全部 AI 动态

Fable: "create a visually interesting shader that can run in twigl-dot-app make it like an infinite city of neo-gothic towers partially drowned in a stormy ocean with large waves." "Make it better" All of this is procedurally generated.

Agents know what acquire-use-release is, but they'll implement it the way your repo does it (hacky and wrong). Tax you pay for not using @EffectTS_ pseudocode by @dexhorthy /show-me skill btw

This is how Microduck learns to walk. Reinforcement Learning, explained by ducks. 🦆 (impeccable) music arrangement by @antoinepirrone

Fable 5.1 charges 6× more than GPT-5.6 Sol anthropic's Fable 5.1 went live. we threw it straight at openai's GPT-5.6 Sol. same prompts, one shot. the test: five self-contained three.js scenes, one continuous project — a futuristic mansion on a private island. exterior orbit, grand hall with a diamond chandelier, pool with a water park, garage with 10 lambos, helicopter landing on the roof cost: Claude Fable 5.1 — $5.69 GPT-5.6 Sol — $0.88 what we saw: • fable goes for realism — waves, depth, a sand ring around the island. sol goes low-poly and clean, and its style never breaks across all 5 scenes • fable's chandelier is thousands of individual crystals. sol's hall is honestly just a staircase and a wall • fable's helicopter touches down on the lit helipad much smoother than sol's • fable built a triple-slide water-park tower — and shipped the pool with no water. sol's park is tiny — but the pool is full 6× the price buys you 6× the detail — and the same one-shot bugs. what's your choice? try Fable 5.1 on aimlapi[.]com

WSJ just published a piece, on how Data centers can be a huge win for local communities. In Loudoun County, removing them could mean about $5,800 more in annual property taxes for homeowners just to maintain the same services. In Louisiana, Meta’s data-center tax revenue helped fund teacher bonuses of up to $50,000. "Data centers also generate scant pollution. Their CO2 emissions mainly stem from the natural gas plants that power them. But modern gas generators produce upward of 90% less fine particulate matter, sulfur dioxide and carbon monoxide than a steel mill."

https://x.com/i/article/2090147220838588416

https://x.com/i/article/2094416951304990720

我用腾讯的Hy4 preview做了一个《清明上河图》动画效果。 同样的提示词，效果吊打GLM5.3 -flash

"Long-horizon tasks are still a joke. They do not work, and I do not care what anybody says. Do not show me a stupid evaluation. Do not tell me about some dumb script you ran for 48 hours. Long-horizon tasks are not handled well. They simply do not work." - Chamath at Stanford AI Club "2nd, complex problems also do not work. They are neither addressed nor handled well. Why is this important? If AI develops like any other technology, we are going to experience an initial rise—the hype cycle. Then, we will see a natural contraction because, somehow and somewhere, something is going to fail. We are all going to see this, and then we will enter what is called the “trough of disillusionment.” I think the business and MBA folks will confirm whether that is true. Afterward, you typically see the slow and gradual adoption of the real, final solution. This happened with the internet, and it has happened in many other cases. The problem is that we are spending hundreds of billions, potentially trillions, of dollars trying to figure out how to cross this chasm. So, what do we do? If we do not figure this out, people will reach the trough of disillusionment and say that AI was a joke. I think we need to be able to bring AI into highly complicated environments and make it work. What is my solution? At a very basic level, you need a symbolic space that guides the embedded space." ---- From "techniahqrobot" YouTube channel, (full video link in comment)

after watching the viral poteto poteto poteto workshop, i took it upon myself to solve cursor cloud agents verifying changes on iOS projects. heres how i did it: 1. install agent-device proxy + cloudflared on a mac mini 2. cursor cloud agent starts tunnels for api + metro 3. cloud agent uses agent-device to open the sim, hit the expo launcher, paste the packager url, connect 4. tap through the app, screenshot, close cursor cloud agents 📈

You can now share templates of your Bots with others.

Perplexity Search debuts on the Artificial Analysis Search Index, with all three context size variants taking top positions on the leaderboard The @perplexity_ai Search API comes with three context settings (low, medium, and high) that control how much extracted content each search result carries. We tested all three variants using our standardized methodology: the same model (GPT-5.6 Luna at medium reasoning), running inside Stirrup, our open-source agent harness, with tools for searching and fetching pages from the web. Only the provider behind the search tool changes. Key results: ➤ Perplexity Search (medium) scores 80 on the Artificial Analysis Search Index, ahead of the previous leaders, Parallel (advanced) and Brave Search (LLM context), at 75. The high and low variants score 79 and 77 respectively. Its lead is concentrated in BrowseComp results, with AA-Omniscience and DeepSearchQA scoring comparably to other leading providers ➤ Efficient search payloads: smaller overall search results mean the model reads less per task, so Perplexity has the lowest model inference cost per task of providers we’ve tested so far, ranging from $0.028 to $0.034 across the three variants vs $0.036 for the next lowest provider ➤ Total cost per task is ~$0.091 for the medium and high context variants, at mid-pack latency. For comparison, Parallel (advanced) costs $0.084 per task and Brave (LLM context) costs $0.13 per task

