, so much more token efficient.

0xSero

65,203 views • 1 month ago

GLM-5.1-478B-NVFP4 Running on: - 4x RTX Pro 6000 - Sglang - 370,000 max tokens (1.75x full context) - p10 27.7 | p90 45.6 tok/s decode (gen) - 1340 tok/s prefill I could get 2x decode if I limit to 64k context (100 tok/s) In this video it operates Figma (:
1:00
0xSero's profile picture

GLM-5.1-478B-NVFP4 Running on: - 4x RTX Pro 6000 - Sglang - 370,000 max tokens (1.75x full context) - p10 27.7 | p90 45.6 tok/s decode (gen) - 1340 tok/s prefill I could get 2x decode if I limit to 64k context (100 tok/s) In this video it operates Figma (:

0xSero

74,772 views • 1 month ago

Finally, full precision MiniMax-M2.7 running at home. 100 tokens/s decode 5050 tokens/s prefill
0:36
0xSero's profile picture

Finally, full precision MiniMax-M2.7 running at home. 100 tokens/s decode 5050 tokens/s prefill

0xSero

71,970 views • 1 month ago

Holy moly, MiniMax-M2.7 is amazing, watch till the end.
3:00
0xSero's profile picture

Holy moly, MiniMax-M2.7 is amazing, watch till the end.

0xSero

110,082 views • 2 months ago

Local AI can be so good, but you’d need about 12k USD to get it. Then it’s not so great Here’s a Q4 of Qwen3.5-262B-REAP Weights 131GB KVCache 50GB 256,000 context 350 tokens/s prefill warmup 4,000 tokens/s prefill cache 36 tokens/s generation Vision enabled REAP is good
3:10
0xSero's profile picture

Local AI can be so good, but you’d need about 12k USD to get it. Then it’s not so great Here’s a Q4 of Qwen3.5-262B-REAP Weights 131GB KVCache 50GB 256,000 context 350 tokens/s prefill warmup 4,000 tokens/s prefill cache 36 tokens/s generation Vision enabled REAP is good

0xSero

87,504 views • 2 months ago

I LOVE Deepseek-v4-flash, incredibly reliable and capable, logical. It's lacking in frontend but I have MiMo for that. I would recommend any company spending 100k+ a year on AI to purchase 8-10~ 6000s and have a few of the works to have them blind test these models for work.
1:13
0xSero's profile picture

I LOVE Deepseek-v4-flash, incredibly reliable and capable, logical. It's lacking in frontend but I have MiMo for that. I would recommend any company spending 100k+ a year on AI to purchase 8-10~ 6000s and have a few of the works to have them blind test these models for work.

0xSero

47,272 views • 1 month ago

I got Zai's GLM models working in Codex App. Fun
0:49
0xSero's profile picture

I got Zai's GLM models working in Codex App. Fun

0xSero

48,123 views • 1 month ago

vllm-studio > claude-desktop officially confirmed
0:44
0xSero's profile picture

vllm-studio > claude-desktop officially confirmed

0xSero

23,206 views • 19 days ago

Let me save you hours of testing frontends. If you're ever working on a front-end, instead of writing tests, and adding puppeteer slop to your repo 1. Get an llm to write you with whatever needs to be tested 2. Copy that, go to browser 3. Open localhost with your selected app 4. Use Claude Chrome Extension or Parchi 5. Send it the prompt 6. QA engineering, there you go. Use models results and pass it back to your coding agent to fix whatever is flagged.
0:42
0xSero's profile picture

Let me save you hours of testing frontends. If you're ever working on a front-end, instead of writing tests, and adding puppeteer slop to your repo 1. Get an llm to write you with whatever needs to be tested 2. Copy that, go to browser 3. Open localhost with your selected app 4. Use Claude Chrome Extension or Parchi 5. Send it the prompt 6. QA engineering, there you go. Use models results and pass it back to your coding agent to fix whatever is flagged.

0xSero

109,697 views • 4 months ago

I figured out how to get Claude working anywhere without extra usage and technically in line with Anthropic's TOS. I don't recommend you adopt this, might get you banned but as you can see, no errors, no extra usage consumed. The point of this is to demonstrate futility.
0:35
0xSero's profile picture

I figured out how to get Claude working anywhere without extra usage and technically in line with Anthropic's TOS. I don't recommend you adopt this, might get you banned but as you can see, no errors, no extra usage consumed. The point of this is to demonstrate futility.

0xSero

51,550 views • 1 month ago

How I am de-slopping my code-bases This feature has made my codebases so much less messy /readiness-report in Droid compares your codebase against best standards and suggests ways to de-slop. 2x speed.
5:21
0xSero's profile picture

How I am de-slopping my code-bases This feature has made my codebases so much less messy /readiness-report in Droid compares your codebase against best standards and suggests ways to de-slop. 2x speed.

0xSero

44,590 views • 2 months ago

I spent an hour chatting with Yacine about education, learning, AI etc.. He has one of the healthiest mindsets around life of anyone I've spoken to. The physical manifestation of you can just do things. Very grateful for your time, Yacine.
58:37
0xSero's profile picture

I spent an hour chatting with Yacine about education, learning, AI etc.. He has one of the healthiest mindsets around life of anyone I've spoken to. The physical manifestation of you can just do things. Very grateful for your time, Yacine.

0xSero

30,773 views • 1 month ago

For my friends with design taste, what do you think? Production ready?
3:59
0xSero's profile picture

For my friends with design taste, what do you think? Production ready?

0xSero

14,472 views • 19 days ago

Qwen3.5-262B-REAP-4bit cleans my Downloads for me in like 2 minutes. Local AI, even 10B param models can be so much more than we know how to harness right now. Intelligence is a spectrum, me and my REAPs are on it.
2:15
0xSero's profile picture

Qwen3.5-262B-REAP-4bit cleans my Downloads for me in like 2 minutes. Local AI, even 10B param models can be so much more than we know how to harness right now. Intelligence is a spectrum, me and my REAPs are on it.

0xSero

32,644 views • 1 month ago

We gotta talk about AGI Sleepy dad day, but I wanted to talk about what I think makes up an "AGI" Local + Hermes + Qwen + MoEs + VLLM + Self hosting I really went into the whole thing.
34:01
0xSero's profile picture

We gotta talk about AGI Sleepy dad day, but I wanted to talk about what I think makes up an "AGI" Local + Hermes + Qwen + MoEs + VLLM + Self hosting I really went into the whole thing.

0xSero

31,944 views • 1 month ago

Trying long form X for the first time. A deeper dive into why Open Source is so important for our industry, I also wanted to walk you through my setup right now. I am not an Academic researcher, I am a tinkerer who happens to have a genius researcher I can guide.
38:24
0xSero's profile picture

Trying long form X for the first time. A deeper dive into why Open Source is so important for our industry, I also wanted to walk you through my setup right now. I am not an Academic researcher, I am a tinkerer who happens to have a genius researcher I can guide.

0xSero

36,543 views • 2 months ago