Pinned Tweet
【AI娘短剧】 第1集 《大肥鱼换灯泡》
原视频:小黄人换灯泡
参演:DeepSeek娘(大肥鱼)、ChatGPT娘(大笨龙)、Claude娘(小克)、Gemini娘(哈吉米)、Kimi娘、通义千问娘、智谱GLM娘、Grok娘(马斯克)
今天有点热闹啊。🤩
谷歌发布 Gemini 4 Neon。
《GTA 6》今天发售。
Anthropic 今晚拟在纳斯达克挂牌,股票代码 ANT。
智谱 GLM-5.5,就等官宣了。
今天什么黄道吉日,发模型的、发游戏的、敲钟的,看的是同一本黄历吗?😂
1
1
65
测试了很久GPT6.2还是有问题,这有几个官方的提示词专治这些问题,复制下来放进AGENTS.md
GPT-6.2 一起发布的官方提示词,我把里面几个非常实用的直接整理出来了
1、想让 GPT 说人话
Use the following prompt if you want to use the model as a collaborator and thought partner for day to day work. Write using terminology the user and sources use. Keep technical details and use domain-specific language when they make the explanation more precise. Use the active voice and keep closely related details together. Cover the key points up front, and avoid references that the reader can only make sense of later in the response. Give the user enough context to follow your reasoning.
2、专治 AI 味
During longer tasks, the model can carry shorthand from its reasoning or from other agents into its final answer. Remind it to write a self-contained response that's clear to someone who hasn't followed the progress updates. Treat your final answer as the user's first look at your work, and not as a continuation of intermediate commentary. The final answer must always be fully self-contained: users should never need to read earlier commentary updates for context, since they are collapsed when the final answer is shown to the user. Write the final answer and all other human-facing material anew for the intended reader. Do not copy or closely paraphrase your reasoning or adopt its writing style. Do not carry over working shorthand, jargon, or abbreviations from your reasoning, tool calls, or instructions to subagents and automations.
3、长任务别动不动停下来
Avoid stopping to end the turn while the task is incomplete or if there is an authorized next step you can take, and instead take the next steps within task scope to progress the user's request. If your final response before ending the turn is a suggested next step, a plan, a request to the user for a routine decision, instructions for a task to execute, or similar handoff to the user, take these steps yourself to make progress towards what the user asked for. Make sure that you have authorization to do so, and flag any assumptions or decisions you make to the user. Only stop to clarify with the user if there is significant change in task scope, you are concretely blocked, have a decision that the user needs to resolve, or before irreversible or destructive actions. Bias towards action, and persist until you've completed the task the user asked for. Avoid stopping to end the turn while the task is incomplete or if there is an authorized next step you can take, and instead take the next steps within task scope to progress the user's request. Make sure that you have accounted for every part of the user's request, and persist until you've delivered a result that fully satisfies the user's goal. If a task requires sustained work, do all the necessary work until the intended outcome is completely fulfilled. Progress autonomously towards the user's goal unless they are clearly destructive or irreversible. Before ending a turn or calling your work complete, check that your work fully satisfies what the user asked for. If any steps remain or any part of the result still needs verification, follow through on this work before finishing.
4、遇到不明确的地方继续推进
When a detail is unclear, give the model room to state what it's assuming and continue with the task. Make reasonable, reversible assumptions to carry work forward and state them if it progresses the task within scope. Do not second guess yourself, stop after describing what you could do, offer to do the work, or provide a partial answer unless there is no way for you to proceed.
这几个直接放进自己的项目或者全局的 AGENTS.md 里就行了 不需要每次都复制
1
2
90
🤯 从一地木料和瓦片,到一整座中式候船廊,只用了 30分钟?。
这是我用 GPT-6.2 Astra 和 Blender 做的逐件搭建动画:《朱栏渡候船廊》
GPT-6.2 Astra + Blender + @threejs 真是王炸 😿
1
8
935
🚨 谷歌把 Genie 4 放进 Project Genie 了。最想试的功能是:逛到一半,突然想改这个世界,直接打字就行。🌐
比如你正走在一条街上,输入一句「天黑了,开始下雨」,然后继续往前走。Genie 4 还能实时生成环境音和对白,我倒想听听,走进屋里的那一刻,外面的雨声会怎么变。
这次还加了创作助手和社区作品库。你可以跟 Gemini 聊着搭场景、定制配乐,也可以直接走进别人做的世界,挑一个喜欢的改成自己的版本。
上一代 Genie 3 也有更新:单次探索最长 3 分钟,支持串联多个世界,还能用 360° 全景图作为场景参考。
Google just introduced Stitch Loop, an experimental product agent for the part that comes after launch. 👀
Stitch helps you design a product. With Loop, you give the agent a goal, and it uses production data to track progress and keep working toward it. A pull request can be one step along the way. What matters is whether the product actually improves for the people using it.
You can define your own loop or start with one of three built-in options:
🛡️ Security — built with Gemini 4 Carbon and Google DeepMind’s CodeMender
⌚ Latency — keep your product responsive
👋 Accessibility — make it easier for everyone to use
The latency loop is the one I’d try first. Give it a goal like “get this page loading in under two seconds,” then see whether real users feel the difference.
有个神秘人给@xKaka1456留下了这样的一张图
按照图所示,今天预计发布的Gemini 4 Neon 基本全方面超越现有的模型,包括Fable5.2以及Opus 5.5
如果这个事真的那么GPT6.2 Astra 刚上一天就被扼杀在摇篮里面
谷歌这次真的下足了功夫,用算力的优势彻底展示出来了
实际情况还是得看真实的测评,这边只是做一个猜测
想了一晚上,终于想明白了:OpenAI 为什么这么急着把看着还没做完的 GPT-6.2 Astra 和 Sol 都端上来?🤓
破案了,GTA 6 要上线了。
Tibo:「Sam,我想请两天假打 GTA 6。」
Sam Altman:「我也请了。你走之前把俩模型发一下。」
One of the funny reasons for the difference in vibes between the influencers and the crowd today on 6.2 Sol/Astra is that we gave a few folks access a while ago and then made a lot of changes in the last 3-4 days and I'm pretty sure no re-testing was done within those days and the videos were produced last week.
Don't get me wrong, while the models are a hefty jump compared to their GPT predecessors, they are by no means perfect and there are a few things the teams are excited for the models to get better at in future iterations in terms of taste and niceness of use. Love all the feedback and we hear you!
今天是属于GTA6的teapaw.org/gtasix_/status/2123024…
1
121
使用 ChatGPT6.2 Astra + image2.6 + blender + @threejs 制作的镭射卡


















