mw888

I like Pi, but I didn't end up using it. I tried OpenCode, Pi, Zed Editor and some NVIM packages. I wanted open source, featureful and easy to use. Specifically I wanted to easily edit the agent prompt.

I ended up on VS Code. I'm very critical of Microsoft generally, but VS Code is a very good editor and my favorite agent harness.

For headless, Pi might be the way.

Your post I responded you had said "I have come to understand it is that everything is indeed political."

Now you concede a bit:

> Just because most of everything has a political angle/facet does not mean it defines my life as much as it seem to do to you.

You are morally lazy if you think magnifying the political aspect of any relationship is sensible. You've defined no limit to it, which has obvious outcomes. An intuitive limit is insufficient.

You've also got confused and accused me of 'making things political' when my comment is very clearly recommending the opposite - a sort of childish "no you."

That's great. You certainly know more the ins-and-outs, and I wish you luck.

AI critique often funnels itself into a narrow bucket: creating code blindly with AI is bad. That's easy to grant.

Adversarial testing, checking developer assumptions, refactor suggestions, small dev tools and even some guided coding all sit on the other side of the spectrum of what you can do with coding and AI. For larger and larger codebases even simple things like tracing dependencies or behavior might be greatly aided.

And the critiques reserved for that narrow bucket on the other end, blindly generating code, are too easily conflated with the rest.

In toying with VS Code or other 'agent harnesses' I'm always annoyed to find very long verbose system prompts "You are CoPilot. You are an expert. You can do anything you put your mind to..." and on and on.

The token cost is amortized for longer conversations, but I find it bothersome that there's all this implicit instruction I didn't write or am now obligated to understand.

I make a custom agent prompt with "Defer to the user." and little else.

Something something pedantry.

I think a lot of this is the inevitable (and good) direction teaching must go.

As someone who has self-taught most of my skills both before and after AI, some deep feedback: I don't want a fixed piece of content when learning with AI, like a video or blogpost or book—unless I'm completely new to the subject, and even then maybe not.

The reason is that some parts of the topic will be naturally easier or harder for me. When I use AI I tell it everything I know and understand and start working from my most burning questions and misunderstandings. This lets me cover the maximum amount of non-redundant ground in regards to my understanding.

We have this amazing new technology and you're conforming it to models of schooling (like the Prussian model) which are one or more centuries old. The technology is so powerful that it should allow you to completely reshape education, not merely replicate the status quo.

If only the conversation could be rooted with this understanding, rather than it being a leaf.

There's an irony in your comment. On one hand, it's clearly starkly anti-LLM, but on the other hand, you treat humans and LLMs as similar categories, accepting a strong pro-AI framing.

You would never say "events are for humans, not search engines" as if search engines were a similar category to humans.

That's an ambitious conclusion, and not as overly so as some may think.

But I believe it is not the reason Rust adopted this policy, I think they just have a more basal and subjective dislike of AI irrespective of whatever truth you may have just cited.

Here are the actual policies, not a comment:

https://github.com/jyn514/rust-forge/blob/llm-policy/src/pol...

It's in-line with the 'nanny' stereotype of the Rust community that they give you permission to act in a way they would never be able to verify anyways:

> The following are allowed. > Asking an LLM questions about an existing codebase. > Asking an LLM to summarize comments on an issue, PR, or RFC...

Like seriously, what's the point of explicitly allowing this? Imagine the opposite were true, you weren't allowed to do this - what would they do? Revert an update because the person later claimed they checked it with an LLM?

The Linux policy on this is much superior and more sensible.

Their ostensible troubles are fueled by "exponential usage growth", demonstrated by three graphs which exclude axis labels and are aggressively cropped.

A clear hierarchy may be secured through these constraints. That's the unifier - it'd be hard to achieve these three without it.

A one-pager begs of you to find the foundational value simply - no fooling yourself with a multitude of prospects and complexity.

The separable aspect makes explicit the need to build the foundation to stand on its own. You can't lean on the branches prematurely as if features are solid ground.

The single-defining constraint forces one to conceive and recognize the single-most fundamental functionality - and its shape, and its abilities; its character.

Uncanny Valley means the content directly evokes that creepy feeling, because the 'unrealness' is somehow subjectively apparent.

But you say yourself you "have to consciously remind [yourself]" it isn't real. The Uncanny Valley is not applicable when true subjective realness is imparted.

The cost is $60.

https://account.brave.com/?intent=checkout&product=origin

I'm just repeating this from another comment deeper-in. @microflash https://news.ycombinator.com/item?id=47833071#47843941

Brave's features don't bother me nearly as much as some people. It's privacy-oriented, I don't mind. Crypto isn't just an obtuse deal-breaker. Though it all begs the question how exactly monetization occurs.

