全部 AI 动态

You can now share templates of your Bots with others.

Sakura Bonsai by Hy4 Preview developed using their WorkBuddy client. Prompt is below (big one) I think is from @majidmanzarpour 👇 Thanks for the early access 🙏🏻 @TencentHunyuan @TencentAI_News @WorkBuddy_AI

Big news: Hy4 preview by @TencentHunyuan just landed ~#5 in the Code Arena: WebDev with 1633 pts (AutoEval). This is a significant improvement from Hy3 at #31 overall (+115 pts)! Among open models, Hy4 preview is ~#3, compared to Hy3 at #7. Note: this is an early AutoEval score, in which a Reward Model trained on Arena's human preference data casts automatic votes in place of live votes. We’ll continue to see how scores converge as more live human votes come in. See thread for more info on the methodology behind AutoEval. Congrats to the @TencentHunyuan team on this release!

https://x.com/i/article/2092581577637363712

introducing pcstack (lmao), a way to use pstack in conductor cloud: https://gist.github.com/vincentmvdm/bafa2463be3061e385f0f178ad2d6bac i'm a pstack disciple but also love conductor cloud. this skill teaches my agents how to map pstack's cursor concepts to conductor. install it and make sure pstack is in skills/vendor

https://x.com/i/article/2092581577637363712

We built a patient intake agent with @SpaceXAI that runs end to end on Grok voice models. Grok STT → Grok 4.3 → Grok TTS, cascaded through LiveKit Inference. Three model strings in one AgentSession. No separate API key, no separate billing, ZDR on every hop. Talk to it: https://xai.livekit.space

I don't see anyone pointing out this Grok Bot innovation, but I think it is actually a big deal for mass adoption. How much time have you spent trying to figure out how to securely give your keys to your agent? Most people give up before they figure out how to build and store an .env file for their agent to access and use. Grok Bot's solution is simple, and most important of all, easy!

If you're a visual learner like me, this one's for you! Try `$visualize` in ChatGPT Work/Codex to turn any information into a nice visualization https://www.youtube.com/watch?v=jzmNh8lbSp8

Physical prompting is an elegant idea! One request for the @GeneralistAI team: can we see an example of *physical prompt steerability*, where different prompts induce distinct behavior in the *same* environment? I'm curious whether GEN-1.5 is listening to the physical prompt or simply executing the most likely action sequence for the scene under its pretraining prior.

Big news: Qwen3.8-27B by @Alibaba_Qwen is now #1 among open models in the Image-to-WebDev Arena (#7 overall)! Priced at $0.40/$3 per M input/output tokens, it has shifted the Pareto frontier (more info below). Qwen3.8-27B has 1574 pts with 27B parameters, achieving performance on par with Kimi K3 (Max) at 2.8T parameters! Congrats to @Alibaba_Qwen on this contribution to the open model ecosystem!

Software Factory Design Patterns: 🦄 AI That Works #71 https://x.com/i/broadcasts/1AGRnZYnYNrGl

Simple way to find customers using Grok Bot: 1) Use Grok Bot to search for people on X complaining about competitors or looking for alternatives (“Looking for an alternative to...”) 2) Use the @amplemarket connector to learn more about the person + company, then reach out to the poster or people commenting. 3) Turn it into a Grok Bot routine so you get these buying signals every week. The interesting part: you don’t need to guess whether someone has the problem you're solving. They just publicly told you they do. This feels like extremely low-hanging fruit for founders/sales teams.

I didn't expect to actually use this (Grok Bot)

man I love telling ai to take a large piece of work and break it up into small stacked PRs that you can land individually it lets you build something big quick but then you can do a final pass to make it production ready by focusing on individual pieces in order breaking it up was so much work before