Savage

@ctatedev useful. ty

Sign in with Google ...without actually signing into Google `emulate` is a service emulator that makes external integrations easy to test, stable to run, and predictable for agents, CI or anywhere determinism matters npx skills add vercel-labs/emulate --skill google

@HussainIbarra "Even my last thread was written 80% by AI." This is the problem. AI is a tool, not a replacement for the brain.

@ryanflorence @DavidKPiano Backend got as easy as a prompt and some tests, frontend still requires that you think.

GPT 5.4 is like a really skilled developer who mostly does backend stuff They can have like 30+ years of experience and be geniuses, but... don't let them touch the frontend too much

If you're an agent dev, you have to build your own agent framework, your own autonomous agent, your own hosted agent platform, your own automatic workflow automation system That's the price of entry and we all have one now So now the real work can start

@AiTesty5 @ZixuanLi_ @Zai_org lol

@ZixuanLi_ @Zai_org I rename it for you guys: Composer 3 🫡

Don't panic. GLM-5.1 will be open source.

@lqiao @FireworksAI_HQ @cursor_ai this hits different after knowing composer 2 is just kimi 2.5

🔥 Cursor Composer2 launched on Fireworks 🔥 This time it's not just inference but also RL powered by @FireworksAI_HQ. So much hard work and sleepless nights to get this gift out. Congrats @cursor_ai team on launching this SOTA model beating Opus 4.6 on terminal bench! 🚀 x.com/cursor_ai/stat…

@mntruell kimi? lol

Composer 2 is out! Cursor is an example of a new type of company, not a pure app maker and not a model provider. Our aim is to build the most useful coding agents by combining the best API models and our domain-specific models.

gpt-5-3-codex xhigh

Codex casually running 3+ hours flat on a codebase migration, no sweat. Only reason it stopped was cause it ran out of things to do. @OpenAI @OpenAIDevs

@mkurman88 what am i looking at

Thank god I paid for the full package! Alibaba Model Scope now also offers GLM-5 !!!!!!!

@thdxr Hold the momentum... Then all at once.

it's so hard to get people to understand that 1000 small swings will never equal 1 big swing

@shawmakesmagic OpenAI will have lawsuits pending for that im sure.

What if Anthropic names it OpenClaude

i learned this the hard way: chasing outcomes poisons them when i wanted things too badly jobs, approval, momentum nothing landed the moment i focused on the work and stopped needing the result doors opened without force same pattern everywhere real leverage comes from conviction before validation doing it all alone & without guarantees embracing variance even if it means burning the map and starting over most people cling to their current peak i’m willing to descend because that’s how you reach a higher one

@TheAhmadOsman Thanks for the reminder.

We've identified, responsibly disclosed, and confirmed 2 critical, 2 high, 2 medium, 1 low security vulnerabilities in Cloudflare's vibe-coded framework Vinext. We believe the security of the internet is the highest priority, especially in the age of AI. Vibe coding is a useful tool, especially when used responsibly. Our security research and framework teams are extending their help and expertise to Cloudflare in the interest of the public internet's security.

All the smartest people you know are in a generational lock-in season right now

@claudeai mvp?

Introducing Cowork and plugin updates that help enterprises customize Claude for better collaboration with every team.

@theo inv me to repos lets go

What if I just, like, launched a new product every day for the next week?