Video wird geladen...

Video konnte nicht geladen werden

Beim Laden dieses Videos ist ein Problem aufgetreten. Dies könnte an einem vorübergehenden Netzwerkproblem liegen oder das Video ist möglicherweise nicht verfügbar.

After playing with the Jev hybrid model, I started looking into OpenJev, and started with a halite 1 implementation with: GLM 5.3 Flash + Jev [vs] GLM 5.3 Flash + OpenJev OpenJev is just a 4B model handily defeating Jev (in this tiny silly toy example ofc). Now I'm... show more

Harrison Kinsley

111,122 subscribers

24,797 Aufrufe • vor 4 Tagen •via X (Twitter)

Wissenschaft & Technologie

Anya Rossi• Live Now

Private livecam show

0 Kommentare

Keine Kommentare verfügbar

Kommentare vom Original-Post werden hier angezeigt

Ähnliche Videos

Jev vs GLM 5.3 at chess! Results: ◾ GLM 5.3 won by checkmate in 29 moves ◾ Jev: ~0.3s and <$0.0001 per move ◾ GLM 5.3: ~5.8s and ~$0.008 per move ◾ The whole game cost 24 cents My main takeaway is that it's often useful to use each one to their strengths: ◾ Fast, well-defined classification → specialized models like Jev ◾ Classifications that need reasoning or lookahead → LLMs like GLM 5.3 ◾ Real classification pipelines → hybrid. Jev handles the easy calls, an open model handles the hard ones. The future is multi-model!

Jev vs GLM 5.3 at chess! Results: ◾ GLM 5.3 won by checkmate in 29 moves ◾ Jev: ~0.3s and <$0.0001 per move ◾ GLM 5.3: ~5.8s and ~$0.008 per move ◾ The whole game cost 24 cents My main takeaway is that it's often useful to use each one to their strengths: ◾ Fast, well-defined classification → specialized models like Jev ◾ Classifications that need reasoning or lookahead → LLMs like GLM 5.3 ◾ Real classification pipelines → hybrid. Jev handles the easy calls, an open model handles the hard ones. The future is multi-model!

Hassan

38,792 Aufrufe • vor 7 Tagen

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.

Built a model router with Jev by TypeSafe AI. Jev decides what model fits your request best and the request is sent to that model.

Duncan

116,081 Aufrufe • vor 9 Tagen

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun

i found a way to make UNCENSORED AI AGENT on a RTX 4090 GPU (!!!) with LOCAL 30B model weights this is GLM-4.7-Flash with abliteration, need 24GB VRAM, safety alignment surgically removed from the weights, the model has native tool calling, it actually executes bash, edits files, runs git (1) use ollama to pull weights of GLM > ollama pull huihui_ai/glm-4.7-flash-abliterated:q4_K (2) proxy it to any coding agent via ollama > ollama launch claude --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch codex --model huihui_ai/glm-4.7-flash-abliterated:q4_K > ollama launch opencode --model huihui_ai/glm-4.7-flash-abliterated:q4_K (3) have fun

chiefofautism

342,264 Aufrufe • vor 7 Monaten

HOLY SHIT Omen Alpha finished the full test in just 1h 30m, while GLM 5.3 Flash and GPT 5.6 Luna Max took around 3 hours. Bro, what even is this model?? Are we actually looking at something that could compete with GPT-6 Astra or Fable 5.1?

HOLY SHIT Omen Alpha finished the full test in just 1h 30m, while GLM 5.3 Flash and GPT 5.6 Luna Max took around 3 hours. Bro, what even is this model?? Are we actually looking at something that could compete with GPT-6 Astra or Fable 5.1?

Iam_

39,852 Aufrufe • vor 22 Tagen

free access to 8+ top AI models 😳 APInex is offering free models with 1M context - Gemini 3.8 Flash - Muse Spark 1.3 - GLM 5.3 Flash - Gemini 3.1 Pro - DeepSeek V4 Pro - GPT-5.6 Luna - Qwen 3.8 MAX - DeepSeek V4 Flash getting started: 1. go to 2. sign up with Gmail 3. create your API key 4. base url 5. choose a free model and start using free models, one API setup 👀

free access to 8+ top AI models 😳 APInex is offering free models with 1M context - Gemini 3.8 Flash - Muse Spark 1.3 - GLM 5.3 Flash - Gemini 3.1 Pro - DeepSeek V4 Pro - GPT-5.6 Luna - Qwen 3.8 MAX - DeepSeek V4 Flash getting started: 1. go to 2. sign up with Gmail 3. create your API key 4. base url 5. choose a free model and start using free models, one API setup 👀

