正在加载视频...

视频加载失败

加载此视频时出现问题。这可能是由于临时网络问题，或视频可能不可用。

Okay… DeepSeek V4 Flash actually COOKED 😭 With OpenCode, I’d place it around GPT-5.6 Terra Max—and definitely above Luna Max in this test. Almost unlimited usage for around €9, by the way. This model is a MASSIVE success. Just don’t use the wrong harness.

OmedTheVibeCoder

1,221 subscribers

35,417 次观看 • 1 个月前 •via X (Twitter)

科学技术游戏

Anya Rossi• Live Now

Private livecam show

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

DeepSeek V4 Flash completely failed this test. Compared to Opus 4.8, GPT-5.6 Sol, Kimi K3, and the other current top models, it’s honestly not good. The gap is massive. Against Luna, however, it performs similarly well. Both have different strengths and weaknesses, so I still need to test them more. The weird part: the Pi harness performed worse than OpenCode for DeepSeek. More tests are coming, guys. Don’t worry

OmedTheVibeCoder

26,166 次观看 • 1 个月前

GLM 5.3, GPT 5.6 Luna, Claude Opus 5, Grok 4.6, DeepSeek V4, Kimi K3, and a cloud browser for agents - all FREE. > DuckDuckGo: GPT 5.6 Luna and older models, no signup: > LM Arena: free side-by-side, Opus 5, GPT-5.6 Sol, Grok 4.6, Qwen 3.8 Max: > Nvidia NIM: Kimi K3 free, 40 requests/minute: > OpenCode: 7 free models including DeepSeek V4 Flash, no API key: > Bright Data: 5K credits/month, cloud browser, MCP for agents: Anthropic just dropped Fable 5.1 today - new benchmark leader. Meanwhile the free tier keeps growing. The gap between paid and open keeps shrinking.

GLM 5.3, GPT 5.6 Luna, Claude Opus 5, Grok 4.6, DeepSeek V4, Kimi K3, and a cloud browser for agents - all FREE. > DuckDuckGo: GPT 5.6 Luna and older models, no signup: > LM Arena: free side-by-side, Opus 5, GPT-5.6 Sol, Grok 4.6, Qwen 3.8 Max: > Nvidia NIM: Kimi K3 free, 40 requests/minute: > OpenCode: 7 free models including DeepSeek V4 Flash, no API key: > Bright Data: 5K credits/month, cloud browser, MCP for agents: Anthropic just dropped Fable 5.1 today - new benchmark leader. Meanwhile the free tier keeps growing. The gap between paid and open keeps shrinking.

ＺＥＦＩ

29,454 次观看 • 20 天前

Codex users: here's an amazing way to take advantage of the efficiency and capability of GPT-5.6 Luna Max. It's called 'sol-advisor'. 1. GPT-5.6 Sol High as orchestrator 2. GPT-5.6 Luna Max as implementer for routine tasks 3. GPT-5.6 Terra Max as implementer for complex tasks 4. Fresh GPT-5.6 Sol instance as reviewer A free and open-source plugin for Codex. Installation instructions below 👇 I dare you to install it, and tell me if you hit your weekly usage limits using 'sol-advisor'. I doubt you can.

Codex users: here's an amazing way to take advantage of the efficiency and capability of GPT-5.6 Luna Max. It's called 'sol-advisor'. 1. GPT-5.6 Sol High as orchestrator 2. GPT-5.6 Luna Max as implementer for routine tasks 3. GPT-5.6 Terra Max as implementer for complex tasks 4. Fresh GPT-5.6 Sol instance as reviewer A free and open-source plugin for Codex. Installation instructions below 👇 I dare you to install it, and tell me if you hit your weekly usage limits using 'sol-advisor'. I doubt you can.

