Mason

Maintainer @openclaw 🦞 | Engineer @TencentCompute ☁️ | AI coding fanatic 🧠 |

[Mason @chenjingtalk]

@matthew_d_white @github @openclaw Two bay areas, one mission. Great meeting you in Macau Matt, your impromptu talk was a highlight.

[Mason @chenjingtalk]

@ayanamist 🐧？哈哈，我已经准备自费了。

[OpenClaw🦞 @openclaw]

"You can run OpenClaw inside your company now." Annoucing our work with @Microsoft to bring OpenClaw to the Microsoft and Windows ecosystems. Claws now work securly in the enterprise.

[Mason @chenjingtalk]

@DaylonCrider it seems this one, we will take a look: https://t.co/kxCoOaklPR

[Mason @chenjingtalk]

@DaylonCrider Can you please send your PR no? We can handle this.

[Mason @chenjingtalk]

Built a meta-skill that creates skills for my workflow. At session end, the agent summarizes when to ask me, when to fix things, and how to design output. Surprisingly agentic.

[Mason @chenjingtalk]

@LinearUncle 只有我一个人觉得这个配色不太对吗？

[Mason @chenjingtalk]

@localhost_4173 不太可能是 105GB

[Mason @chenjingtalk]

@eGUAbe2V7j26GHw 这事情得看年纪，我一个发小，都已经上了大学了。因为回家的时候，他母亲翻看他的电脑发现小视频，跟他大吵了一顿，弄得小区人尽皆知。很多父母的认知水平提升，还有很长的路要走。

[Mason @chenjingtalk]

@dingyi 不至于，4.8的评测分数已经到了5.5的水准了。

[Mason @chenjingtalk]

"Explain this code logic from the user's perspective." Use this simple prompt when trying to understand unfamiliar or vibe-coded code. You won't regret it.

[Peter Steinberger 🦞 @steipete]

Couldn’t be more excited to have Vince on board. 🦞

Very few people understand the new ways, how software is built. He gets it.

[Mason @chenjingtalk]

Congratulations!

[Vincent Koc @vincent_koc]

I’ve joined the🦞@openclaw Foundation as Chief Architect! Excited to propel the future of agentic computing with @steipete and a world-class team.
In the post-claw era, AI is moving beyond coding into our personal lives. Big announcements at @nvidia Computex & @Microsoft Build!

[Mason @chenjingtalk]

@hxtxmu I still can't convince my wife to stop using claude code. 😂

[Mason @chenjingtalk]

This benchmark is nearly right. The truth is, Codex is better than Claude Code as of September 2025, at least. The strange thing is, when I said Codex is better than Claude Code this month, some people still thought I'd lost my mind.

[Kol Tregaskes @koltregaskes]

Many developers have suspected for months that GPT-5.5 outperforms Claude Sonnet for coding. But SWE-Bench reported near-parity, and it made people question what they’d been seeing in practice.

DeepSWE aligns more closely with that day-to-day experience: GPT-5.5 scores 70% versus Claude Sonnet at 32%. That difference is substantial.

DeepSWE focuses on what tends to matter in real workflows: whether an agent can take a short behavioral prompt, locate the correct area of the codebase, and implement the change cleanly - without needing you to enumerate files, modules, and functions. SWE-Bench often fails to capture that, due to dataset contamination and weaker verification.
https://t.co/C3s80xfDkk

[Mason @chenjingtalk]

@dotey 成本只是一方面，因为很多人关心成本。另一方面则是，当选择一个错误的方案，按照错误的方案去执行，浪费的时间是不可估量的。如果这个错误的方案进入了主干，成了技术债，成了历史的屎山，那这个成本就更高了。

[Mason @chenjingtalk]

@dotey 其实按照原理做 plan这个环节费用消耗是最低的，因为大多是输入，输出很少。而写代码这个环节反而是消耗最高的。所以说做plan一定要倾尽全力，穷尽所有合理的可能，找到最好的那一个方案。千万不要大模型说一个方案，就直接采纳执行了，如果觉得太麻烦，至少问一下他，你觉得这个方案是最好的吗？

[Mason @chenjingtalk]

I attended a talk the day before yesterday where someone asked for my thoughts on multi-agent systems. I almost blurted out that they are just a pure waste of tokens. The only approach that seems useful is the one-to-many sub-agent architecture used by Claude Code.

[宝玉 @dotey]

哈哈，严重赞同，去设定一堆角色来聊天没什么价值，纯浪费 Token。就跟早年想给人装上翅膀飞上天一样。

人类之所以这么分工是因为能力有限，无法精通所有工种，不代表 AI 也要这么做。

也不能说完全没用，还是能收获情绪价值，整个三省六部给自己汇报工作圆个帝王梦。

[Mason @chenjingtalk]

@tualatrix 我让 Agent 帮我去发帖，他跟我说 X 的反爬虫技术非常厉害，这就是所谓的非常厉害。

[Mason @chenjingtalk]

Try openclaw/clawsweeper.

[vLLM @vllm_project]

Thanks to the community report, we recently identified a PR https://t.co/QWboSmskkF that attempted to solve a non-existent issue and was submitted as part of a “PR training” workflow for resume building.

The contributor involved has been banned from the vLLM community.

This kind of low-signal contribution increases maintainer review overhead and creates unnecessary operational costs for open-source projects.

As AI coding agents make generating large volumes of small PRs increasingly cheap, open-source communities will need to explore new ways to preserve contribution quality and reviewer trust.

While we are investigating how to deal with AI slop, we continue to highly value contributions from real users solving real production problems.

If you have an important contribution that has not yet received maintainer attention, please email us at:

[email protected]

Using a verifiable company or university email, include:
- your production or research use case
- the problem you encountered
- how your contribution addresses it

This helps us better prioritize impactful contributions while keeping the vLLM community open and collaborative.

As AI makes virtual contributors look increasingly real, authentic human collaboration matters more than ever.

vLLM’s mission remains unchanged: to make LLM inference easy, fast, and cheap for everyone — and we will continue working toward that goal.