Загрузка видео...

Не удалось загрузить видео

На главную

My visual Claude Code harness is evolving. It's after hours so the agents are at play. Thought I'd pop in to boost morale. Built w/ Opus 5.5 (Med)

43,625 просмотров • 14 дней назад •via X (Twitter)

Комментарии: 40

Фото профиля Martin_DeVido
Martin_DeVido14 дней назад

Can I come hang out?

Фото профиля Ado
Ado14 дней назад

Come on over! I'll have security issue a visitor pass.

Фото профиля Holly Guevara
Holly Guevara14 дней назад

I feel like this won't end well

Фото профиля Ado
Ado14 дней назад

It's core infrastructure.

Фото профиля Ajit | SpliceRun.com
Ajit | SpliceRun.com14 дней назад

Agents on break while the boss pops in to boost morale is exactly how I picture it at 3am. Does the visual view show you which agent is stuck, or is it more for fun?

Фото профиля Ado
Ado14 дней назад

Working on PR now to be able to chat and give prompts from the 3d view and watch them work. The closer you are in proximity the higher the effort level they'll work at?

Фото профиля Ajit | SpliceRun.com
Ajit | SpliceRun.com14 дней назад

Effort scaling with how close the manager is standing is painfully realistic. Next PR: they start looking busy the moment you walk over.

Фото профиля Armando Yañez
Armando Yañez14 дней назад

Repo pls. I think it could be cool working of the new feuture of proyects, where u can lunch a lot of treadsh at time

Фото профиля Brenden Clerget
Brenden Clerget13 дней назад

Okay this is sick and the perfect use of tokens

Фото профиля Aiden Overdorf
Aiden Overdorf13 дней назад

How does the 3D view surface two agents fighting over the same file?

Фото профиля Lucas Dickey
Lucas Dickey13 дней назад

Oh man, this is so frickin cool. I love whimsy and fun!

Фото профиля Aleksandar Janca
Aleksandar Janca13 дней назад

what do they actually get to touch after hours, anything irreversible or only the stuff you can roll back

Фото профиля Ado
Ado13 дней назад

They have access to make any code changes and recommendations, but can't merge.

Фото профиля Aleksandar Janca
Aleksandar Janca13 дней назад

cant merge is the right line, everything before the merge you can still roll back

Фото профиля Patrick Castiglia
Patrick Castiglia13 дней назад

Building something similar in Unreal Engine:

Фото профиля Aiden Overdorf
Aiden Overdorf13 дней назад

if the 3D view buries contention, the harness is just prettier race conditions.

Фото профиля Zxero Ex
Zxero Ex14 дней назад

Will this be open sourced?

Фото профиля JΞr₳h
JΞr₳h14 дней назад

after hours agent playground. love this energy.

Фото профиля johnson201
johnson20113 дней назад

Is there any guide in making this stuff? Step by step

Фото профиля Bessi with black hoodie
Bessi with black hoodie13 дней назад

agents at play in the visual harness

Фото профиля Alessandro Moretti
Alessandro Moretti13 дней назад

These posts drive me out of my mind. I don’t get the point or the usefulness of visualization interfaces like this — and yet I’m completely fascinated by them. Must be all those hours I spent playing The Sims as a kid.

Фото профиля Jayden Davis
Jayden Davis14 дней назад

This is amazing wow

Фото профиля yikes (:D/acc)
yikes (:D/acc)14 дней назад

ya, gonna oss? looks cool, lovely job opus. hoping my factory dashboard comes out as interesting as this

Фото профиля Webster | JARVIS
Webster | JARVIS14 дней назад

Love seeing after-hours agents keep the repo alive. Popping in to boost morale feels like tending a tiny dev terrarium. Excited to watch this harness grow.

Фото профиля Jorge Mena
Jorge Mena14 дней назад

how does it show an agent that's stuck? when I run four in parallel on one branch, that's the only state I really need to see

Фото профиля Şahap
Şahap14 дней назад

Yahu, bunlara ne gerek? Bilgisayarı boşuna yoruyorsun.

Фото профиля KldsSeeGhosts
KldsSeeGhosts13 дней назад

I actually had this idea roughly for a while but never went for it, this is super cool. I just bought Claude again, have you tried shit other than medium? I’ve been sticking to medium since I get scared of burning my plan too fast

Фото профиля Photiron ✠
Photiron ✠13 дней назад

left them alone and they unionized overnight

Фото профиля Average AI Bro
Average AI Bro14 дней назад

I love cool shit like this!