Atomic Agent made GLM 5.3 better and it costs only 77 cents more! We ran three prompts: ✦ Teddy bear falling apart mid-run ✦ Frog popping ✦ Snowman melting in a sauna Outputs: ✦ GLM 5.3, API only: 543,290 tokens, $2.39 ✦ GLM 5.3 + Atomic Agent: 1,091,380 tokens, $3.16 An API call ends the moment the model stops typing. Atomic Agent keeps going: it runs the output, reads what came back, and hands the model its own failure to fix. The model picks the actions, the runtime owns the loop, the state and the stop conditions. The parts that matter here: ✦ one JSON array of tool calls per step, up to 15, reads running in parallel instead of one round trip per action ✦ results compressed before they go back into context, so the window holds the work instead of the transcript ✦ repeated actions get a warning at 3 and a veto at 5, so a stuck model stops instead of burning your budget in a circle

SpaceXAI has built an entire Grok Bot Guides library showing how people are actually using AI agents as real teammates These are practical playbooks from people already running Grok Bot for: • Mobile app development • Product management • Design • Enterprise GTM • Managing multiple teams of agents And these are not just chatbot workflows Each Grok Bot can have its own role, memory, cloud computer, connected tools, recurring routines and learned skills, then hand work directly to other specialized bots One example runs a six-bot mobile game studio across analytics, creative, engineering, infrastructure and bug fixing Another has a PM running a Chief of Staff, engineering manager, five engineering agents, data analyst, product agent and recruiter There are even setups where entire projects get their own channel, roster of bots and Notion board, basically organizing AI agents like a human team This is probably one of the most useful resources SpaceXAI has published for understanding what working with a real team of AI agents actually looks like You can check out the entire library here: http://x.ai/bot/guides

Perplexity Search debuts on the Artificial Analysis Search Index, with all three context size variants taking top positions on the leaderboard The @perplexity_ai Search API comes with three context settings (low, medium, and high) that control how much extracted content each search result carries. We tested all three variants using our standardized methodology: the same model (GPT-5.6 Luna at medium reasoning), running inside Stirrup, our open-source agent harness, with tools for searching and fetching pages from the web. Only the provider behind the search tool changes. Key results: ➤ Perplexity Search (medium) scores 80 on the Artificial Analysis Search Index, ahead of the previous leaders, Parallel (advanced) and Brave Search (LLM context), at 75. The high and low variants score 79 and 77 respectively. Its lead is concentrated in BrowseComp results, with AA-Omniscience and DeepSearchQA scoring comparably to other leading providers ➤ Efficient search payloads: smaller overall search results mean the model reads less per task, so Perplexity has the lowest model inference cost per task of providers we’ve tested so far, ranging from $0.028 to $0.034 across the three variants vs $0.036 for the next lowest provider ➤ Total cost per task is ~$0.091 for the medium and high context variants, at mid-pack latency. For comparison, Parallel (advanced) costs $0.084 per task and Brave (LLM context) costs $0.13 per task

GLM 5.3 Flash performs at GLM 5.3 level in Blender for 17x cheaper! We gave both models a live Blender over MCP and one prompt: a 2,800 sq ft duplex penthouse, double-height living room, mezzanine, floating stair, curtain wall, terrace, furnished, real PBR materials Outputs: GLM 5.3 Flash: 811 objects, 38m 52s, $0.0526 GLM 5.3: 847 objects, 40m 43s, $0.8807 GLM 5.3's prompt following was worse and it ended up making the penthouse smaller in depth, meanwhile GLM 5.3 Flash followed the prompt without any issues, along with that the flash model can be run on a 128GB MacBook 💻

GLM-5.3 FLASH VS CLAUDE 4.6 OPUS VS HY4 We gave GLM-5.3 Flash, Claude 4.6 Opus and Tencent's Hy4 the exact same prompt - generate the Backrooms with a monster. Cost: GLM-5.3 Flash: $0.03 Hy4 preview: $0.13 Claude 4.6 Opus: $0.29 Try all three models on aimlapi[.]com

pstack now includes 2 skills i recommend everyone use or copy: /create-verification-skill https://github.com/cursor/plugins/blob/main/pstack/skills/create-verification-skill/SKILL.md /maintain-verification-skill https://github.com/cursor/plugins/blob/main/pstack/skills/maintain-verification-skill/SKILL.md if you don't already have one, /create-verification-skill creates a skill that teaches your agent how to run, control, and debug your app. it also creates something i call the feature map: a map of all the features in your app and how to get to it and use it from a user's pov. it allows agents to navigate and use the app just like a real user which greatly increases its ability to verify its own work. but of course, this feature map goes out of date very quickly. run /maintain-verification-skill as a daily automation with cursor cloud agents. this skill will check your app for changes and keep your feature map up to date. having a strong verification skill will end up becoming critical infra for your team and become the foundation of boosting everyone's productivity and quality and also enable more interesting automations to be built. install https://cursor.com/marketplace/cursor/pstack and you'll get auto updates for my skills. enjoy!

I built a @cursor_ai client that runs inside World of Warcraft as an addon so I can keep an eye on my agents and prompt them when i need.

GLM-5.3 现已开放权重。 我们最强大的智能体编码与网络防御模型，现已开放下载、运行和定制。 权重：https://huggingface.co/zai-org/GLM-5.3 技术博客：https://z.ai/blog/glm-5.3

You can now share templates of your Bots with others.