K2S

27,390 Aufrufe • vor 19 Tagen

GLM 5.3 is FREE right now and you can actually use it. you can access it through ZenMux with a free API key, and Z. ai is also offering free access rn. you get: - GLM 5.3 - 1M context window - Up to 128K output - Tool calling + MCP - Free API access ZenMux currently lists GLM 5.3 at $0 for both input and output. to get started: > Go to > Create an account > Generate an API key > Use as the base URL > Select z-ai/glm-5.3-free you can also test GLM 5.3 directly at free access can change, so this is worth testing while it’s available

GLM 5.3 is FREE right now and you can actually use it. you can access it through ZenMux with a free API key, and Z. ai is also offering free access rn. you get: - GLM 5.3 - 1M context window - Up to 128K output - Tool calling + MCP - Free API access ZenMux currently lists GLM 5.3 at $0 for both input and output. to get started: > Go to > Create an account > Generate an API key > Use as the base URL > Select z-ai/glm-5.3-free you can also test GLM 5.3 directly at free access can change, so this is worth testing while it’s available

MIKE

42,231 Aufrufe • vor 1 Monat

Working on a new skill where Fable acts as an orchestrator and delegates work to OpenCode subagents running OSS models. It delegates to GLM 5.3 Flash for easier tasks and Kimi K3 for harder tasks, all running on Together AI. GLM 5.3 Flash is 100x cheaper than Fable for output tokens while being pretty good at coding so I'm excited to experiment with how well this works.

Working on a new skill where Fable acts as an orchestrator and delegates work to OpenCode subagents running OSS models. It delegates to GLM 5.3 Flash for easier tasks and Kimi K3 for harder tasks, all running on Together AI. GLM 5.3 Flash is 100x cheaper than Fable for output tokens while being pretty good at coding so I'm excited to experiment with how well this works.

Hassan

35,251 Aufrufe • vor 24 Tagen

You can now use GLM-5.3 Flash completely FREE 😱 GLM-5.3 is now officially out and free on No bank card needed. You can also use Qwen3.8, HY3, MiMo-V2.5 and other models for $0. Setup: 2 mins: > Go to > Create a free account > Pick any model showing 0 credits > Use it in chat or create an API key No official end date yet. Grab it before the free access disappears.

You can now use GLM-5.3 Flash completely FREE 😱 GLM-5.3 is now officially out and free on No bank card needed. You can also use Qwen3.8, HY3, MiMo-V2.5 and other models for $0. Setup: 2 mins: > Go to > Create a free account > Pick any model showing 0 credits > Use it in chat or create an API key No official end date yet. Grab it before the free access disappears.

CDG

13,405 Aufrufe • vor 29 Tagen

Union Alpha is now in Codex!! The speed is insane over 300 to 400 tokens a second, 262k context, images in, and it's free for a week. It's a good timing too, most of the Codex usage is basically gone right now. Zai did this exact thing in August: Ox Alpha showed up unnamed, free for a week, built for agentic coding, and a week later it was GLM-5.3-Flash. So what model do you guys think it is?

Union Alpha is now in Codex!! The speed is insane over 300 to 400 tokens a second, 262k context, images in, and it's free for a week. It's a good timing too, most of the Codex usage is basically gone right now. Zai did this exact thing in August: Ox Alpha showed up unnamed, free for a week, built for agentic coding, and a week later it was GLM-5.3-Flash. So what model do you guys think it is?

Ziwen

98,712 Aufrufe • vor 9 Tagen

I used Jev to classify 1,018 AI research papers. The result: $0.08 total cost and 256ms median end-to-end latency per paper. The pipeline was: 1. Summarize each paper with DeepSeek V4 Flash 2. Send the title + summary + 24 possible topics to Jev 3. Use Jev to classify each paper 4. Visualize everything on The summaries cost $3.99 on Together AI. The classifications cost $0.08 on TypeSafe AI. So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year. I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything. I’m running evals on the Jev classifications before replacing the current ones, but the site is already live:

I used Jev to classify 1,018 AI research papers. The result: $0.08 total cost and 256ms median end-to-end latency per paper. The pipeline was: 1. Summarize each paper with DeepSeek V4 Flash 2. Send the title + summary + 24 possible topics to Jev 3. Use Jev to classify each paper 4. Visualize everything on The summaries cost $3.99 on Together AI. The classifications cost $0.08 on TypeSafe AI. So for just over $4 of inference, I ended up with a pretty useful way to explore the top AI research papers from the past year. I think this is where things are heading: different models for different parts of the workflow, instead of using one model for everything. I’m running evals on the Jev classifications before replacing the current ones, but the site is already live:

Hassan

333,468 Aufrufe • vor 9 Tagen

Xiaomi MiMo-V2.6 Pro vs MiMo-V2.6 Flash, Honestly, I didn’t expect them to be this cheap, The whole test cost me just a few cents and took around an hour From what I’m seeing in my benchmarks, MiMo V2.6 Pro is even doing a bit better than GLM 5.3 in some areas, But the thing that surprised me the most is the efficiency, For the price, this is kinda crazy, Xiaomi is really cooking with these models

Xiaomi MiMo-V2.6 Pro vs MiMo-V2.6 Flash, Honestly, I didn’t expect them to be this cheap, The whole test cost me just a few cents and took around an hour From what I’m seeing in my benchmarks, MiMo V2.6 Pro is even doing a bit better than GLM 5.3 in some areas, But the thing that surprised me the most is the efficiency, For the price, this is kinda crazy, Xiaomi is really cooking with these models

Iam_

18,129 Aufrufe • vor 4 Tagen

DeepSeek-V4.1-Flash is crazy! first time experiencing a model this FAST that’s also this efficient this is what I built in less than a minute with just a simple prompt in Alysis Code

DeepSeek-V4.1-Flash is crazy! first time experiencing a model this FAST that’s also this efficient this is what I built in less than a minute with just a simple prompt in Alysis Code

remakw

20,153 Aufrufe • vor 18 Tagen

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

Also have been playing with TypeSafe AI Jev, insane! So many immediate use cases and new apps are possible. What a time to be a builder! Sharing some experiments here starting with: Keystroke oracle / predictive launcher: Your launcher ranks by aliases, fuzzy match, and habit. Jev reads intent: type "the pdf I just downloaded" and the newest PDF is already the top hit with a full confidence on every keystroke, in ~100 ms

nader dabit

430,743 Aufrufe • vor 8 Tagen

I watched Ox Alpha top OpenRouter for a week with no name on it. Now it's GLM-5.3-Flash, and four platforms still give it away FREE: > MIT weights, self-host. 320B, runs on multi-GPU > free coding tier, 1M tokens/day, 500 requests > free API, no card. Full 320B model at $0 > official chat from the lab that built it The stealth preview ended. The free access didn't.

I watched Ox Alpha top OpenRouter for a week with no name on it. Now it's GLM-5.3-Flash, and four platforms still give it away FREE: > MIT weights, self-host. 320B, runs on multi-GPU > free coding tier, 1M tokens/day, 500 requests > free API, no card. Full 320B model at $0 > official chat from the lab that built it The stealth preview ended. The free access didn't.

ＺＥＦＩ

16,114 Aufrufe • vor 1 Monat

Got DeepSeek V4 Flash running on 2x H200s at 160–200 tok/s on JarvisLabsAI this speed is perfect for in the loop things I do with these agents. It feels like a GLM-5.2-class model with much lower hardware requirements. I’m going to daily-drive it for a bit and see how it performs, but first impressions are really good.

Got DeepSeek V4 Flash running on 2x H200s at 160–200 tok/s on JarvisLabsAI this speed is perfect for in the loop things I do with these agents. It feels like a GLM-5.2-class model with much lower hardware requirements. I’m going to daily-drive it for a bit and see how it performs, but first impressions are really good.

Atharva Ingle

21,925 Aufrufe • vor 1 Monat

Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.07 in inference costs: - $0.068 from Kimi K3 on Together AI - $0.003 (1/3 of a cent) from Jev on TypeSafe AI. I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM. I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.

