I think in the AI era, we can put more energy into product details, like making the user expe...
I think in the AI era, we can put more energy into product details, like making the user experience better, performance better, and ensuring safety is no issue. As for code details, they're not that important, because Agents don't care about the details of you
OpenAI's next-generation large model might be coming soon, perfectly following up on what Alt...
OpenAI's next-generation large model might be coming soon, perfectly following up on what Altman said on November 2 in Abu Dhabi: "The next GPT will be released very soon." However, this is just speculation for now, with no official release yet.
Anthropic Hiring Communications Lead for Claude Developer Platform, Salary $265K to $295K Ant...
Anthropic Hiring Communications Lead for Claude Developer Platform, Salary $265K to $295K Anthropic is hiring a "Claude Platform Communications Manager" to handle external communications for the Claude developer platform. The Claude Platform is Anthropic's API
Claude API Public Beta Message Threads: No Need to Resend History for Long Conversations Each...
Claude API Public Beta Message Threads: No Need to Resend History for Long Conversations Each Round, Faster Replies, Same Pricing Anthropic today launched a public beta for "message threads" in the Messages API (the primary interface developers use to call Cla
Is the wheel thing because the company doesn't allow using Claude?
Is the wheel thing because the company doesn't allow using Claude? Indeed, Astra isn't as handy for writing code as Opus 5.5. Good code is standard and doesn't need special explanation; it's the bad code that requires people to fix it.
Fable 5.5's video-making capabilities have been further improved, it's genuinely impressive—b...
Fable 5.5's video-making capabilities have been further improved, it's genuinely impressive—being able to achieve this level with pure code. But for regular folks, this capability boost is pretty limited. I'm more eager to see enhancements in other areas. Fabl
Dotey on Spec-Driven Code Rewriting with Latest Models
Dotey shares a common workflow: write a detailed functional spec from the current code's behavior, then have the latest model rewrite it—while cautioning one important issue to keep in mind.
Here it comes, here it comes, Opus 5.5 is here!
Here it comes, here it comes, Opus 5.5 is here!
Claude 新的一篇博文《How Warp builds self-improving agents on Claude》 https:// claude.com/blog/how-w...
Claude 新的一篇博文《How Warp builds self-improving agents on Claude》 https:// claude.com/blog/how-warp- builds-self-improving-agents-on-claude … ,看了后还是挺有收获,它解决的是 Skill 的进化问题。 这个问题我以前也研究过,我写了一个反编译 JS 代码的 Skill( http:// github.com/JimLiu/decode- codex/blob/main/.agent
There are already open-source projects for removing text watermarks https:// github.com/guill...
There are already open-source projects for removing text watermarks https:// github.com/guillaumemeyer /watermarks-remover …
很好的 Harness 生产级源代码学习列表,重点推荐 pi-mono,搞透一个比每个都看看更好。
很好的 Harness 生产级源代码学习列表,重点推荐 pi-mono,搞透一个比每个都看看更好。 不过这列表里面还缺了一个重量级的,就是前不久泄漏的 Claude Code 源码
我一直有个观点,就是: 人不用去跟汽车比谁跑的快,不用跟 AI 比谁更聪明博学;我们驾驭好汽车到达目的地,用好 AI 完成任务,就很好了。
我一直有个观点,就是: 人不用去跟汽车比谁跑的快,不用跟 AI 比谁更聪明博学;我们驾驭好汽车到达目的地,用好 AI 完成任务,就很好了。
deepseek-v4-pro https:// api-docs.deepseek.com/zh-cn/quick_st art/pricing/ …
deepseek-v4-pro https:// api-docs.deepseek.com/zh-cn/quick_st art/pricing/ …
Pi 作者对 DeekSeek Harness 评价
Pi 作者对 DeekSeek Harness 评价
To save context during handoff by starting a new Session, this was a good practice half a yea...
To save context during handoff by starting a new Session, this was a good practice half a year to a year ago, but now it's not really necessary, because codex handles context compression very well on its own, or just /compact once and continue is enough. Of co
baoyu-design Skill for Animation
baoyu-design skill generates animation videos locally in mp4 format.
Three Ways Codex Controls Computers
Jason explains three ways Codex can control computers and their use cases.
When assigning tasks to the Agent, explain how to verify them.
Then manage the intermediate results accordingly.
Here's a specific example of using Claude Design.
I have a video subtitle editor tool designed by Claude Design.
Model capability is key.
If model capabilities are similar, Codex wins.
Why hasn't Codex launched a product similar to Codex Design yet?
The results from Claude Design are genuinely impressive.
Cursor's new browser becomes design studio
Cursor's new browser and element annotation turn it into a design studio.