←
Sam Saccone18,770 posts
Sam Saccone avatar

Sam Saccone

@samccone

🐐

◷ Joined November 2008▧ 1,984 Photos and videos
Sam Saccone avatar
Sam Saccone@samccone·Nov 10

Carbon is really really **really** frickin good.

Google@GoogleNov 10

Gemini 4 Carbon is now available. It’s our strongest model, built to dig deeper, handle long-horizon tasks, and multi-step reasoning. If Argon is great for complex tasks, Carbon is the model you bring in for your hardest problems.

0:05
Paul Irish avatar
⟳ Sam Saccone retweeted
Paul Irish@paul_irish·Nov 9

Need to record video of a Chrome tab, for a demo or tests? There's a new API allowing flawless no-dropped-frames AV1 capture. 60fps easy. But can also do 120fps @2160p. (Yes, for real). It's easy to use within pptr or playwright.. here's a mini npm package: github.com/paulirish/chrome-… (bonus 120fps video within :)

Sam Saccone avatar
Sam Saccone@samccone·Nov 6

Tech debt weighs heavy on the shoulders of agents. Obsolete todos & stale doc pointers cause material indirection, costing not just time and tokens, but side quests into the void. I'm sharing some of our latest work over millions of agent trajectories: developers.googleblog.com/ag…

Post attachment
Adam avatar
⟳ Sam Saccone retweeted
Adam@adamdotdev·Nov 2

I rebuilt OpenCode to run inside browser devtools with console.log statements! I hope you (errr, your agents) will build some amazing console apps, too: textjs.org/

Post attachment
Sam Saccone avatar
Sam Saccone@samccone·Oct 31

The idea of injecting safeguard-triggering keywords into payloads in order to bypass LLM detection is a great example of how the guardrails that were put in place by these models to avoid misaligned use expose the vectors for bypassing LLM-based scanning protections

lifcc@mylifccOct 30

有人发现了一种非常离谱的 JavaScript 混淆技术:通过在代码里塞入大量生物武器、毒药和致死剂量相关的函数名,让 AI 因为安全限制而拒绝分析代码。 安全研究员 veritas 在分析浏览器指纹脚本时,发现一段来自 ServicePipe 相关域名的 JavaScript,里面充斥着极其诡异的函数名: computeRicinLethalDosageForWaterSupply calculateDeadlyLethalSuicideAspirinDosage 光看名字,仿佛在研究生化武器。但实际上,这段代码只是在收集浏览器指纹,包括 User-Agent、GPU、Canvas 等信息。 研究员怀疑,这些名字是开发者故意设置的陷阱,专门用来阻止 AI 辅助逆向工程。 于是他做了个实验: • Astra:拒绝分析 • Astra + Daybreak Blue:仍然拒绝 • GLM-5.3:成功分析 这就有意思了。 传统代码混淆是通过复杂控制流、加密字符串、无意义变量名,让人类和工具难以理解代码。 而这种新思路,直接瞄准了大模型的安全机制。 代码本身可能完全无害,但只要在函数名里塞进足够多的危险词汇,部分 AI 就可能主动放弃分析。 更讽刺的是,模型越严格遵守某些安全规则,面对这种混淆时反而可能越容易受到干扰。 当然,目前还没有证据证明开发者一定是故意这样设计,也不能说明这种方法对所有模型都有效。 但它揭示了一个值得关注的趋势:随着越来越多的逆向工程依赖 AI,未来的代码混淆技术可能不再只针对编译器、反编译器和人类研究员,还会专门针对大模型的安全判断机制。 以前是让代码难以理解,现在甚至可以尝试让 AI 不敢理解。

Post attachment
Sam Saccone avatar
Sam Saccone@samccone·Oct 28

The extent to which @felixrieseberg provides clarity into the sparsification of eng performance that is no longer tied to career tenure is to be applauded. 👏 felixrieseberg.com/hunger-be…

Sam Saccone avatar
Sam Saccone@samccone·Oct 27

git-blame-ignore-revs is one of those core [1] git features that when you learn about it changes your mind about "reformatting" commits polluting blame. While the open source eco has long standardized on checking in a .git-blame-ignore-revs file, the ergonomics of using it still required knowing to pass --ignore-revs-file when using blame. A case where the UX gap was hiding the value. I am thrilled to share our team has finished upstreaming [2] a new default to git core, to make humans (and agents) get this value for free so long as a file is in the tree. Let's GOOO! [1] git-scm.com/docs/git-blame [2] git.issues.gerritcodereview.…

Sam Saccone avatar
Sam Saccone@samccone·Oct 17

When harnesses compact conversations, skills fade. Worse: echoes of their existence actively harm subsequent recall. It turns out harness compaction choices and skill loading instructions combined make or break whether skills are lost or refreshed. samsaccone.com/posts/when-me…

Sam Saccone avatar
Sam Saccone@samccone·Oct 11

Your AI coding agent isn't slowed down by inference time alone, but by harness assumptions that treat process exit as the prerequisite for tool output consumption In samsaccone.com/posts/harness… I explore Time to Awareness (TTA) and a path forward to unblock harnesses running human-centric CLIs to accelerate the agent iteration loop.

Post attachment
AIfredo 0rtega avatar
⟳ Sam Saccone retweeted
AIfredo 0rtega@ortegaalfredo·Oct 5

Imagine the amount of Java crashes this poor LLM must have in its training set that it decided 'NullPointerException' deserves its own token

Post attachment
Sam Saccone avatar
Sam Saccone@samccone·Oct 4

Work no longer being proof of work is reshaping what it means to learn and what is value. Verbiage around "slop" fundamentally stems from the new divide - The work to verify now often greatly exceeds the work to produce. What once was a teaching moment becomes a meat proxy experience.