LBan (@LBan2049) profile picture

Frontend engineer exploring AI-native tooling. Building agent-driven workflows and structured systems that actually ship. LBAN AI: https://teapawt.org/t.co/Ih5bFEL3jy

Joined September 2015
Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)Photo by LBan (@LBan2049)
Gemini AI Pro 感觉不太经用,使用 Neon 做主对话,操作 HyDrogen 干活,一天蹬完了两个号的额度。
1
53
Gemini 这次真的站起来了,而且通过昨天的漏洞,在大家免费体验之后,把胃口都吊起来了,在多地方看到有人在考虑如何真的付费订阅,但是土区之前的价格没了,但是价格锚定大家的心理价位,很难接受原价去订阅,只能再等后面是否有类似的价格了
66
Google 这次羊毛简直像是一次高级营销活动,免费试用种草,现在好多人想付费了
13
这两天有关注大 V 的一点思考,如果这个大 V 没有使用 AI 做出自己的业务,或者做出能产生收益的产品,那他做的东西只能说是 demo 级别的,基本可以认为他是通过 AI 做自媒体,你可以通过他了解最新的 AI 资讯,但是不要指望学到能实际落地的技术,毕竟他自己都没做到
1
31
最近 Gemini 模型口碑又变得很好了,这样轮转其实挺好的,避免一家完全领先,慢慢就会降额度或者涨价,还是要充分的去竞争,消费者多获益,哈哈哈
20
垂直 Agent 可能会蛮有意思的,在一个小的领域做的比通用 Agent 回答的更好,用户还是愿意使用,需要有特有的数据,或者特有的服务。
18
不知道是不是 T3 的原因,在里面使用 CodeX ,一个任务没跑完,用完了两个五小时额度,是的,我不会再订 Plus 会员了
28
现在模型的能力缺失提升了很多,有很多操作都可以替代人工操作,国内社交媒体、电商平台对自动化操作检查很严格,但是很多外围的业务系统基本是不限制的,比如抖音店铺管理后台,以后 ERP 系统,基本不会限制,之前人工操作的现在我都会尝试让 AI 去操作,可能会慢一点,但是人可以空出时间做别的事情
1
44
重置对 Plus 用户来说完全没有意义,因为 5 小时限制的存在,当你的额度快用完的时候,差不多一周的时间也快过去了,完全没有使用重置的动力。
It’s been a while without resets. Maybe I should come back out of the basement
32
从目前的结果看,deeepseek 在价格和通过率上已经赢得了比赛,配合 pi 使用最佳
We’re spending up to 100B tokens across 26,040 agent runs to answer one question: when you switch models, should you switch harnesses too? Our v1.0 FrontierHarness leaderboard ranked harnesses on a single model. V1.1 expands it to 21 harnesses × 5 models × 62 tasks × 4 attempts, 72x the size of v1.0. Results are coming in live. Link below🧵
28
We’re spending up to 100B tokens across 26,040 agent runs to answer one question: when you switch models, should you switch harnesses too? Our v1.0 FrontierHarness leaderboard ranked harnesses on a single model. V1.1 expands it to 21 harnesses × 5 models × 62 tasks × 4 attempts, 72x the size of v1.0. Results are coming in live. Link below🧵
91
65
75
664
496,959
今天体验使用 T3 来真实处理几个任务,感受下来缺失体验不错,可以选择多个 Agent 工具,相当于套了一层壳,GUI 做的体验也不错,通过中继服务在手机上可以同步处理,未来几天准备继续重度使用体验下。 不过好像有 BUG ,电脑端使用 Pi 处理的任务在手机端看不到。
42
T3 有这么厉害吗,还是最近推广比较多
9
这也行?
Погані новини для плиточників, які сміялись з АІ та роботів
15
最近在尝试制作一些 AI 视频的时候,上来遇到的问题就是需要考虑生成什么风格的视频,然后再去生成相应的参考图,这样生成出来的视频会比较符合自己的预期。 为了更好的挑选自己喜欢的风格,我做了一个风格图鉴的站点,可以查看多个视频风格,可以方便的创建风格一致的参考图 styles.lbanai.com/
🤖 Made with AI
2
37
Meet Gemini Omni 1.2 Flash ⚡️ We’ve made the model more cost-effective, bumped the video generation and editing limit up to 15 seconds, and made updates to how scenes hold together over time. We've also given character speech an upgrade, reduced visual glitches like jump cuts, and made sure the model stays even truer to any reference assets you upload. So… what does all of that actually mean for you? It gives you more room to tell your story. With up to 15 seconds to work with, you have more flexibility to create what you need — videos look more cinematic and smooth, offering stronger consistency that keeps objects anchored from start to finish. And when characters speak, the dialogue sounds more fluid and natural. Creators and everyday users can start directing scenes and multi-turn edits in @FlowbyGoogle, generating 15-second clips at no additional cost in Google Vids, or creating 15-second videos in the @GeminiApp. Plus, for developers and businesses building with the API, we've dropped the price by 30% from the previous generation, making it available at just $0.07 per second for 720p video. Watch the model in action as it turns a single style frame into a 4-shot, 15-second macro science explainer of a living beehive ↓
163
244
147
2,571
340,342
通过 Hermes 几乎自动完成了我的首个表情包的制作和上传,提供了想法,最近比较火的“大肥鱼”这个梗,形象做了一些改造,生图使用的 CodeX,感觉效果还不错。
40
之前用Herdr一直没有特别大的感觉,总觉得只是一个管理更方便的终端工具。今天才发现,其实它更强大的一个能力是可以让Agent自己去做窗口管理、派发任务、编排其他的Agent,不只是一个简单的终端管理工具。
81
可以生成动图了,再进一步就是视频了,感觉 OpenAI 最终还是会拾回视频模型的
Images, upgraded—introducing ChatGPT Images 2.6. Now with GIFs and reference images. Plus, two new models are coming to the API with 50% faster image generation.
9
效果真好
AI models can change through long-term refinement and consistent creative direction. Take this image, for example. It was generated entirely by ChatGPT, yet somehow, it doesn’t quite look like a typical ChatGPT image. Over time, through countless experiments, adjustments and a clear artistic vision, I’ve gradually pushed its output closer to my own aesthetic. Perhaps the real art of AI creation isn’t simply learning how to use a model, but learning how to make it speak your visual language. Prompt in the comments. 🎨
1
5