Dan McAteer

692,061 次观看 • 1 个月前

GPT-5.6 LUNA AND DEEPSEEK V4 FLASH ARE BOTH FREE RIGHT NOW -- ONE IN A CHATBOT, THE OTHER IN A BROWSER IDE • ChatGPT, the chatbot > GPT-5.6 Luna is now the default on Free and Go: > Unlimited text chats and a Think button land next week. • MonkeyCode, the browser IDE > 30M tokens a day, resets daily, no card: > DeepSeek V4 Flash, Qwen, GLM, Kimi and MiniMax behind it. > Cloud workspace at 1 vCPU and 4GB, nothing to install. Luna posts 62% fewer factual errors than the model it replaces. MonkeyCode is open source from Chaitin and runs on their cloud, so aim it at side projects. One is live today -> The other arrives next week.

GPT-5.6 LUNA AND DEEPSEEK V4 FLASH ARE BOTH FREE RIGHT NOW -- ONE IN A CHATBOT, THE OTHER IN A BROWSER IDE • ChatGPT, the chatbot > GPT-5.6 Luna is now the default on Free and Go: > Unlimited text chats and a Think button land next week. • MonkeyCode, the browser IDE > 30M tokens a day, resets daily, no card: > DeepSeek V4 Flash, Qwen, GLM, Kimi and MiniMax behind it. > Cloud workspace at 1 vCPU and 4GB, nothing to install. Luna posts 62% fewer factual errors than the model it replaces. MonkeyCode is open source from Chaitin and runs on their cloud, so aim it at side projects. One is live today -> The other arrives next week.

slash1s

33,804 次观看 • 1 个月前

Timelapse #177 (14 hrs) - Picked up an RTX Pro 6000 Blackwell and wired in another 1000W PSU - running two of them now - DeepSeek v4 Flash running locally on both GPUs - Distilling DeepSeek v4 Flash down into Nanbeige (still cooking) - Kernel bench runs for DeepSeek v4 Flash and Qwen 3.8 Max - Got it into chat but couldn't reliably get it into the OMP harness yet - Private contract work - days like this are stuff I actually want to build. and when it's the high-intensity grind, i still have to show up and get it done

Timelapse #177 (14 hrs) - Picked up an RTX Pro 6000 Blackwell and wired in another 1000W PSU - running two of them now - DeepSeek v4 Flash running locally on both GPUs - Distilling DeepSeek v4 Flash down into Nanbeige (still cooking) - Kernel bench runs for DeepSeek v4 Flash and Qwen 3.8 Max - Got it into chat but couldn't reliably get it into the OMP harness yet - Private contract work - days like this are stuff I actually want to build. and when it's the high-intensity grind, i still have to show up and get it done

Elliot Arledge

17,401 次观看 • 1 个月前

My Codex weekly limit just reset.. This time Sol doesn't get to touch the actual work. It plans, it verifies, it spawns the agents, that's it. Luna at max effort and DeepSeek do the grinding. We're running Luna from two places at once, the $10 OpenCode Go sub and the Codex plan Luna barely moves the meter. Sol is what drains weekly usage. Setup video below for getting DeepSeek into Codex

My Codex weekly limit just reset.. This time Sol doesn't get to touch the actual work. It plans, it verifies, it spawns the agents, that's it. Luna at max effort and DeepSeek do the grinding. We're running Luna from two places at once, the $10 OpenCode Go sub and the Codex plan Luna barely moves the meter. Sol is what drains weekly usage. Setup video below for getting DeepSeek into Codex

Ziwen

38,411 次观看 • 1 个月前

Codexers: Multi-agent v2 now supports GPT-5.6 Luna. You can use Luna Max as a native sub-agent in Codex and benefit from the incredible price/performance ratio. 'sol-advisor' just shipped support for this. Free and open-source 👇

Codexers: Multi-agent v2 now supports GPT-5.6 Luna. You can use Luna Max as a native sub-agent in Codex and benefit from the incredible price/performance ratio. 'sol-advisor' just shipped support for this. Free and open-source 👇

Dan McAteer

92,826 次观看 • 1 个月前

DeepSeek v4 Flash experimental with vision running (fast) on an m5 max computer and analyzing an image. The implementation for Metal / CUDA / ROCm is finished, just doing the last tests today before releasing it.

