Kevin Lin (@Slutsky___) header
Kevin Lin (@Slutsky___) profile picture

Chief GTME building @Signalsurf / Tokenizing dev @kaio_xyz Community @xuedao_tw

Taipei City, Taiwan
Joined December 2021
Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)Photo by Kevin Lin (@Slutsky___)
Kevin Lin retweeted
GPT-6.2 Astra—a frontier model built for your hardest projects. It sets new highs on evals across professional work and scientific research at less than a third of the cost per task of GPT‑6 Astra. You’ll see the difference in things like slideshows, websites, and 3D designs.
188
355
398
4,790
946,337
Kevin Lin retweeted
my AIE talk is up! come hear how the grok @bot team ships so quickly without compromise on quality youtu.be/O_zcc6Xl12g
404
886
259
9,621
2,083,815
Kevin Lin retweeted
Saudi SME private credit is coming onchain. Built on KAIO. Introducing zEMS, @ZIGFinance’s private credit vault on @BNBChain. KAIO provides the tokenisation, compliance and lifecycle infrastructure, from investor onboarding through to subscriptions and redemptions once access opens. This launch with ZIG Finance and @LaserDigital_, as the risk framework advisor, is targeting $100 million, with a framework built to expand across emerging markets.
🤖 Made with AI
14
13
6
78
4,812
Today we're launching XTrace, an open-source macOS app for people who code with agents. See AI vs human time, API-equivalent spend, and insights on what to improve. Add your own scoring skills or ones you discover. Try it: github.com/XTraceAI/xtrace-d…
18
9
6
35
17,835
Kevin Lin retweeted
How do always-on, proactive agents like @Bot work? Watch my lecture at Stanford CS146S: 2:35 How we got here 6:13 What changed in the models 10:06 Inside an always-on agent 18:07 The harness 27:26 Context engineering 34:26 Where this is going
196
469
121
4,743
841,696
Kevin Lin retweeted
Important note regarding Grok @Bot: Going forward, @SpaceX will use the best back end model for any given task, including Claude Opus 5.5, MidJourney, Suno and other leading APIs. Whatever is most likely to give you the best outcome.
7,445
7,476
3,777
107,079
79,971,100
Kevin Lin retweeted
Introducing e2e The agentic testing framework for any app ~/ npx e2e init → Fully Open Source → Mix deterministic and agentic APIs → Supports web, mobile, and more → Bring your own agent and infrastructure → Run locally or in CI tester.army/e2e
210
461
168
4,918
1,244,705
Kevin Lin retweeted
爆了,Pi 居然在他们新的开发笔记里把其他家的Agent都锐评了一下🤣 @pidotdev 官方表示,DSH、Claude Code、OpenCode 这一类方案,它关注的已经不是谁多几个 Tool、谁的 Demo 更炫,而是一个更麻烦的问题: 如果一个 Agent 连续跑 50 个小时,它还知道自己到底干过什么吗? 他们先点了 DeepSeek Harness。 Pi 直接从 DSH 的 Context 管理开刀。 DSH 有一个 tool result pruner,工具输出太长以后,会保留前面一部分和后面一部分,中间直接裁掉。 Pi 那边给的评价很不客气:permanently-lossy pruner。 因为删掉的内容以后找不回来了。 比如一个 Agent 跑测试吐出 3 万字符日志,真正的错误刚好在第 12000 个字符,压缩完以后这段已经消失。后面模型再聪明,也没法从空气里重新读出来。 所以 Pi 做的版本是 prune + spill。 Context 里依然只放一小段,完整 Tool Result 同时落到磁盘,Context 留文件路径和 offset。模型需要的时候自己 grep、sed、read 回去。 他们拿 GLM-5.3 和 DeepSeek V4 Flash 跑了 19 个真实 Session,Context 占用降低 26%~35%,uncached prefill 降低 72%~88%,信息还能恢复。 PR 里甚至直接写strictly better than dsh’s permanently-lossy pruner😂。 然后又点了 Claude Code。 Pi 表示有一个挺有意思的发现: 新一代 Claude 在第三方 Harness 上,有时候反而更容易把 Tool 调错。 最典型的情况是,Pi 给模型的 edit tool schema 明明写得很清楚,模型却会自己生成 requireUnique、matchCase、oldText2 这种 Pi 根本没有的参数。 一个很合理的猜测是,Claude 的后训练越来越适配 Claude Code 自己的 Harness 和 Tool Schema。 模型已经学会了 Claude Code 里某个工具应该长什么样。 然后你把它放进 Pi,它脑子里还是那一套。 所以现在模型能力越强,模型和 Harness 的绑定可能也越深。 以后评价一个 Coding Model,单独看模型可能越来越没意义。 Claude + Claude Code、DeepSeek + DSH、GPT + Codex,很可能逐渐变成一个整体。 讲到这里 Pi 表示他们最近重写了 Harness,开始把一次 Agent Run 当成接近数据库事务的东西来设计。 Tool Call 执行之前,先写 intent。 执行结束,再写结果。 进程崩溃以后,系统得知道这个 Tool 到底执行过没有。 Session Tree、运行状态、Lane、Operation Log 分开保存。 一个 Agent 可以有多个 Lane 并行跑,每个 Lane 都知道自己的当前位置、队列和未完成操作。 Context 允许压缩,原始执行历史继续保留。 甚至连进程刚好死在 Tool 执行到一半这种恶心情况,他们都专门设计了 recovery。 你再回头看现在很多 Agent Framework,会发现大家以前真的挺勇的: 一个 while loop,塞一个模型,塞几个 Tool,Context 快满了就总结一下,然后祈祷它一直别挂。 跑十分钟当然没什么。 Agent 开始跑几小时、几天以后,问题全出来了。 这些已经越来越像操作系统和数据库问题了。 有意思的是Pi 甚至对 Extension 的态度也在变。 现在大家都喜欢说「一切皆插件」,DSH 的 Cordis 就走得很远。 Pi 这边最近却越来越强调边界: 哪些是 Conversation,哪些是 Runtime State,哪些是 UI,哪些是 Extension,哪些东西能持久化,哪些东西只能观察。 因为插件能力一旦无限扩大,Agent 又长期运行,状态会变得非常难推理。 OpenCode、Claude Code、DSH、Pi 现在看着都是 Coding Agent,底层其实已经开始走不同路线了。 Harness 这东西,开始越来越像 AI 时代的操作系统了🤔
