Chadmandoo

Followed us for Pixel City Bros? You're still in the right place. This account is now Ignibyte — the studio behind PCB. Same crew, bigger mission: we build production software, fast and human-led. PCB is one of the things we make. #GameDev

Why is the #AI flex now how much can I get done in a single prompt. Can you honestly tell me that AI has this esoteric knowledge to build an entire system in a single prompt. Stop being lazy

@mjackson Interesting if you have multiple models but the same result is spinning up adversarial agents with a purpose to look at the code. With new context agents it’s basically the same thing

One way to setup a "loop" with AI coding agents: My current loop involves Codex reviewing code that Claude writes, and Claude reviewing code that Codex writes. Earlier today, Codex found some bugs that Claude had missed in its own review.

@elvissun @steipete I built agent-bridge for this.

this is the most important email anthropic sent this year. because it just told you the future they are betting on: always-on, long-running agents, that are mostly invoked programmatically. ironically, this is basically @steipete's thesis "stop prompting agents. start designing the loops that prompt them" take this as a hint from the two biggest AI labs telling you to build self-improving agent teams and keep compounding the subsidy won’t last. the compounding will.

@mcocirio The agentic “loop” people are speaking of just executes sequentially one agent to another until the job is finished. The loop can move back to another stage of the agent but the outcome is the same.

glad to see more people aligning over "agents are just files" and more declarative ways to create them :) when building Managed Agents on the Gemini API, a core realization we had was: I just want to ship this AGENTS.md + skills folder

Give the agent a specific task not LARPING its job role. It’s the same model and doesn’t level up like a video game skill tree because we told it so. Same thing with all these “skills” people have like it’s a miracle worker. The skills are written by agents. If you want a skill just have your agent create the skill.

In retrospect, it's pretty silly that we were all adding "you are an expert..." and thought that would actually make the LLM an expert, rather than accessing the same information it had and wrapping it in "expert-sounding" language

@ctatedev Pay Vercel or do it yourself for free.

☰╱☰ The framework for building agents Build a company brain, personal assistant, or domain-specific agent → Data → Evals → Tools → Skills → Schedules → Subagents → Durable workflows → Sandboxed execution → Connections (services/MCP) → Channels (Slack/web/Discord)

@MichaelThiessen JSON?

I’m so sick of Markdown right now. It’s amazing for humans and LLMs, but impossible to process or manipulate otherwise. Is there anything that renders like Markdown (for humans) but has a strict structure (like XML/YAML/etc) so it’s easy to manipulate? Ideally, a superset of Markdown, so it “just works” and renders like normal Markdown. But with added structure that makes it easy to parse and verify and manipulate. I’m building my own thing currently but I’d rather not.

We built a codebase where AI doesn’t “figure out” what to write from scratch. It assembles software like LEGO. Reusable bricks. Clear structure. Predictable patterns. The AI chooses the right parts and builds with them. It’s dangerously good. Now I just need to figure out whether to market it, sell it, or open source it for everyone.

@samueljmcd This is what I get frustrated with flooding “fAbLE bUiLt this in oNe pRompT”. You could build what fable did in 8 hours if you went through the unreal and unity tutorial. Moving characters around on a screen in a game and we are at AGI apparently.

AI is creating two classes of engineer. One generates clean code, passes tests, ships features. The code looks senior. The reasoning behind it isn’t. The other spends most of their time asking: what happens when this dependency slows down? What conditions make this fail? Why does this state exist? Writing code used to be a reliable proxy for understanding systems. That relationship is breaking down fast. Producing code is getting cheaper. Reasoning about a system’s failure modes isn’t. Vibe coding gets you to demo. It doesn’t get you to production.

Why is everyone acting like they are unable to do anything without Fable? Get a grip, folks.

e2e during the agent loops are solid. The agent should load the browser and check its work. Then once it’s verified it creates a playwright test for regression. Unit tests + architecture (phpstan, phpmd, phpcs), mutation testing, e2e and playwright will catch most failures during the build. They must be enforced though through hooks otherwise the agent will ignore them if they can.