DeepSeek v4 Flash experimental with vision running (fast) on an m5 max computer and analyzing an image. The implementation for Metal / CUDA / ROCm is finished, just doing the last tests today before releasing it.

antirez

60,229 次观看 • 21 天前

DeepSeek V4.1 Flash just dropped, and holy shit this thing is fast,I’m getting almost 400 t/s in my video tests. The speed is honestly crazy, I’m running my own benchmark right now and I’ll share all the results once I’m done. You just need to go to the DeepSeek harness and use deepseek-v4.1-flash-expires-on-0910. Speed wise, it’s actually competing with Muse Spark 1.3!

DeepSeek V4.1 Flash just dropped, and holy shit this thing is fast,I’m getting almost 400 t/s in my video tests. The speed is honestly crazy, I’m running my own benchmark right now and I’ll share all the results once I’m done. You just need to go to the DeepSeek harness and use deepseek-v4.1-flash-expires-on-0910. Speed wise, it’s actually competing with Muse Spark 1.3!

Iam_

102,575 次观看 • 14 天前

this is f*cking gold HOW TO USE GPT6-ASTRA & Fable 5.1 FOR FREE Based on my tests, this is definitely the genuine 100% version of the Astra: > ultra-fast performance > a large number of tokens > not many people How to get: 1. go to: 2. log in via Gmail or GitHub 3. get API key 4. start using Other available models: Qwen3.8 27B, DeepSeek V4 Flash, GPT-5.6 Luna, Claude Fable 5.1, GPT-6 Astra and many other..

this is f*cking gold HOW TO USE GPT6-ASTRA & Fable 5.1 FOR FREE Based on my tests, this is definitely the genuine 100% version of the Astra: > ultra-fast performance > a large number of tokens > not many people How to get: 1. go to: 2. log in via Gmail or GitHub 3. get API key 4. start using Other available models: Qwen3.8 27B, DeepSeek V4 Flash, GPT-5.6 Luna, Claude Fable 5.1, GPT-6 Astra and many other..

kaize

32,778 次观看 • 17 天前

You can use GPT 6 Astra, 5.6 Luna totally for FREE This is one of the easiest methods in recent times, all you need is a Discord account. You can get access to: - GPT 5.6 Luna - Claude Sonnet 4.6 - DeepSeek V4 Flash - GPT 6 Astra and many others.. How to get: 1. go to: 2. create an account 3. claim $50 4. invite friend and earn more In addition, you can get $10 for free every day to use. Based on my tests so far, there aren't many people online, and everything is running very quickly.

You can use GPT 6 Astra, 5.6 Luna totally for FREE This is one of the easiest methods in recent times, all you need is a Discord account. You can get access to: - GPT 5.6 Luna - Claude Sonnet 4.6 - DeepSeek V4 Flash - GPT 6 Astra and many others.. How to get: 1. go to: 2. create an account 3. claim $50 4. invite friend and earn more In addition, you can get $10 for free every day to use. Based on my tests so far, there aren't many people online, and everything is running very quickly.

kaize

22,968 次观看 • 14 天前

I replaced my $200/mo chatgpt with this $10/mo setup the setup: opencode go ($10/mo) + deepseek harness ($0/mo) deepseek harness just crossed 106,000+ stars in just 45 hours so this guy mapped the entire deepseek-v4 agentic workflows into 9 diagrams → the council, the assembly line, the skeleton crew, the orchestrator, the tracker + the 4 optional builds →every one flow-mapped, numbered, editable in excalidraw → each paired with the exact cordis rows that run it and the check that proves it worked plus this is all free. send all the screenshots to your AI agents... that's the new workflow

I replaced my $200/mo chatgpt with this $10/mo setup the setup: opencode go ($10/mo) + deepseek harness ($0/mo) deepseek harness just crossed 106,000+ stars in just 45 hours so this guy mapped the entire deepseek-v4 agentic workflows into 9 diagrams → the council, the assembly line, the skeleton crew, the orchestrator, the tracker + the 4 optional builds →every one flow-mapped, numbered, editable in excalidraw → each paired with the exact cordis rows that run it and the check that proves it worked plus this is all free. send all the screenshots to your AI agents... that's the new workflow