Jev + Kimi K3 for fraud detection! TLDR: Jev classified 100 emails in 1.42 seconds, then I routed the uncertain cases to Kimi K3. The full pipeline got 96/100 correct for only ~$0.07. Video is not sped up, check out the live run! Here was my process: I gave Jev 100 emails to classify (a mix of 50 legit & 50 fraudelent emails). It classified all of them in 1.42 seconds. An underrated feature about Jev is it will give you the confidence score for a classification, so I routed any prediction under 95% confidence to Kimi K3 to be fully sure. 31 emails fell below that threshold. After routing those to Kimi K3, the combined pipeline reached 96% accuracy. The full run took 16 seconds & ~$0.07 in inference costs: - $0.068 from Kimi K3 on Together AI - $0.003 (1/3 of a cent) from Jev on TypeSafe AI. I think this is a really interesting pattern: use a fast specialized model like Jev for the narrow task, then route the uncertain cases to a larger LLM. I feel like this kind of approach could be a game changer for use cases like fraud or anything realtime. You can use the speed & low cost of Jev while having a larger LLM as a fallback to ensure high accuracy.

Hassan

59,800 Aufrufe • vor 9 Tagen

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)

this is the best trick to maximum usage limits on chatgpt codex codex's best kept secret is that your main agent doesn't have to do everything... custom agents are just files in ~/.codex/agents, and one file gives you a second worker on deepseek v4 flash > create ~/.codex/agents/deepseek-worker.toml > set model = "opencode-go/deepseek-v4-flash" with model_reasoning_effort = "max" > keep it bounded: one task packet, no scope creep, report back ```toml name = "deepseek_worker" description = "bounded implementation, testing, and cleanup on deepseek v4 flash" model = "opencode-go/deepseek-v4-flash" model_reasoning_effort = "max" ``` then @ deepseek_worker in the composer... your root agent plans while the worker ships the implementation planning on the main model, execution on the flash lane... that's the whole trick (we run this exact file, last i checked it keeps the heavy turns off the main thread)

Avid

49,981 Aufrufe • vor 1 Monat

You can now use GPT 5.5, Gemini 3.7 Flash, Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.

You can now use GPT 5.5, Gemini 3.7 Flash, Kimi K3 and 47 other AI models completely free😱 No subscription. No credit card. Even the API usage costs $0. AIHubMix just opened a free catalog with 50 AI models. Some of the available models: • Ox Alpha • Gemini 3.7 Flash • GLM 5.2 • Kimi K3 • MiniMax M3 • GPT 5.5 • 40+ more And you don’t need separate API keys for each model. Setup takes 2 minutes: > Step 1: Go to > Create an account using your email or OAuth. No card needed. Step 2: Create one API key > The same key works with every free and paid model. Step 3: Add it to any OpenAI-compatible tool Base URL: Then choose any model ending in -free, such as: coding-glm-5.2-free gpt-5.5-free That’s it. One API key. 50 AI models. $0 for both input and output. Save this. You might need a free multi-model setup later.

CDG

15,388 Aufrufe • vor 1 Monat

🐐 Gemini 3 Pro GA One shot prompt is in comment with the codepen link I repeat no model in this entire world able to implement this level of physics and spatial reasoning Not even Opus 4.6 and Gpt-5.3 codex , this is like a generation gap Sub Woofer submitted this

🐐 Gemini 3 Pro GA One shot prompt is in comment with the codepen link I repeat no model in this entire world able to implement this level of physics and spatial reasoning Not even Opus 4.6 and Gpt-5.3 codex , this is like a generation gap Sub Woofer submitted this

Chetaslua

35,579 Aufrufe • vor 7 Monaten

I was super intrigued when I noticed that JEV returns not just probs for candidate choices, but also a CONFIDENCE SCORE of it's prediction... I was wondering if TypeSafe AI brought back Bayesian Networks or something to learn uncertainty. Turns out - NO. Acc to their docs, confidence is just a derived metric from the classification scores. It carries ZERO extra information. Their demo page shows: confidence = (3 × largest probability − 1) / 2 Confidence is tightly coupled with the classification scores it is measuring the uncertainty for. There is no magic here. The model can produce high probability on a wrong choice and just be confidently wrong.

I was super intrigued when I noticed that JEV returns not just probs for candidate choices, but also a CONFIDENCE SCORE of it's prediction... I was wondering if TypeSafe AI brought back Bayesian Networks or something to learn uncertainty. Turns out - NO. Acc to their docs, confidence is just a derived metric from the classification scores. It carries ZERO extra information. Their demo page shows: confidence = (3 × largest probability − 1) / 2 Confidence is tightly coupled with the classification scores it is measuring the uncertainty for. There is no magic here. The model can produce high probability on a wrong choice and just be confidently wrong.

AVB

66,354 Aufrufe • vor 6 Tagen