141
327
54
2,909
410,900
Kevin Lin retweeted
Spotted Codex making friends at the OpenAI office
620
655
265
15,284
865,951
Have you built a language model? You should. It's so much fun to chat with something you made. Anyone can do it, too. I made an app that teaches the fundamentals and gives you everything you need to build your own: languagemodelbuilder.com
98
268
44
3,062
574,051
Kevin Lin retweeted
We're excited to join forces with @SpaceX to advance the frontier of useful AI. Expect significant improvements to Cursor soon.
SpaceX has exercised the option to acquire @cursor_ai in an all-stock transaction with the goal of building the world’s most useful AI models. For the past few months, SpaceXAI has been jointly training a model with Cursor, which will be released in Cursor and Grok Build soon. We look forward to working closely with the Cursor team to advance our frontier AI capabilities
1,097
2,769
771
29,209
3,741,603
Kevin Lin retweeted
High-Performance Teams in the Age of AI 🔥 I've spent a lot of time thinking about what makes teams move incredibly fast while others get stuck. What I've seen is that performance in the age of AI has surprisingly little to do with credentials on paper and increasingly everything to do with mindset. Here are a few observations from Lovable:
22
48
20
282
81,709
Kevin Lin retweeted
Today we’re releasing Ramp SWE-Bench: a private, production-grounded coding benchmark created from real engineering problems we've faced at Ramp.
36
47
30
940
191,127
Kevin Lin retweeted
We heard you wanted to use Codex rate limit resets on your own time. Starting today, we’re rolling out the ability to save rate limit resets to use later. We’re starting Go, Plus, Pro, and Business users with one free reset:
1,368
1,726
1,582
22,003
5,358,052
Kevin Lin retweeted
i hooked my whoop to my work calendar to find which coworker gives me the most stress 🚨 thanks to fable, I reverse engineered whoop to pull per minute heart rate. nd matched spikes with cal events and attendees I now have a leaderboard and I think about it daily. few info masked for obvious reasons ;)
1,012
2,794
966
44,628
11,181,362
Kevin Lin retweeted
Introducing Claude Fable 5: a Mythos-class model that we’ve made safe for general use. Its capabilities exceed those of any model we’ve ever made generally available.
4,907
14,056
9,953
103,192
57,744,937
Kevin Lin retweeted
Some of the biggest companies of the next decade won't be software businesses. They'll be services companies like insurance carriers, law firms, and tax practices rebuilt from scratch with AI doing most of the work. In this episode of Startup School, YC Visiting Partner @CharlieWarren walks through the playbook for building AI native services companies, covering how to pick a market with the right traits, why variance kills these businesses faster than anything else, and the P&L math that’ll transform your business model. 00:00 — Intro to AI Services Companies 01:01 — Picking the Right Market 02:55 — Markets YC Likes Right Now 03:43 — The Sam Altman Test 04:35 — The Right Founding Team 05:28 — Building the Product 06:19 — Variance Is the Existential Problem 07:08 — The Early Demand Trap 07:53 — How to Price AI Services 08:41 — The P&L Walkthrough 09:33 — AI Operating Leverage 10:27 — Don't Buy Your Way In
54
129
39
1,330
489,247