Avid

51,723 次观看 • 1 个月前

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each

Pi Agent vs OpenCode token usage A lot of people recommended Pi Agent so I decided to check Pi Agent took 1.1k tokens in first turn OpenCode took 11.5k Setup: 1) Trimmed OpenCode (from usual 30k first turn to 11.5k) - 0 MCPs - 2 lightweight plugins (opencode-env-protect and openslimedit) - 8k char AGENTS.md - 11585 deepseek-v4-flash input tokens - for $0.0016 2) Vanilla Pi - 0 MCPs - 0 system prompt - 8k char AGENTS.md - 1114 kimi-k2.6 input tokens - for $0.0008 I think using better models with capped tokens per turn can keep usage nearly the same as uncontrolled DeepSeek V4 Flash? The challenge now is finding the sweet spot. Can't cap tokens if quality drops. We'll see. Video below - OpenCode vs Pi side by side "say hi back" first turns test, with OpenCode Go usage for each

raymel 👋

209,100 次观看 • 4 个月前

🚨 Deepseek V4 pro GA is being tested to few users > this is the output on the same prompt that was used for kimi k3 and GPT sol 5.6 in the quoted video > The details are solid , addition of tents , campfire and everything this model looks promising

🚨 Deepseek V4 pro GA is being tested to few users > this is the output on the same prompt that was used for kimi k3 and GPT sol 5.6 in the quoted video > The details are solid , addition of tents , campfire and everything this model looks promising

Chetaslua

172,573 次观看 • 2 个月前

This test shows clearly why GPT 5.6 Sol wins I asked the simplest prompt ever : > Create a gmail clone, the nearest possible to the real gmail ui You can see the result, GPT 5.6 Sol and Fable make a 100% perfect But here's the price difference: → GPT 5.6 Terra: $1.04 - 8 minutes → GPT 5.6 Luna: $0.44 - 10 minutes → GPT 5.6 Sol: $6.72 - 20 minutes → Claude Fable 5: $25.09 - 40 minutes Fable is 3.7x more expensive than Sol for "the same result"

This test shows clearly why GPT 5.6 Sol wins I asked the simplest prompt ever : > Create a gmail clone, the nearest possible to the real gmail ui You can see the result, GPT 5.6 Sol and Fable make a 100% perfect But here's the price difference: → GPT 5.6 Terra: $1.04 - 8 minutes → GPT 5.6 Luna: $0.44 - 10 minutes → GPT 5.6 Sol: $6.72 - 20 minutes → Claude Fable 5: $25.09 - 40 minutes Fable is 3.7x more expensive than Sol for "the same result"

Melvyn • Builder

22,254 次观看 • 2 个月前

Opus 5 High might be the most ridiculous model I’ve ever tested. It produced this result in around ONE HOUR. Fable 5 needed almost 3 hours. GPT-5.6 Sol worked for over an hour and still created almost nothing compared to this. Opus 5 didn’t just win. It completely OUTCLASSED them.

Opus 5 High might be the most ridiculous model I’ve ever tested. It produced this result in around ONE HOUR. Fable 5 needed almost 3 hours. GPT-5.6 Sol worked for over an hour and still created almost nothing compared to this. Opus 5 didn’t just win. It completely OUTCLASSED them.