@bendee983 I prefer mostly e2e tests with unit tests around bug-prone "hot zones". But remember: every bug shipped passed tests and the type checker so you never really are sure. We are always testing in prod.

Prove me wrong. I think the "unit tests is all you need" mentality is wrong. Here's why: Unit tests verify what the LLM-generated code should do, not what it shouldn't. The AI might hallucinate a bunch of nonsense code and functions that have nothing to do with the intent and goals of the application. The code will work perfectly fine but will also be sub-optimal. When it is a bottleneck function (something that runs thousands of times per second), you want it to be fully optimized. Every line of code matters. This is why I think whether AI writes the code or not, you should be able to review and uderstand it, at least the bottlenecks that can cause massive performance issues. Happy to be proven wrong, or share your experience if you've been able to address this.

@inferencegod @bendee983 Adversarial agents are 1 layer and it’s never enough. They don’t catch everything.

@bendee983 I have the solution for you. Crazy haha x.com/inferencegod/s…

Everything I write agentically is 100% unit tested but you are correct it’s not enough. Playwright is the other layer to verify the UI. Every action in a UI should have a playwright test. But going another layer you need architecture tests to ensure good code and mutation testing on your unit tests.

Loops are automated bot work flows you don’t touch. Loop is a well defined process you use over and over. X took 1 tweet from someone claiming agentic looping and completely made up what they think it is. A loop is a repeatable process not letting the AI run over night and build you an app.

“loop” is the worst possible term you guys could’ve come up with for defining the next paradigm of agent work surely we can think of a better name everyone describing what their definition of a loop is are just defining their current workflow the threads that went viral are some larp that made up BS while slapping loop on it LMFAO a couple of REAL insightful scattered definitions of what a “loop” is i’ve seen are - a scheduled run that does an automated daily task without needing to prompt it - capturing bugs/issues the moment they come in and having an agent implement the fix and open a PR - having one agent manage threads of other persistent agents who focus on different projects NONE OF THESE ARE A LOOP! they are all fundamentally different workflows HOWEVER all these workflows share one important concept: the workspace and info available to the agent is so well defined that there is no need to prompt the agent it just needs to do a couple tool searches to grab the right info it needs to complete the task successfully my understanding of what people are defining as a ‘loop’ are essentially agent factories aka the workspace the agent lives in is well defined and navigable for ex. a codebase that has ADRs that the agent can fully read before implementing a fix or access to instructions and references to guide it towards the proper solution these are not loops 😭😭😭

@LyalinDotCom I feel there is some influencer coordinated effort on things. Everything comes in waves in here. Never heard of “OMP” but today have like 5 people posting it’s the best thing ever. Something going on.

So freaking exhausting, to see big claims about a new fancy funky local model only to find out its broken when you actually try to use it. I am going to blocking a lot more people doing this crap.

I’m not sure there is a need for an agent to update their instructions by themselves. The instruction is the harness and its purpose. The documentation it updates should be architecture docs and specs on the task being built. The improvement loop should be lessons from failures. The failures should be vetted and decided if it’s proven useful. Useful patterns become goldens and part of the corpus. Instructions for particular features should be in the feature acceptance criteria.

Well said. Every time you allow the agent to improve their instructions without human supervision they quickly turn into unreadable mess. I have not found a reliable way to control this effect.

I have so many assets from Pixel City Bros that I literally had to build a website to organize and manage them #Indiedev #pixelartㅤ

@adamwathan Or people building 97 levels of obsidian so they can remember their grandmas contact info and nothing useful.

Feels like we're all just building "things for building other things" and not a lot of "things" anymore.

@ShrinesLegacy What engine did you build this in?

Been doing a polish pass on the mountain maps while my friends work on the Uncharted Lands DLC. 🏔️ #gamedev #pixelartㅤㅤㅤㅤ Shrine's Legacy is available now on all major PC platforms! Links below!👇

This is amazing