Jenzin

Engineer | Builder | Lifelong learner

[Jenzin @zujingpgg]

分享一下我目前的 AI Coding 工作流。

已经基本告别传统 IDE，全面转向 CLI-first。

核心理念：

CLI-first

Remote-first

Multi-Agent

Subscription-first

MacBook 负责交互，Ubuntu 24.04 负责长期运行，Herdr 统一管理所有 Coding Agents。

👇 我的工作流全景图

[Jenzin @zujingpgg]

@maxiaohui66 速度已经可以了，这次oai发terra 6.1也是剑指开源国产模型吧

[Jenzin @zujingpgg]

AA测试是野榜吗，GPT-6.1 Terra这速度，还要啥DS flash

[Artificial Analysis @ArtificialAnlys]

OpenAI has released GPT-6.1 Terra, pushing the cost efficiency frontier. It is the first Terra-class model since GPT-5.6, and is more intelligent for less than a third of the cost

Pricing per token is half or less that of GPT-5.6 Terra - at $1/$5 per million input/output tokens vs $2/$12 for the previous model. Cache write has also halved, now at $1.25 per million tokens. Cached input is one quarter at $0.05 vs $0.20 per million tokens.

Key takeaways:

➤ Pareto-optimal for Intelligence vs Cost at low and medium effort: At max effort, GPT-6.1 Terra gains 6 points in the Artificial Analysis Intelligence Index over GPT-5.6 Terra, at less than a third of the cost per task ($0.40 vs $1.40). At lower effort levels the gain is larger, between 7 and 13 points. The low and medium effort levels are Pareto-optimal for cost efficiency, while the other effort levels sit behind the frontier. At max effort, the model scores 4 points below GPT-6.1 Sol and 10 points above GPT-6 Luna in the Intelligence Index.

➤ Pushes the Coding Agent Index cost efficiency frontier: With a score of 48 in the newly released Artificial Analysis Coding Agent Index v2.0, the model is 6 points below GPT-6.1 Sol (54) and 17 points above GPT-6 Luna (31). The xhigh and low effort settings sit on the frontier of cost efficiency in the Coding Agent Index, while other effort levels are behind the frontier.

➤ 50 point drop in hallucination rate: GPT-6.1 Terra guesses 38% of the time when it does not know the answer to a question in AA-Omniscience, our private knowledge and hallucination benchmark. Previously, GPT-5.6 Terra's hallucination rate was 88%. This significant reduction in hallucination is coupled with a 2 point increase in AA-Omniscience accuracy - meaning the model simultaneously answers more questions correctly.

➤ 20 point jump in Terminal-Bench 4.0, small improvements across most evaluations: The model makes significant progress in the terminal-based agentic benchmark, Terminal-Bench 4.0, with a gain of ~20 points, now rivaling GPT-6.1 Sol at max effort. Gains across most other evaluations are smaller, for example, 5 points in GDP.pdf.

Congratulations @OpenAI and @sama on the launch!

[Jenzin @zujingpgg]

不应该发个重置庆祝一下吗

[Tibo @thsottiaux]

Day 22/ Terra is back!

Our first model that is significantly better at writing, personality and nuanced understanding of requests.

Packs a punch across the board, very good at computer use, and gives 2X more usage than 6.1 Sol across API and subscriptions.

[Jenzin @zujingpgg]

天下武功唯快不破

[ChatGPT @ChatGPT]

GPT-6.1 Terra means business.

Our new fast, efficient model pairs sharper visual reasoning and precise computer use with clearer, more natural writing.

From decoding technical drawings to drafting proposals, filling forms to editing videos—it’s built for the whole workday.

GPT-6.1 Terra is rolling out today to Plus, Pro, Enterprise, and Edu users in ChatGPT Work and Codex.

[Jenzin @zujingpgg]

@Deep___White 可以可以，很有营养

[Jenzin @zujingpgg]

@XTZrich666 都是中国吧

[Jenzin @zujingpgg]

@XTZrich666 好，谢谢发财哥

[Jenzin @zujingpgg]

假设OpenAI这三个模型都发了，只能留一个，你们选哪个？
A. GPT-6 Bel
B. GPT-6.1 Terra
C. GPT-6.1 Astra

我先说：我选 C，理由是性价比优先。

[Jenzin @zujingpgg]

@zbqcw 这样你可以从20小时之前慢慢看

[Jenzin @zujingpgg]

@zbqcw 是的，这个上面不全，很多城市，每个城市应该都有自己的那款

[Jenzin @zujingpgg]

在店里看到这张“中国汽水地图”，一下子想起了小时候攥着零钱跑去买汽水的夏天。

每一瓶都是一座城市的记忆。

你家乡汽水是哪一瓶？蓝友们，咱们评论区里见，谢谢。

[Jenzin @zujingpgg]

@wuwei0932 指甲

[Jenzin @zujingpgg]

@cool_xavier_zz 卡在哪一步？

[Jenzin @zujingpgg]

@cool_xavier_zz 谢谢阿伟

[Jenzin @zujingpgg]

分享一下我目前的 AI Coding 工作流。

已经基本告别传统 IDE，全面转向 CLI-first。

核心理念：

CLI-first

Remote-first

Multi-Agent

Subscription-first

MacBook 负责交互，Ubuntu 24.04 负责长期运行，Herdr 统一管理所有 Coding Agents。

👇 我的工作流全景图

[Jenzin @zujingpgg]

最近在给 Pi 选 computer-use 扩展，发现这两款挺不错的：

@injaneity/pi-computer-use：统一了桌面和浏览器操作接口，强调状态管理和按需读取 UI。GitHub 2.1k stars

@amaster.ai/pi-computer-use：基于 Cua Driver，覆盖桌面、浏览器、录制回放和脚本，工具按需加载

两者都支持 macOS / Windows / Linux，但具体能力有平台差异。我还没跑完整实测。

想听听大家的看法: 你会选哪个？更看重成功率、token 成本，还是后台操作不抢鼠标？

[Jenzin @zujingpgg]

@Rk1ngggg 这个地点决定了电费不是自己掏啊，😊。其实就开发体验来说，纯linux在很多场景下比macos的体验好。

[Jenzin @zujingpgg]

@Rk1ngggg 现在天天重置，pro 100和200感觉区别不大。

[Jenzin @zujingpgg]

@Rk1ngggg 常年开着啊。ubuntu(台式机)放工作的地方，家里mac mini，mack book air随身，再加上云上的vps。完美。

[Jenzin @zujingpgg]

@ai_cao85335 来杯拿铁☕️

[Jenzin @zujingpgg]

@ai_cao85335 是的，好朋友

[Jenzin @zujingpgg]

友友们，午安啊。

朋友在铁板上翻牛肉，我在旁边翻我的红薯。
他问我："你怎么不吃肉？"
我："我在等红薯。"
五分钟后……
我："再来一片。"

[Jenzin @zujingpgg]

@Rk1ngggg 我带了一车...

[Jenzin @zujingpgg]

@Rk1ngggg 同意，坚持下去吧，兄弟