OmedTheVibeCoder

39,729 次观看 • 1 个月前

Been giving my M3 Ultra Studio some love and tinkering with MLX. Started the afternoon at 42 tok/s. Now: 73 tok/s, and there’s still more on the table. Running Qwen3.8-Flash-Next @ 4-bit locally. Now for the crazy bit: Artificial Analysis Intelligence Index v4.3: GPT-5.6 Sol 39 (Medium) GPT-5.6 Sol 42 (High) Qwen3.8-Flash-Next 42 GPT-5.6 Sol 44 (XHigh) GPT-5.6 Sol 47 (Max) Grok 4.5 39 (High) Claude Sonnet 5 38 (Max) *Qwen score currently estimated by Artificial Analysis. A 4-bit open-weights model running at 73 tok/s on a Mac under my desk... with an estimated intelligence score matching GPT-5.6 Sol at High reasoning. Local AI is getting ridiculous. 🔥 Plus, this model does not say no to a bit of red teaming. Once I am happy with it, I will do a pr for Jun Kim's oMLX :)

Been giving my M3 Ultra Studio some love and tinkering with MLX. Started the afternoon at 42 tok/s. Now: 73 tok/s, and there’s still more on the table. Running Qwen3.8-Flash-Next @ 4-bit locally. Now for the crazy bit: Artificial Analysis Intelligence Index v4.3: GPT-5.6 Sol 39 (Medium) GPT-5.6 Sol 42 (High) Qwen3.8-Flash-Next 42 GPT-5.6 Sol 44 (XHigh) GPT-5.6 Sol 47 (Max) Grok 4.5 39 (High) Claude Sonnet 5 38 (Max) *Qwen score currently estimated by Artificial Analysis. A 4-bit open-weights model running at 73 tok/s on a Mac under my desk... with an estimated intelligence score matching GPT-5.6 Sol at High reasoning. Local AI is getting ridiculous. 🔥 Plus, this model does not say no to a bit of red teaming. Once I am happy with it, I will do a pr for Jun Kim's oMLX :)

Ash Hart

18,827 次观看 • 13 天前

🚨 The Sims one shotted by GPT-5.6 Pro this is without codex or any coding harness , one shot entire game with logic in 48 minutes, all in one .html file. cc : Mirochill for the test roon when we can have big model taste and personality ? like after GPT 5 its so robotic

🚨 The Sims one shotted by GPT-5.6 Pro this is without codex or any coding harness , one shot entire game with logic in 48 minutes, all in one .html file. cc : Mirochill for the test roon when we can have big model taste and personality ? like after GPT 5 its so robotic

Chetaslua

144,849 次观看 • 3 个月前

Discovered Materials' Akash Ramdas reveals a hilarious GPT 5.6 Terra hallucination: the model saw the materials science term "relaxation" and just gave up, writing about wanting to take some time off "I have a favorite example from a benchmark on this. We use terms like relaxation and screening. Screening's like to screen out properties. Relaxation is when you let the atoms go to their local favorite positions." "Our friend GPT 5.6 Terra read this and gave up with a blurb about how it wanted to relax and take some time off." "So yes, hallucination is an issue. But we're still excited by how you can build these frameworks around them to guide them to actually do good research."

Discovered Materials' Akash Ramdas reveals a hilarious GPT 5.6 Terra hallucination: the model saw the materials science term "relaxation" and just gave up, writing about wanting to take some time off "I have a favorite example from a benchmark on this. We use terms like relaxation and screening. Screening's like to screen out properties. Relaxation is when you let the atoms go to their local favorite positions." "Our friend GPT 5.6 Terra read this and gave up with a blurb about how it wanted to relax and take some time off." "So yes, hallucination is an issue. But we're still excited by how you can build these frameworks around them to guide them to actually do good research."

MTS

13,992 次观看 • 1 个月前

This completely changes how I look at AI benchmarks. Qwen 3.8 Max Preview felt nearly unusable in OpenCode and Qwen Code. With the Claude Code harness, it suddenly came surprisingly close to Kimi K3 and Fable 5. Same model. Same task. Different harness. Wildly different result. How is this even possible?

This completely changes how I look at AI benchmarks. Qwen 3.8 Max Preview felt nearly unusable in OpenCode and Qwen Code. With the Claude Code harness, it suddenly came surprisingly close to Kimi K3 and Fable 5. Same model. Same task. Different harness. Wildly different result. How is this even possible?

OmedTheVibeCoder

30,223 次观看 • 2 个月前