csallen

Yeah I thought so too, just didn't want to overstate it. So actually, a pretty big reason not to use an open-source harness if you're using a big lab's model.

I'm responding to a comment, not to article, and the comment is asking about open source harnesses, presumably in comparison to all non-open source harnesses, not just in comparison to Cursor.

1. A lot of people already have Claude Code set up, and it's easier to keep using that than to install something new.

2. Lots of people are used to Claude Code's interface/commands/etc. and don't feel like paying the cost of learning something new. The benefits would have to outweigh those switching costs, and it's unclear that they do.

3. Claude Code already works with your Claude MAX subscription[0], which gives you an incredible amount of usage of the top-tier models for cheap, which can't be matched by any open-source options. And most people won't exhaust this usage, so they have no real need to use open-source models.

4. Although it's hard to 100% confirm this, there's reason to believe that Claude itself works better with Claude Code than with other harnesses.

5. There's no real lock-in. If tomorrow you decide you don't want to use Claude Code, you can just switch to something else ezpz. So there's no reason to worry that you're digging a hole and locking yourself in. Thus, there's no urgency to switch away.

[0] Yes, open-source harnesses can use your Claude MAX subscription, but does this "benefit" of open-source harnesses really outweigh the costs of #1, #2, and #4 above?

What's your reasoning? What makes Claude Code better? Genuinely curious to learn.

> dot, bot, and duet

And Meta Muse

> I'm still not sure why I'd pick one where I'm locked into a specific model family

I'm guessing mostly because they subsidize a lot of the costs

If that's all true then it's almost certainly because you work at a large, mature, bureaucratic, unusually privacy-focused company. Verrrrry few companies work like this when they're small and new. I'd round down to ~0%. And I would bet that, if your company was ever a small startup, it didn't work like this back then, either.

Also, this idea that it's bad or weird to anonymously discuss customers is strange. I've known cops, doctors, dentists, and all sorts of other people who routinely share stories about weird things that happen with people and customers at work, anonymously. This is the norm in the world and always has been.

It's also the norm for the companies who own your data to look at it, when asked to. What do you think customer support even is?

It's only really a small corner of the tech world that treats these things as strange and sacrilege.

Two reasons:

1. Product decisions require far more knowledge than coding and architecture decisions, and that knowledge is harder to come by. It often requires research, talking to customers, understanding the organization of the company, the company's mission, the company's employees, their performance, stakeholders, the competitive landscape, funding, growth/sales/marketing strategies and budgets, customer buying patterns, company strategy, etc. Not to mention the code, the coding backlog, etc. Companies have to compete in a hostile, competitive, capitalistic market, which means they're trying to beat other companies, which means a seemingly very good product decision can actually be bad solely because other people are doing it better. Imagine if your perfectly functional code failed to compile simply by nature of the fact that better programmers exist.

2. Product design requires taste, and taste is partly a function of novelty, but there aren't that many LLMs, so everyone's using the same few LLMs, therefore everyone's getting the same designs, therefore the designs look like clones of each other rather than novel thoughtful design, therefore they fail the taste bar. In addition, LLMs simply weren't trained on good vs. bad visual or product design nearly as much as they've been trained on good vs. bad, functional vs. non-functional code.

It's a movie with at least one surprising twist, which seems to be fairly central to enjoying the experience, and people who've seen it don't want to spoil it for others. Hence they're vague in their descriptions. It's as simple as that.

I clicked the story just to see the very ugly bridge in question, and it turned out I think it's quite attractive

Corporations are generally protected by limited liability laws, and for good reason, because in the world before that was the case, there was a massive amount of disincentive to ever start a corporation, to do research, to experiment, to release new products and services, etc., because you could be sued into oblivion for the smallest things or even go to jail. Which happened all the time.

Obviously there are upsides to that too. It leads to more accountability. But there are downsides which include having a world with less innovation, less technology, and more expensive technology. Generally, the mass is when, when there's more businesses competing to create ever better and cheaper products. So there's a tradeoff there. And it's very difficult to draw the line at the perfect point.

There are countless cases of executives going to jail when they've crossed that line, beyond reckless experimentation and into willful negligence or harm. Still, I think we would mostly all agree that the line has been pushed too far in the other direction.People are incentivized, if they're running corporations, to lobby and try to push this line as far as possible in order to provide cover for themselves, and that's the problem with money playing such a big role in politics.

But still, it's a bit silly to be comparing this to your own personal responsibilities with your car. There's pretty much no societal benefit to creating laws that protect people from being reckless with their own possessions.

As I said at the end of my comment, unless you're an AI researcher pushing the bound of what LLMs can do. I don't think most of us are running ten million dollar AI swarms with unreleased models that are escaping their sandboxes. That's research, not software engineering, and this discussion is about whether or not software engineers can reasonably expect to understand their LLM generated code.

Also, for what it's worth, LLM research is hardly the first scientific research to have accidents with negative external consequences.

I mean it could be, sure. But I think people are generally speaking more careful with higher stakes code than they are with lower stakes code. I know a lot of people who are YOLO'ing it with LLMs, but who ask for more understanding, more reviews, more tests, etc., in trickier areas. Which is only natural. Just like people are more careful when carrying a baby than when carrying a pillow.

(Yes, there will be individual exceptions to this, just like with everything else in life.)

> I see no reason to believe that people are going to be thoughtful about LLM-generated code.

I think that's true for low value code. But the more important and crucial and high-stakes code is, the more effort people put into it, generally. Even with LLMs.

> Never as good pay and many end up on the system.

I mean, every complex large-scale change to society has upsides and downsides. Very few things are purely good. So it makes very little sense just to name the upsides and pretend it's all good, or just to name the downsides and pretend it's all bad. You need to do the actual cost-benefit analysis.

And when you do, net-net, generally speaking, technological progress does does much more good for humanity than bad, even though there is some bad.

We tend to get things that make our lives easier, more efficient, safer, and more comfortable at ever cheaper prices.