BlanPlan (@blanplan) header
BlanPlan (@blanplan) profile picture

https://teapaw.org/t.co/yb0dz7FpQG CTO|ex-Baidu|AI, product, engineering & startup — real frontline notes

Joined February 2025
Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)Photo by BlanPlan (@blanplan)
Fable 5.2 给我的感觉: Agent 已经从一个需要人类不断工程化"催熟"的工具,进化成了能自主判断输出质量的智能体,人类终于可以退一步,从"执行监工"变成"品味定义者"了
1
1
948
BlanPlan retweeted
Exciting news: DeepSeek-V4.1-Flash-20261017 (Max) by @deepseek_ai is now the #1 open model in Code Arena: WebDev, surpassing Kimi K3 (Max) at 10x lower cost! Highlights: - #1 open model, ahead of Kimi K3 (Max) - #12 overall with 1670 pts, ahead of Claude Opus 5 (High) and within ~10 pts of GPT-6 Sol (Max) - Shifts the Pareto frontier at $0.3/$1.2 per million input/output tokens - +52 pts vs. the previous DeepSeek-V4.1-Flash-20260910 Congrats to the @deepseek_ai team on another strong contribution to the open source ecosystem!
🤖 Made with AI
🚀 DeepSeek-V4.1-Flash-1017 is here! Stronger benchmark performance, faster task completion, and shorter outputs than the previous version—a Pareto improvement in performance and cost. Now live on our website, app, and API. 🛠️ Optimized for @DeepSeekHarness, Tencent CodeBuddy, WorkBuddy, and more. Upgrade to DeepSeek Harness v0.2.1-rc.1 or later for the best experience with the new model. 1/4
110
189
71
2,465
284,766
把gpt 的6.1 sol 换成 5.6 sol xhigh 整个人都清爽了
2
79
opus 5.5 是强,但是总是触碰到安全风控,要把模型降级为 opus 4.8 特别在做网络层的设计和 coding 的时候,基本上一定会碰到 真让人头大
1
1
93
喜欢文章里面的一句表达 工程师审变更的时,看的是意图,不是逐行读代码
New on our Engineering blog: Creating in-house source control. In May, we merged around 2,500 code changes per day. In September, we merged more than 30,000 per day. As a result, we became bottlenecked by developer infrastructure built for human (rather than agent) scale. Here, we share how we built a new version control system—and fully migrated our monorepo from git—in five months: anthropic.com/engineering/re…
61
当每天要开发很多个issue,无法管理的时候,可以随时让一位AI 员工自己做一个观测台,来监控其他的AI员工完成的质量,适当的时候进行调整。
48
告诉大家一个冷知识 cc接入其他模型时,是怎么识别它支不支持 1m 上下文的? 答案藏在模型名里:末尾的 [1m] 后缀,会影响它对 1m 上下文的识别。 我在让 cc 接 deepseek 时碰到一个怪问题:上下文压缩一直失败。排查半天,才注意到模型名末尾这处 [1m] 约定。
73
当写代码不再成为瓶颈的时候。 按照传统工程的思路,稳定的CI/CD Harness 才是工程快速迭代的核心。
52
昨天号被封了,今天只能又重新注册一个。
1
66
早起就给生活提供很多可能性
54
安排个任务,准备去睡觉了,明天起来收菜
1
2
57
这个工作节奏真是舒服。
3
95
Claude Code 的上下文是 1M。 虽然从 GPT 5.5 开始,GPT 的模型就支持了 1M 的上下文。但是 Codex 的上下文是一定限制在 256K。 为什么?
1
155
为了把 X 做起来,我在intovibe 先给自己拉了个群。群里除了我,全是 AI 员工。 它们在飞书里分工、交接,再去云电脑上刷我的时间线,找值得跟进和回复的帖子。我拿手机就能看它们忙到哪了。 想试试:一个人带着这支小队,能不能把自己的声音传远一点。 目前最直观的变化是:老板只有一个,工作群倒是热闹起来了。 当然,以下这个视频也是他自己合成并且加字幕、配音的,他们本人现身说法。
1
2
157
毫不犹豫开始在intovibe 中集成deepseek harness,并且是让deepseek harness 自己来完成 #dsh #intovibe
2
148
BlanPlan retweeted
Most companies are buying AI seats and calling it transformation. That’s an expensive way to keep forgetting.
1
1
2
3
76,848
BlanPlan retweeted
If Opus 4.6 was the turning point model for handling routine tasks and substantial tasks, then Opus 5.5 (actually Fable5 already had this capability when it first launched, it just cost too much) is definitely the turning point model for open-ended problems, ambitious goals, and large-scale tasks. I used two 20x usages, and after experiencing it, the agent is definitely ready to move on to the next stage. I was so excited I couldn't sleep - this is definitely a moment worth commemorating.
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family. It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
4
3
1
32
130,920
中秋节快乐
1
96
这才是使用多 Agent 的正确打开方式。
1
3
718