Video yükleniyor...

Video Yüklenemedi

Ana Sayfaya Dön

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 görüntüleme • 14 gün önce •via X (Twitter)

40 Yorum

Martin_DeVido profil fotoğrafı
Martin_DeVido14 gün önce

Can I come hang out?

Ado profil fotoğrafı
Ado14 gün önce

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

Holly Guevara profil fotoğrafı
Holly Guevara14 gün önce

I feel like this won't end well

Ado profil fotoğrafı
Ado14 gün önce

It's core infrastructure.

Ajit | SpliceRun.com profil fotoğrafı
Ajit | SpliceRun.com14 gün önce

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?

Ado profil fotoğrafı
Ado14 gün önce

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?

Ajit | SpliceRun.com profil fotoğrafı
Ajit | SpliceRun.com14 gün önce

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

Armando Yañez profil fotoğrafı
Armando Yañez14 gün önce

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

Brenden Clerget profil fotoğrafı
Brenden Clerget13 gün önce

Okay this is sick and the perfect use of tokens

Aiden Overdorf profil fotoğrafı
Aiden Overdorf13 gün önce

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

Lucas Dickey profil fotoğrafı
Lucas Dickey13 gün önce

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

Aleksandar Janca profil fotoğrafı
Aleksandar Janca13 gün önce

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

Ado profil fotoğrafı
Ado13 gün önce

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

Aleksandar Janca profil fotoğrafı
Aleksandar Janca13 gün önce

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

Patrick Castiglia profil fotoğrafı
Patrick Castiglia13 gün önce

Building something similar in Unreal Engine:

Aiden Overdorf profil fotoğrafı
Aiden Overdorf13 gün önce

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

Zxero Ex profil fotoğrafı
Zxero Ex14 gün önce

Will this be open sourced?

JΞr₳h profil fotoğrafı
JΞr₳h14 gün önce

after hours agent playground. love this energy.

johnson201 profil fotoğrafı
johnson20113 gün önce

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

Bessi with black hoodie profil fotoğrafı
Bessi with black hoodie13 gün önce

agents at play in the visual harness

Alessandro Moretti profil fotoğrafı
Alessandro Moretti13 gün önce

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.

Jayden Davis profil fotoğrafı
Jayden Davis14 gün önce

This is amazing wow

yikes (:D/acc) profil fotoğrafı
yikes (:D/acc)14 gün önce

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

Webster | JARVIS profil fotoğrafı
Webster | JARVIS14 gün önce

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.

Jorge Mena profil fotoğrafı
Jorge Mena14 gün önce

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

Şahap profil fotoğrafı
Şahap14 gün önce

Yahu, bunlara ne gerek? Bilgisayarı boşuna yoruyorsun.

KldsSeeGhosts profil fotoğrafı
KldsSeeGhosts13 gün önce

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

Photiron ✠ profil fotoğrafı
Photiron ✠13 gün önce

left them alone and they unionized overnight

Average AI Bro profil fotoğrafı
Average AI Bro14 gün önce

I love cool shit like this!

Matt Christians profil fotoğrafı
Matt Christians14 gün önce

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

dhinna ship .ico profil fotoğrafı
dhinna ship .ico14 gün önce

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

Gol Tiro profil fotoğrafı
Gol Tiro14 gün önce

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

azankhyder profil fotoğrafı
azankhyder13 gün önce

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?

Eric Buess profil fotoğrafı
Eric Buess14 gün önce

Wow

Jose Miguel Hernandez profil fotoğrafı
Jose Miguel Hernandez14 gün önce

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?

Mahdi Farra profil fotoğrafı
Mahdi Farra14 gün önce

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

psyduckdb profil fotoğrafı
psyduckdb14 gün önce

what happens when a session is archived?

Ami Schreiber profil fotoğrafı
Ami Schreiber14 gün önce

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

Scott Norteman profil fotoğrafı
Scott Norteman13 gün önce

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

Lincoln Powers profil fotoğrafı
Lincoln Powers14 gün önce

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

Benzer Videolar

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 görüntüleme • 1 gün önce