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。

got opencode working in taugentic, so now i can use glm-5.1 with my coding plan.

Kevin Kern

20,611 subscribers

15,366 次观看 • 4 个月前 •via X (Twitter)

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

another open source win: opencode + GLM 4.6 is basically Claude Code (used it all day) but insanely cheap + better TUI. And you can use it with your Hugging Face token now 🔥

another open source win: opencode + GLM 4.6 is basically Claude Code (used it all day) but insanely cheap + better TUI. And you can use it with your Hugging Face token now 🔥

Victor M

217,717 次观看 • 10 个月前

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

341,710 次观看 • 5 个月前

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.

(Z.ai) is now a model provider inside TRAE. You can BYOK and add GLM-4.6 and GLM-4.5 to TRAE IDE. GLM-4.5 supports up to 128K context and GLM-4.6 expands up to 200K context. Both deliver strong coding and reasoning performance on the benchmark and offers dual “thinking/fast” modes. Available now in the latest version.

TRAE

63,585 次观看 • 9 个月前

OpenCode says it has reached 13M monthly users, 4.6M weekly users and roughly $40M in annualized revenue. Anthropic restricted competing coding tools. OpenCode works with any model, which gives teams a way around building their coding stack on one lab.

OpenCode says it has reached 13M monthly users, 4.6M weekly users and roughly $40M in annualized revenue. Anthropic restricted competing coding tools. OpenCode works with any model, which gives teams a way around building their coding stack on one lab.

Digg

21,282 次观看 • 15 天前

You can now use GLM 5.2 in Omma Canvas. Strong model for frontend generation. Enable it on canvas using the "Higher" mode.

You can now use GLM 5.2 in Omma Canvas. Strong model for frontend generation. Enable it on canvas using the "Higher" mode.

Omma AI

13,059 次观看 • 1 个月前

My reaction when I paid $20 for Claude with limits... and on April 7, GLM-5.1 was released, which tears it up and works for free according to the guide below

My reaction when I paid $20 for Claude with limits... and on April 7, GLM-5.1 was released, which tears it up and works for free according to the guide below

shmidt

529,860 次观看 • 3 个月前

in opencode v0.3.53 we implemented message queuing so you can send a message while opencode is working and it'll update the LLM on the next opportunity - basically lets you resteer it in a different direction should feel pretty natural

in opencode v0.3.53 we implemented message queuing so you can send a message while opencode is working and it'll update the LLM on the next opportunity - basically lets you resteer it in a different direction should feel pretty natural

dax

35,773 次观看 • 1 年前

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

we just released a new blog "Training a coding agent using the OpenCode harness in remote HF sandboxes with TRL and OpenEnv" you can take a real coding agent (OpenCode), let it run its own tool loop against real coding problems, and train it with RL on the exact tokens it produced and every rollout runs in its own remote HF sandbox, so rollouts scale out beyond one machine the loop: - OpenCode owns its tool loop inside an OpenEnv sandbox - an in-sandbox proxy records the real token ids + logprobs, per turn - a hidden-test verifier scores the result, and that is the reward - TRL trains with AsyncGRPO, weights sync back to vLLM over NCCL blog + runnable example:

Sergio Paniego

36,159 次观看 • 3 天前

Poe now supports OpenCode An open-source AI coding terminal that pairs with all major models on Poe. One click login, instant access, no extra configuration. Start building now.

Poe now supports OpenCode An open-source AI coding terminal that pairs with all major models on Poe. One click login, instant access, no extra configuration. Start building now.

Poe

46,041 次观看 • 4 个月前

Truth: AI coding models are good for code execution, but not good at planning. If you let AI plan next step while coding, it will mess up the codebase. You can solve this by attaching a detailed "Implementation Plan" Here's how I create my plan: ↓

Truth: AI coding models are good for code execution, but not good at planning. If you let AI plan next step while coding, it will mess up the codebase. You can solve this by attaching a detailed "Implementation Plan" Here's how I create my plan: ↓

CJ Zafir

64,900 次观看 • 1 年前

Working on some animated wallpapers for my church. I can now say I've written shaders for God now, so that's cool

Working on some animated wallpapers for my church. I can now say I've written shaders for God now, so that's cool

Xor

19,810 次观看 • 1 年前

got my Avalanche🔺 card and now i can finally buy my coffee with crypto!

got my Avalanche🔺 card and now i can finally buy my coffee with crypto!

Ashley

166,959 次观看 • 1 年前

Anyone can now build an internal AI ops tool without coding skill And it only takes minutes to go from idea → working product I just built one with built-in UI, database, AI copilot, and analytics Here’s how:

Anyone can now build an internal AI ops tool without coding skill And it only takes minutes to go from idea → working product I just built one with built-in UI, database, AI copilot, and analytics Here’s how:

Nelly;

32,972 次观看 • 1 年前

this is how it looks in blender so you can see the actual twist bones working! i know some just use 1 twist bone for this but i found it much more natural to use 2 with different influence 🙂‍↕️

this is how it looks in blender so you can see the actual twist bones working! i know some just use 1 twist bone for this but i found it much more natural to use 2 with different influence 🙂‍↕️

𝗞𝗔𝗥𝗜𝗛𝗔 🌘🍀 3D VRoid Artist ☻

42,159 次观看 • 9 个月前

Can anyone help me clear my negative balance so I can overdraft $500 i could really use it my over draft eligibility just got approved $500! My SOL addy for any help!! BkXFsYrArL1i5DpNLYxofGECjZcMCXxP2zV6VBAg7DuC

Can anyone help me clear my negative balance so I can overdraft $500 i could really use it my over draft eligibility just got approved $500! My SOL addy for any help!! BkXFsYrArL1i5DpNLYxofGECjZcMCXxP2zV6VBAg7DuC

YankMyCrank

72,782 次观看 • 11 天前

Now I can watch zosan all day on my working table.

Now I can watch zosan all day on my working table.

Yuu Shishio

30,494 次观看 • 2 年前

Uh, hey... can I use my iPad now? ;-; #Dragon #Dragonart

Uh, hey... can I use my iPad now? ;-; #Dragon #Dragonart

TH

16,737 次观看 • 2 个月前

I use the latest coding agents in a lot of the material for Interface Craft. I wanted everyone to be able to use them, so I reached out to my friends at v0 and Claude who were generous enough to provide every founding member with one month of Pro.

I use the latest coding agents in a lot of the material for Interface Craft. I wanted everyone to be able to use them, so I reached out to my friends at v0 and Claude who were generous enough to provide every founding member with one month of Pro.

joshpuckett

61,976 次观看 • 5 个月前

Finally getting this scene setup in game so that i can use in the new gameplay trailer im working on for next month! #VR #UE4 #indiegame

Finally getting this scene setup in game so that i can use in the new gameplay trailer im working on for next month! #VR #UE4 #indiegame

Dmaw⛅

819,879 次观看 • 3 年前

in the next release of OpenCode desktop you can now see git and branch changes in the review panel

in the next release of OpenCode desktop you can now see git and branch changes in the review panel

nexxel

46,496 次观看 • 4 个月前