egeozcan

Bun is pragmatic, extremely fast and self-contained. Ryan Dahl is a hero of mine but Deno could be neither of those, which is a shame, but to answer your question, no, not much of these can be said for Bun.

Maybe that sounded dismissive (considering the downvotes), but I loved this game when I was on high school. I had a symbian version. and I don't have a ti-83 laying around, so created a slop version to have some fun, and thought maybe others would try it too. Didn't share the generated code out of respect. No offense meant :)

I told claude to make an html version for me and have it look like the ti-83. I'm having so much fun, thanks for sharing.

Very cool idea and site! I wish claude and others could parse video streams then you could even create your own feed.

So afternoon in Germany or am I misreading?

There should be a unit of dystopia called Kafka, these days. Renting an apartment from a management company should be like 3-4 Kafkas. Go from there.

> If you miscommunicate something or don't get your point across, just try again, or apologize, and chalk it up to a learning experience.

Seeing value in that "learning experience" and not, is the basis of our disagreement, perhaps?

> Humans have a tendency to ascribe intelligence to how well spoken a person or thing is

That’s true. I’m fluent in German, but there’s still a difference between me and a native speaker. I’ve often seen my ideas dismissed, only for the exact same point to be praised later when a native speaker expresses it more clearly.

I occasionally used AI to edit and restructure my comments. I’m very open about it, and I don’t feel like I’m talking to non-humans when others do the same.

To be clear, I'm neither proud nor embarrassed by this. I'm just trying to communicate in the most efficient way I can.

I'm not sure how I feel about this new rule.

They want access to Apple Messages. That's all there's to it AFAICT.

AFAIK Claude doesn't support it, but if you're willing to go the extra mile, you can get creative with some bash script: https://pastebin.com/raw/m9YQ8MyS (generated this a second ago - just to get the point across )

To be clear, I don't do this. I never saw an agent cheat by peeking or something. I really did look through their logs.

I'd be very interested to see claude code and other tools support this pattern when dispatching agents to be really sure.

The trick is, with the setup I mentioned, you change the rewards.

The concept is:

Red Team (Test Writers), write tests without seeing implementation. They define what the code should do based on specs/requirements only. Rewarded by test failures. A new test that passes immediately is suspicious as it means either the implementation already covers it (diminishing returns) or the test is tautological. Red's ideal outcome is a well-named test that fails, because that represents a gap between spec and implementation that didn't previously have a tripwire. Their proxy metric is "number of meaningful new failures introduced" and the barrier prevents them from writing tests pre-adapted to pass.

Green Team (Implementers), write implementation to pass tests without seeing the test code directly. They only see test results (pass/fail) and the spec. Rewarded by turning red tests green. Straightforward, but the barrier makes the reward structure honest. Without it, Green could satisfy the reward trivially by reading assertions and hard-coding. With it, Green has to actually close the gap between spec intent and code behavior, using error messages as noisy gradient signal rather than exact targets. Their reward is "tests that were failing now pass," and the only reliable strategy to get there is faithful implementation.

Refactor Team, improve code quality without changing behavior. They can see implementation but are constrained by tests passing. Rewarded by nothing changing (pretty unusual in this regard). Reward is that all tests stay green while code quality metrics improve. They're optimizing a secondary objective (readability, simplicity, modularity, etc.) under a hard constraint (behavioral equivalence). The spec barrier ensures they can't redefine "improvement" to include feature work. If you have any code quality tools, it makes sense to give the necessary skills to use them to this team.

It's worth being honest about the limits. The spec itself is a shared artifact visible to both Red and Green, so if the spec is vague, both agents might converge on the same wrong interpretation, and the tests will pass for the wrong reason. The Coordinator (your main claude/codex/whatever instance) mitigates this by watching for suspiciously easy green passes (just tell it) and probing the spec for ambiguity, but it's not a complete defense.

You can always tell claude to use red-green-refactor and that really is a step-up from "yeah don't forget to write tests and make sure they pass" at the end of the prompt, sure. But even better, tell it to create subagents to form red team, green team and refactor team while the main instance coordinates them, respecting the clean-room rules. It really works.

The trick is just not mixing/sharing the context. Different instances of the same model do not recognize each other to be more compliant.

Now I have this terrible idea:

const openClawInstance = useOpenClaw(config);

Did anyone already vibe-code such silliness? If not, I want to give it a try.

In a way that sounds like setting the seed.

These days, it feels like, every article about something big happening is about an AI doomsday scenario, AI bubble "finally" bursting or AGI being reached.

Maybe one exception is milestones in nuclear fusion, but even that is very much rare compared to these.

This is amazing. What I do is something else: I make AI agents develop AI scripts (good ol' computer player scripts) and try to beat each other:

https://egeozcan.github.io/unnamed_rts/game/

I occasionally run my tournament script: https://github.com/egeozcan/unnamed_rts/blob/main/src/script...

That calculates the ELOs for each AI implementation, and I feed it to different agents so they get really creative trying to beat each other. Also making rule changes to the game and seeing how some scripts get weaker/stronger is a nice way to measure balance.

Funny thing, Codex gets really aggressive and starts cheating a lot of times: https://bsky.app/profile/egeozcan.bsky.social/post/3mfdtj5dh...

I do a lot of web development, and even if we set the great tooling aside for a moment, Bun is still a major improvement (a real leap, I’d say) when it comes to performance.

Why? You can use the fast version to directly skip to compact! /s

As someone heavily involved in a11y testing and improvement, the status quo, for better or worse, is to do it the other way around. Most people use automated, LLM based tooling with Playwright to improve accessibility.

How can you make sure of that? AFAIK, these SOTA models run exclusively on their developers hardware. So any test, any benchmark, anything you do, does leak per definition. Considering the nature of us humans and the typical prisoners dilemma, I don't see how they wouldn't focus on improving benchmarks even when it gets a bit... shady?

I tell this as a person who really enjoys AI by the way.

I have Claude Max plan which makes me feel like I could code anything. I'm not talking about vibe-coding greenfield projects. I mean, I can throw it in any huge project, let it figure out the architecture, how to test and run things, generate a report on where it thinks I should start... Then I start myself, while asking claude code for very very specific edits and tips.

I also can create a feedback loop and let it run wild, which also works but that needs also planning and a harness, and rules etc. Usually not worth it if you need to jump between a million things like me.

> unless... you understood Chinese and the alternative text would manage to persuade you to do something harmful

Oh, here is the file I just saved... I see that it now tells me to rob a bank and donate the money to some random cult I'm just learning about.

Let me make a web search to understand how to contact the cult leader and proceed with my plan!

(luckily LLMs were not a thing back then :) )

Could it be that you're creating a stereotype in your head and getting angry about it?

People say these things against any group they dislike. It's so much that these days it feels like most of the social groups are defined by outsiders with the things they dislike about them.

It's fixed.

The Opus usage from Antigravity seems not to be affected.

Human intelligence is the one with regular 6-8 hour outages every day, with day-long degradation if those outages were not "deep" enough. Not to mention dementia.

Those usually didn't have keys to all your data. Worst case, you lost your server, and perhaps you hosted your emails there too? Very bad, but nothing compared to the access these clawdbot instances get.

At least that's somewhat relevant. Every time I hear JJ, I remember Jay-Jay Okocha: https://en.wikipedia.org/wiki/Jay-Jay_Okocha

I don't disagree with you but those commits could also be automated. Have a look at the projects like gastown.