0xSero's banner

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 次观看

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

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

24,131 次观看

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

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

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

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

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

34,805 次观看 • 5 天前

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

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

21,533 次观看 • 4 天前

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.

235,591 次观看 • 4 个月前

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

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

131,544 次观看 • 2 个月前

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.

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.

65,217 次观看 • 1 个月前

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 (:

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 (:

74,772 次观看 • 1 个月前

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

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

71,970 次观看 • 1 个月前

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

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

110,082 次观看 • 2 个月前

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

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

87,504 次观看 • 2 个月前

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.

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.

47,272 次观看 • 1 个月前

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt

Deepseek-V4-Flash helping me setup Nvidia's Dynamo for disaggregated inference. I have really gotten this model to be a daily driver now. It's really strong at agentic workflows and a decent programmer. For all my side stuff, it's local deepseek now Claude sub cancelled wdyt

24,373 次观看 • 19 天前

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

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

48,123 次观看 • 1 个月前

vllm-studio > claude-desktop officially confirmed

vllm-studio > claude-desktop officially confirmed

23,206 次观看 • 19 天前

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.

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.

109,697 次观看 • 4 个月前

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.

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.

51,550 次观看 • 2 个月前

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.

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.

44,590 次观看 • 2 个月前

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.

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.

30,773 次观看 • 1 个月前

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

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

14,472 次观看 • 19 天前

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.

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.

32,644 次观看 • 1 个月前

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.

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.

31,944 次观看 • 1 个月前