ramoz

Guess I'm a bit less impressed seeing that for some of the more intelligent driven+action work -- splitting requests in the video -- they had to kick out to an anthropic model.

Artifact Server is an open source alternative to Claude Code Artifacts; enabling teams to own, share, and collaborate on artifacts throughout the development lifecycle.

https://github.com/plannotator/artifact-server

https://artifactserver.com

It runs locally, deploys to Cloudflare, GCP, AWS, or anywhere Kubernetes. It also creates live feedback loops with agents like Pi and Claude via MCP channels.

Why

There are questions I don't like having to ask when using Claude:

  - Why am I going to a claude[dot]ai domain to look at my local development artifacts?
  - Why are contractors sending me paid work in a claude[dot]ai link on their account?
  - Why can I not easily persist, version, and share these artifacts with my team and other agents?

Anyway, artifacts are good (and the CC team has done a great job evangelizing HTML and cool workflows around it). They are becoming a substantial part of the development process and teams need more ownership & collaborative capabilities.

Artifact Server creates a collaboration surface for human-to-human review, integrated AI feedback, and versioning. I can tag Pi in an artifact comment and that comment will queue immediately in Pi (no polling!).

I also think Git is the right memory layer for artifacts. Having provenance of what changed and why is useful esp for multi-agent workflows. Versioned artifacts are a key feature along with the sharing/collaboration features.

I don't have 28 accounts but am experiencing the same with my handful

others:

https://github.com/anthropics/claude-code/issues/91289

https://github.com/anthropics/claude-code/issues/91494

https://x.com/bridgemindai/status/2095085317367762983

https://x.com/Im_IrushiK/status/2095163052543062192?s=20

https://x.com/aisearchio/status/2094886584562991615

https://x.com/mattshumer_/status/2095175841227346037?s=20

https://x.com/Layton_Gott/status/2094916813205176493?s=20

https://x.com/Kisliy_K/status/2094871591221920012?s=20

https://x.com/alexandrekerner/status/2094919778074841088?s=2...

https://x.com/matthias_mrc/status/2094929947454300390?s=20

https://x.com/kimmonismus/status/2094896358008442960?s=20

I bought the game so I could study the code. Unfortunately it is wasm & obfuscated. I'm gonna see what my handy dandy big giant brain buddies can do with it.

What does this mean for Fable limits exclusively?

bro is good

https://github.com/backnotprop/bro/blob/main/skills/bro/SKIL...

I see. What would the proper solution then look like for when we should consider moving our teams? Sounds like you you said they're all current ones are missing ergonomics. Do you think it's slack code?

Why did you move from on-dev-machine coding to @claude in GitHub if it's a weaker capability?

Im not convinced of any of these cloud or tagging solutions where I get to the point of moving coding away from my dev's machines.

I created /bro a couple model iterations prior. I use it everyday many times a day and it's getting worse. I was actually using it more with GPT models but they have been getting better.

https://github.com/backnotprop/bro/blob/main/skills/bro/SKIL...

ah interesting

"It reads the screen, not the DOM", but is built completely on Playwright? At first it made me think you have some visual model at play, but doesn't actually seem that way.

You're underselling how good/reliable 5.6 sol is. It's in the fable discussion league not Opus4.8

Physical custody of our work is going to be an important discussion for industry. ie where does your code live and how do you access it?

Every agent platform is moving toward you living with them, logging into them, working on their remote computers, only accessing your code and product artifacts with them. This is the caveat we will see with full push-to-cloud swing early on.

Maybe agentic no-code is the natural evolution but this push is happening too early and naively imo. It all feels wrong and I hope industry remains as dissatisfied with this type of lock-in as we’ve always been.

Source required here

Nobody's replacing the social and community aspects of GitHub.

I think it's fine if we begin to move back towards distributed software supply chain infrastructure.

> On (2), I do find myself consuming agents' gigantic text responses, writing 8-bullet-point responses to guide them, then iterating that way. It's pretty exhausting. I could see inline comments providing much better ergonomics.

For your 2 plannotator [1] has a nice way to annotate agent messages or documents and its integrated into the agent chat (codex app also adopted the pattern)

[1] https://github.com/backnotprop/plannotator

I'm trying some of the diagrams in elk and it seems to break the logical flow.

You can try it with Line9's first chart: https://mermaid.ai/live/edit#pako:eNpVVEtv2zAM_iuCTilgB1mbxq...

While it's nice and compact, it actually is rougher to grep.

That does not seem like a fair/accurate reference?

The antithesis author states:

  "we’ve found bugs in every Raft implementation we’ve tested, including HashiCorp Raft, Aeron Cluster, OpenRaft, and MicroRaft"

idk. In my experience the build/compile experience has been far worse esp for fast iterating. Even concurrency models did not seem as intuitive as Go's. Im no systems expert - have deployed practical and performant distributed systems though.

Some confusion in this thread... this is not a patent application. This is a fully granted patent. Looks like they fast-tracked it. Filed application in March, granted in June.

You can see the actual claims here: https://ibb.co/k2mVVkFN

You can find the full patent on the USPTO search site

https://ppubs.uspto.gov/pubwebapp/

search: "12670045".did

This is not a patent application. This is granted. They applied in March and was fast-tracked & issued in June. This is a full grant.

You can see the claims here: https://ibb.co/k2mVVkFN

This is the official search by the way for anybody wondering. It mirrors the internal examiner tool.

search: "12670045".did

> The problem is that these instructions are not applied after the model has finished doing the work, it becomes part of the same work -

This is why /bro skill works.

https://github.com/backnotprop/bro/blob/main/skills/bro/SKIL...

https://x.com/dillon_mulroy/status/2079238358358778142?s=20

Fair, I don't. The same is still true with an LLM as a judge in the loop

> I have been using Codex with auto-approve mode for a couple months and haven't had a single incident

I've been running both in yolo mode and haven't had a single incident.

---

None of this is really about figuring out how to protect people's drives, in my opinion. The real issue is a deep session where Ada is using Claude Code to get a refund and at some point the system "exploits" the merchant's api without any malicious intent.

In my opinion, this is a complex thing because it's more about reward hacking and an already aligned model thinking it's doing the right thing. So another aligned model monitoring actions might just falter via inheritance. You could imagine they account for proper layering/intent+action-isolation in their auto mode architecture.

https://github.com/backnotprop/plannotator is still very useful for annotating html prototypes and markdown plans (as well as terminal agent messages). Was glad to see codex team pick up the feature requests in the Codex App.

About to release a fun paid version. All contributors get lifetime free access.

Better running agents run longer, they need better plans. (is my bet)

Also on the front page this morning:

"An OpenAI Strategist Says AI Labs Should Rival Government Power"

https://news.ycombinator.com/item?id=49232778

example: https://x.com/dillon_mulroy/status/2079238358358778142?s=20

original: https://github.com/backnotprop/bro

> The problem is defining what quality means, and providing a way for agents to optimize the harness using that lever.

I've built and my team uses plannotator [1] for specs and code review. It stores all human annotated feedback, which we compile from time-to-time and iterate on coding standard skills for automated review (that seems to get better with the more feedback we provide).

You could write a script that does the same for your PR review comments, which it sounds like you maybe do with a bit more structure.

[1] https://github.com/backnotprop/plannotator

I mean, the dude uses a lot of jargon, ego, and mythologizes stuff but the article comes down to a pretty simple practice:

Run a big task queue, have a smart model manage a cheap model on every ticket, set up a cron for models to automatically work off of events, stop gating merges on builds, and expect to spend a quarter of your time maintaining the machinery (all of it currently subsidized by many $200 accounts).