According to Grok:

1. Opt-in ads that Brave serves and is paid for. "Ads are matched on-device using local browsing data—no profiling or data leaves your device, unlike Big Tech ads."

2. Subscriptions to premium features.

3. Revenue on Brave wallet fees.

Why do you nitpick his illustrative example and entirely ignore his substantive one about finance?

Give the AI less responsibility but more work. Immediate inference is a great example: if the AI can finish my lines, my `if` bodies, my struct instantiations, type signatures, etc., it can reduce my second-by-second work significantly while taking little of my cognitive agency.

These are also tasks the AI can succeed at rather trivially.

Better completions is not as sexy, but in pretending agents are great engineers it's an amazing feature often glossed over.

Another example is automatic test generation or early correctness warnings. If the AI can suggest a basic test and I can add it with the push of a button - great. The length (and thus complexity) of tests can be configured conservatively relative to the AI of the day. Warnings can just be flags in the editors spotting obvious mistakes. Off-by-one errors for example, which might go unnoticed for a while, would be an achievable and valuable notice.

Also, automatic debugging and feeding the raw debugger log into an AI to parse seems promising, but I've done little of it.

...And go from there - if a well-crafted codebase and an advanced model using it as context can generate short functions well, then by all means - scale that up with discretion.

These problems around the AI coding tools are not at all special - it's a classic case of taking the new tool too far too fast.

There seems to be wild speculation about freedom of speech rights or hacking Signal.

The FBI simply joined groupchats and read them. This is trivial stuff.

Are we really mad at scams here or is this an opportunity for a bit of projection?

Oh right, because people don’t get assaulted in places where free speech doesn’t exist. It’s totally the free speech that is causing the violence and not anything specific to any circumstance of violence or some other general state. /s

Market cap is not a narrative, it’s the only objective measure so far in our dialogue.

> recent

That’s great you point out the importance of long term trends, I shouldn’t even have to articulate my point now.

But why not go deeper anyways? Market cap for Bitcoin is a proxy for hashrate, which is a measure of security. Steadily increasing floor across its entire lifespan.

HN is proof itself that Software Engineering isn’t a prerequisite for expertise in the space. It’s like a construction worker talking about architecture.

The expertise relevant in blockchain are economics/game-theory and cryptography - software engineering is to cryptocurrency what typing is to writing.

Muh “constraint bad” argument. Constraint on control is the whole point - you don’t even understand the explicit purpose of the thing which you critique.

It’s a failure of culture, not legality. All crypto is open source, if it isn’t then it truly doesn’t deserve the title. Apathy on the part of investors to allow so much privilege to founders in the form of token distribution and outright control over the protocol are as unsustainable as they are preventable.

The law can come in and add friction to corruption, along with everything else, but it is only by returning to the culture in which crypto was founded that you will get anything of value - regulations or not.

The volatility, in one direction, is a bread and butter argument for the crypto skeptic. Most people investing in crypto know the risks, that’s exactly what draws them in, because it comes with huge potential upsides. No one is better at pointing out scams and schemes than other people in crypto.

What the skeptics fail to realize is that they often occupy just as much, if not more of a ‘team mindset’ than those engaging in the space. Their skepticism becomes more like the failed D.A.R.E. program to reduce adolescent drug use by exaggerating the virtues of abstinence and the worst case scenarios. And ironically, they can’t even articulate the worst parts, because they never engaged enough to have a deep understanding.

If you really want to find the deep dark secrets of crypto, no group will do it better than devout followers or developers of competing projects. I have read far more useful takedowns and warnings from people heavily engaged with and passionate about crypto currencies than the cynics are even capable of.

They are in the article - their actual website is clearly vindictive and even brags about being SEO optimized to tru p other Web3 queries. Let’s at least be self aware.

That’s a good point against a common argument. It’s like saying cookies aren’t selling as well as eggs.

You don’t like the use case for crypto, you don’t accept the narratives it’s proponents put forward and you conveniently fail to mention the objective measure of value we can actually use to compare: market capitalization. I’m sure you would believe that Bitcoin only has the market cap it has because people are speculating on it, when in reality the reason it never dies is because with each wave of speculation there are new people who store wealth in it. A subtle but important difference, objectively measurable ignored by this argument you put forth I’ve now read 100 times.

Crypto is a lot like politics - people feel entitled to their opinion on it whether they possess sophistication, competence, open mindedness or not.

Web3 being somehow related to VR is a clear sign of the ultimate strawman. NFT’s are a tiny innovation, VR is completely unrelated, Web3 on HN is a derogatory term leaning off the assumption that it’s focus is NFTs and VR video games.

Free speech is about free expression of ideas; nothing more or less specific.