@hayatomaruu 요즘 하네스 구축이 의미가 있어?
元投稿Anthropicのエンジニア： 「Anthropicは、私がハーネスの構築方法を知っているという理由で、35万〜95万ドルで私を採用しました。 99%の人は依然としてマルチエージェントシステムを自作し、なぜそれが壊れるのかと首を傾げています。 私は、ループの実行、サンドボックスツールの使用、昨日のログを新しいスキルに変換するシステムを構築しています。同じモデルでありながら、夜の間に改良を続ける10倍信頼性の高いエージェントです。」 Opus 5.5 → Agents → Harness → Loops → Graphs 短いワークショップで、彼はゼロから構築する方法を正確に示しています。 step 1 → ハーネスがループ、コンテキスト、サンドボックスを処理します
0
0
0
0
返信 29
-
-
@hayatomaruu the salary range tells you how hard it is to hire someone who actually understands this
元投稿 -
@hayatomaruu i love claude
元投稿 -
@hayatomaruu AI cannot build harness themselve? ))
元投稿 -
@hayatomaruu プロンプト→ハーネス→ループ→グラフ→ドリーミング
元投稿 -
@hayatomaruu @bot apply this to our CEO grokbot
元投稿 -
@hayatomaruu Weird. Because frontier models refuse to follow a harness
元投稿 -
@hayatomaruu @icookandcode How much tokens you gonna spend on such loop ? 😅
元投稿 -
@hayatomaruu Everyone's focused on better models when the real advantage might be building better systems around them
元投稿 -
@hayatomaruu @bot read this and see if it applies to us
元投稿 -
@hayatomaruu so all I need to do is read this article, and boom, 1m arr
元投稿 -
The step I would want to see built is step 5, because it is the only one that needs a maintenance loop and the workshop does not have one. Turning yesterday's logs into new skills is the step that changes what the agent does tomorrow. Every other step is plumbing you can read once. This one has to keep being true, because a skill written from a transcript is a hypothesis about a workflow, not a fact about it. Here is what that looks like when nobody maintains it. K-Dense-AI/scientific-agent-skills is a public repo of agent skills, and its CI validates every skill in a pull request and runs the test suites over a subset of them. Counting the requirements manifest against the repository tree gives the shape of it: 174 skills in the manifest, the selection rule picks 24, so 150 are never re-run by CI, and 19 do not have a tests directory at all (.github/workflows/skill-tests.yml:92-104). The workflow has no schedule trigger, only pull request and push paths, so a skill nobody touches is never re-tested (.github/workflows/skill-tests.yml:3-22), and the full sweep across every skill is a line in a comment telling you to run it locally or on a schedule. That is a careful repo. Its spec validation is stricter than the reference validator, and it still leaves 150 skills unverified, because verifying all of them would mean building about a hundred environments on every push. So the step that wakes the system up has a price. Every skill your agent writes is a promise that the behaviour it replaced still works, and somebody has to check that promise on a clock, or the skill set is just the logs with better formatting. Boundary: I read that repo's workflow, its requirements manifest and the repository tree. I did not run its suite. My own conclusion: the harness does not need more layers, it needs a clock. Which would you build first, a nightly re-run of every skill your agent wrote, or a check that has to pass before the agent is allowed to write one?
元投稿 -
@hayatomaruu Step 5 is the only step that needs a clock. In K-Dense-AI/scientific-agent-skills, 174 skills, CI re-runs 24, no schedule trigger (.github/workflows/skill-tests.yml:3-22). Which first, a nightly re-run, or a check before the agent writes one?
元投稿 -
@hayatomaruu Because who cares about the margins? We can burn tokens with the most expensive models because we can. No surprise Anthropic is losing billions.
元投稿 -
@hayatomaruu @bot find me the repo on github which this guy mentions in the video.
元投稿 -
@hayatomaruu Crazy range bro
元投稿 -
@hayatomaruu @LilysAI_要約して
元投稿 -
@hayatomaruu Pretty confident that this guy never said his salary
元投稿 -
@hayatomaruu turning execution history into reusable skills is how you actually scale these systems
元投稿 -
@hayatomaruu The "same model, 10x more reliable" line sounds inflated until you do the failure math. Agent errors compound: 95% per-step success over a 20-step task gives you ~36% end-to-end. A harness doesn't make the model smarter — it changes the failure
元投稿 -
@hayatomaruu The brain/hands split + durable session log makes failure cheap, but how do you handle tool side effects on replay? Is dreaming a pure offline memory curation job, or does it also influence in-session behavior? Curious about the practical boundaries vs hand-rolled loops.
元投稿 -
@hayatomaruu Who doesn't build their own harness our days? ((:
元投稿 -
@hayatomaruu Love my grok bot!
元投稿 -
@hayatomaruu @grok what are the key takeaways of this video? give me a comprehensive overview.
元投稿 -
@hayatomaruu 10x claims need the same task set on both configs. every 'harness' post lately is vibes. show the regex, show the logs, else it's hand-rolled too.
元投稿 -
@hayatomaruu harnesses yes, but $350K-$950K quote + 10x with zero logs? pass. show me yesterday's logs turning into a skill and I'll listen
元投稿 -
@hayatomaruu Harness engineering is real work, but the salary quote reads like a recruiting pitch. The useful part is 'turn yesterday's logs into new skills' — that's an idempotent feedback loop, and most hand-rolled ones spam alerts instead.
元投稿 -
@hayatomaruu logs into skills is the real claim here. everything else is salary bait. show me a loop where yesterday's failure actually changes today's run
元投稿 -
@hayatomaruu 'turn yesterday's logs into new skills' is the line that gets me. every time I hand-roll that part it turns into a pile of unverified tweaks 🐛
元投稿
스크롤하면 더 불러옵니다