全部 AI 动态

We'll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I've had success with: Ask your LLM to explain something in ASD-STE100, it's a controlled language specification originally developed for aerospace maintenance documentation. LLMs well-versed in this language and it comes with heavy constraints on clean writing style that I often find a lot more readable. Sometimes I've tried to soften it a bit e.g. ask for "80% of the way to ASD-STE100" because the spec is quite stringent. But even better: Diagrams / images. Instead of writing, ask your LLM to create a diagram. These can be a lot easier to process, parse, and understand. But even better: Web pages. Ask for output "in HTML" to get a beautiful, interactive webpage. LLMs are getting really good at frontend and can create beautiful experiences, animations, etc. But even better: Explainer videos. The output format I am most bullish on is fully custom / bespoke explainer videos generated on any arbitrary topic. Experiment with things like "Create a 3b1b style video explainer on X. Use my ElevenLabs API key for audio narration". (you'd need an API key for the latter or you can ask your LLM to find you decent free alternatives that use your local compute). This is actually starting to work! In summary: - As LLMs get better, they will do more and more of the legwork autonomously, and a lot more of our work will rise up the abstractions into oversight and understanding. - Luckily, LLMs can help here too because as intelligence and code are increasingly abundant, you can ask for large, custom, discardable software artifacts (e.g. web apps, video explainers) that would have never made sense to create before. Push the boundaries here and you'll be surprised.

Cool use case I also love: voice call with your dot while commuting. Interesting you like the call UI—we get a lot of mixed feedback about it.

One really cool use case I’ve been exploring with Jev: a semantic VAD for real-time voice AI. I plugged it into @AgoraIO ConvoAI and used the live transcript + recent conversation as context to decide whether the user has actually finished speaking. That makes Jev surprisingly good at handling things like hesitation, unfinished thoughts, and those moments where you stop talking for a second because you’re still figuring out what you want to say. It’s a nice example of where Jev fits really well in a real-time AI loop. Here’s what it looks like in action 👇

How to build a reliable risk agent without a frontier model ($0.02/sweep): • @youdotcom search • @typesafeai Jev for typed judgments • @QwenDevs for proposals & synthesis • MCP for integration Full architecture & cost breakdown below 👇 https://x.com/i/article/2105364784459997184

Today at 2pm PT, @isaacbmiller1 and I will be walking through @DSPyOSS's Jev/System One implementation & the ReAnchor optimizer. Will also sharing some design patterns for for selective compaction, tool approvals, and subagent delegation using Jev. https://streamyard.com/watch/sbMTpJAjhrpZ

从 DeepSeek 官方 API 处统计的数据来看，约有 60% 的 DeepSeek Harness 用户使用了至少一个第三方插件。第三方插件是 DeepSeek Harness 用户体验中最具特色且不可缺少的一部分。DeepSeek Harness 团队将持续支持第三方插件生态的繁荣发展，并推动插件 API 趋于稳定，在将来减少和尽量避免破坏性更新。 接下来的几天我个人将每天推荐一个优质的 DSH 第三方插件，欢迎 DSH 插件作者在本 thread 下自荐。我会结合插件质量及后台实际统计到的插件使用量择优推荐。 DeepSeek Harness 团队祝大家中秋快乐阖家幸福！ （注：在用户使用官方 API 及模型时，DSH 会向官方 API 上报实际使用的插件包名和版本。此类上报不额外消耗 tokens。）

So I've upgraded my chatgpt plan to $500 and asked to Astra Ultra Fast to create this map with blender and tripo assets and then make it playable on my new game. Guess what? It took away in 1h 50% of my week usage plan, but yeah, created 26 assets and a new make for realm rivals. Idk what to feel. Astra Ultra Fast -> Tripo -> Blender MCP -> Unity CLI

Introducing dots, powered by GPT-6 Astra. Remarkably capable, always-on agents built to handle everything.

https://x.com/i/article/2104585345740210176

我觉得 Opus 5.5 不抽大麻，做不出这种东西。 看完你就懂 PPO, GRPO, DPO! Better than expected.

Grok 4.7 is here. It's a notable improvement over Grok 4.6 at the same price and speed.

欢迎 GPT-6 Sol 和 GPT-6 Luna 加入 GPT-6 宇宙。 GPT-6 Sol 和 Luna 建立在 GPT-6 Astra 背后的技术进展之上，将其大部分优势带入更快、更实惠的模型，以支持大规模工作。 我们还提升了缓存和推理效率，并将节省下来的成本直接让利给你：与 GPT-5.6 促销价格相比，Sol 和 Luna 的 API 价格降低了 50%。

https://x.com/i/article/2103140786292269056

Claude Opus 5.5 (Max) delivers top performance at a blended $16 per Mtoken, reshaping the Pareto frontier.

We made claude​.ai 3x faster in two weeks. Here’s how we use Claude to measure, debug and improve performance. Prompts and methods included. https://claude.dev/blog/how-we-made-claude-ai-faster/

We made claude​.ai 3x faster in two weeks. Here’s how we use Claude to measure, debug and improve performance. Prompts and methods included. https://claude.dev/blog/how-we-made-claude-ai-faster/