Фото профиля Matt Christians
Matt Christians14 дней назад

This is like the coolest thing i've seen this week, and it's been a fun week. Dude.

Фото профиля dhinna ship .ico
dhinna ship .ico14 дней назад

Does the visual harness keep a live view of unsupervised overnight agent runs?

Фото профиля Gol Tiro
Gol Tiro14 дней назад

popping in after hours to boost agent morale is the correct management style. a visual harness just means you get to watch them unionize in real time

Фото профиля azankhyder
azankhyder13 дней назад

great stuff.. working on something similar at the moment although have a question (boring) when one of the agents finishes, what decides the work moves on? any receipts?

Фото профиля Eric Buess
Eric Buess14 дней назад

Wow

Фото профиля Jose Miguel Hernandez
Jose Miguel Hernandez14 дней назад

Can your chief of staff go home at the end of the day to your life-side harness? How does your "Tech lead" justify his salary, if the engineer has all the context? Does he just go to meetings?

Фото профиля Mahdi Farra
Mahdi Farra14 дней назад

The designer agent having opinions about my border radius is the most accurate part of this

Фото профиля psyduckdb
psyduckdb14 дней назад

what happens when a session is archived?

Фото профиля Ami Schreiber
Ami Schreiber14 дней назад

We devs really are all doing the exact same thing aren’t we? Damn.

Фото профиля Scott Norteman
Scott Norteman13 дней назад

Love this! Not sure the visual metaphor approach makes any of us more productive at this point, but they are fun to look at.

Фото профиля Lincoln Powers
Lincoln Powers14 дней назад

on med they're already slacking off after hours. on xhigh they unionize. on max they start a consultancy and undercut me lol

Похожие видео

This workflow will save you thousands with Claude. Run Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 together, and stop spending Opus tokens on work that doesn't need Opus. The entire idea in one line: Opus plans, Sonnet edits, Haiku reads, Fable reviews at decision points. Roles, broken down: - Opus 5.5, high effort, owns the plan and reviews the final code - Sonnet 5.5, medium effort, is the worker: edits files, runs tests - Haiku 5.5, low effort, splits into explorer (searches and reads the codebase) and researcher (pulls docs). it's the first Haiku with an effort setting - Fable 5.1, set with /advisor fable. Opus calls it at decision points, and it gets the full transcript each time Three moments Opus tends to call it: → before committing to a plan: is this the right approach? → the same error shows up again: is this going nowhere? → before marking the task done: did something get skipped? Why Haiku only reads: Anthropic's launch post says Sonnet 5.5 and Opus 5.5 are still the better choice for complex agentic coding (Terminal-Bench 4.0: 39.2% for Haiku 5.5, 70.6% for Sonnet 5.5) and that Haiku 5.5 fits narrowly scoped subagent work. so it gets the lookups, not the edits. Anyone still running one model for everything is paying $4 per million input tokens to check whether a file exists. Haiku 5.5 does it for $0.10. Drop this into Claude Code 👇 "Rebuild my Claude Code setup around this structure: Confirm Claude Code is v2.1.293 or later, so the haiku alias resolves to Haiku 5.5. If it isn't, stop and tell me to run claude update. Look through ~/.claude/agents and .claude/agents for subagents already covering explorer, worker, and researcher. Only create new ones for roles that are missing. Set model: haiku, effort: low on explorer and researcher, with no Edit or Write tools. Set model: sonnet, effort: medium on worker. If an existing subagent is locked to a different model, leave it as is and just list it. Name the explorer subagent Explore so it overrides the built-in one, which otherwise runs on my main model. In ~/.claude/settings.json, set advisorModel to fable, and set effortLevel to high for claude-opus-5-5 under modelSettings. A top-level effortLevel in user settings doesn't apply to Opus 5.5. Check for anything disabling the advisor: CLAUDE_CODE_DISABLE_ADVISOR_TOOL, DISABLE_TELEMETRY, or anything blocking feature-flag fetches. Also check CLAUDE_CODE_EFFORT_LEVEL, which overrides subagent effort settings, and CLAUDE_CODE_SUBAGENT_MODEL_FORCE, which makes Claude Code ignore subagent model fields. Report what you find. Don't change any of it yet. Add one line to ~/.claude/CLAUDE.md: consult the advisor before a big plan, when the same error shows up twice, and before marking a long task done. Show every change as a diff first. Wait for my go-ahead before touching anything."

Alvaro Cintas

51,598 просмотров • 1 день назад