> The best anyone can hope for is a free market, with everything properly priced. But for decades, the American market has not been free. It’s used purposefully added friction to exploit a time asymmetry between the business and you. And due to things like call centers, this has been very profitable for the businesses. Cable companies and insurance rely on the fact that your time is more valuable than theirs. They can hire people in India at scale to waste your time.
The market actually is not very free, because large companies increasingly use their weight to pull off things that smaller companies or individual customers cannot afford: lobby to obtain preferences, tax exemptions, exclusive deals, other favors that violate or at least skirt the law.
But running a call center overseas is not one of these things.
As soon as we admit that humans are easily corrupted, the sooner we can stop finger pointing and start developing systems to mitigate the natural tendency toward corruption.
I cannot understand how any of the things you describe are not free. The government kowtowing to corporations is as free as it gets. No one said that just because the market is free that you personally wouldn’t end up holding the shit end of the stick
Free markets don't exist, or they only do for a very brief period of time. It's the same fundamental force behind why social hierarchies naturally form, and communism doesn't work in practice.
When governments kowtow to corporations, it's the corporations who are then acting as the government. For example, in states like Texas, Alabama, and Wisconsin, laws prohibit automakers from selling vehicles directly to consumers. But these laws only exist because dealer associations wanted and lobbied for them to protect their business. Which is to show that freedom itself isn't a matter of who is kowtowing to whom, but merely whether or not kowtowing is happening whatsoever. If it is, then someone's freedom is being restrained, and said market environment could be argued to not be "free". In fact, this is what Tesla has argued multiple times in court in such states in that these laws are anticompetitive, and violate due process and the commerce clause.
Hold up, there are two very different kinds of "free" that pop up, from mutually incompatible ends of a spectrum.
In the first, it's a "free" market because everything moves smoothly and efficiently in ways that make economic mathematicians happy. There's perfect information, all transactions and prices and actor-identities are are known, and it's generally assumed there are no monopolies or monopsonies.
In the second, individual actors are "free" to construct secret deals with special secret prices, non-disclosure agreements, act anonymously through proxies, etc.
At least in US politics, the equivocation is common: Someone appeals to the benefits of the first, while promoting the contradictory mechanics of the second.
The violence of the state makes the market not "free." Unless you want to abstract all the way out: the planet is and always has been run through violent coercion by psycopaths, and, as exampled by reality, they are "free" to do so.
But in the sense they mean, the violence of the state precludes a free market. For the record, I do not believe in the validity of money, coercion, usury, violence.
My understanding of the definition of a "free" market is it would have almost no external regulation.
However, a "unregulated free market" is nearly impossible--somw player will eventually drive out competition to maximize profits and some will not be troubled at harming or killing their customers in the name of immediate profit (tobacco, sugared drinks, talc powder, and round-up come to mind immediately but the list is very long).
Is market with enough regulations to ensure competitiveness and transaction transparency (including long-term consequences) truly "free"?
It comes down to what’s “free”: most people want that to mean freedom of choice for buyers but sellers want that to mean freedom from restrictions. Trying to balance the two depends critically on regulation because it’s too easy for larger players to reduce the choices for everyone else.
One popular desire is common, but not universal, in both groups: the freedom to lie, cheat, swindle those party to a transaction without consequence. It may help to consider that ‘the consequences of one’s actions’, such as lying or cheating in the above case, are viewed by many as a violation of their personal freedom from persecution (e.g. “it’s not my fault you didn’t stop me from conning you”); that extends to their participation in trade as well.
I assume that the pools of either corporate entities and/or their leadership cogs have a much higher percentage of adherence to said belief than the general pool of either buyers and/or sellers excluding such, as the corporate implementation of liability shielding exists specifically to sate this need.
I'm not recommending we build a frictionless plane, I'm just saying it doesn't have friction. This is the most politely I've ever been called a libertarian.
A "free market" is one in which all the participants of the market have perfect information and act completely rationally. This is, of course, an academic ideal, similar to solving a physics problem that tells you to ignore friction.
What we have is a "capitalist market", where those with more power (capital) within the market leverage it to exploit the other participants. Capitalists use their money to extract as much money as possible from a segment of the market, usually destroying it in the process. But for a beautiful moment in time they created a lot of value for shareholders!
Classic clickbait title. I guess it works, but also baits me to respond to it in the first paragraph: Issue tracking is clearly not dead, it is more important than ever.
They are doing almost everything right: I believe that this mode of control is exactly the future (use the chat for more complex natural language manipulation while seeing the result in the traditional UI).
> Code Diffs. Review code within a fast, modern interface built for both humans and agents to iterate together.
I really want to see diffs right in the issue. PRs are a dumb historically grown in-between step that is just annoying. As everything else becomes faster, this becomes more of a bottleneck for iteration speed.
> Linear Coding Agent. Linear writes code and automatically fixes bugs. Powered by frontier models, enhanced with native Linear context and tools.
Is this supposed to replace my dedicated coding agent? I’m skeptical of coding agents being built as parts of other products. It feels like an afterthought, 80% solution - not good enough for real intense use.
If it has very tight HITL (possibly integrated right into the ticket - that would be amazing), it might be really good - they are in a unique position to build an amazing product here.
Issue tracking is not only not dead, it’s a more structured way to handle your agents.
I find that the most respected writing about AI has very few signs of being written by AI. I'm guessing that's because people in the space are very sensitive to the signs and signal vs. noise.
And because people writing anything worth reading are using the process of writing to form a proper argument and develop their ideas. It’s just not possible to do that by delegating even a small chunk of the work to AI.
And usually both exist in document and lengthy communications. This gets what I wanted across with exactly my intention and then I can attach 10x length worth of AI appendix that would be helpful indexing and references.
> attach 10x length worth of AI appendix that would be helpful indexing and references.
Are references helpful when they're generated? The reader could've generated them themselves. References would be helpful if they were personal references of stuff you actually read and curated. The value then would be getting your taste. References from an AI may well be good-looking nonsense.
I agree wholeheartedly, I don’t see any balance in the effort someone dedicated to generating text vs me consuming it. If you feel there’s further insight to be gained by an llm, give me the prompt, not the output. Any communication channel reflects a balance of information content flowing and we are still adjusting to the proper etiquette.
Note, it's not one prompt (there aren't really "one prompt" any more, prompt engineering is such a 2023-2024 thing), or purely unreviewed output. It's curated output that was created by AI but iterated with me since it goes with and has to match my intention. And most of the time I don't directly prompt the agent any more. I go through a layer of agent management that inject more context into the agent that actually work on it.
It’s both! The core is implemented as a server and any UI (the TUI being one) can connect to it.
It’s actually “dumber” than any of your suggestions - they just let the agent explore to build up context on its own. “ls” and “grep” are among the most used discovery tools. This works extraordinarily well and is pretty much the standard nowadays because it lets the agent be pretty smart about what context it pulls in.
This is another one of OpenCode’s current weak points in the security complex: They consider permissions a “UX feature” rather than actual guardrails. The reasoning is that you’re giving the agent access to the shell, so it’ll be able to sidestep everything.
This is of course a cop-out: They’re not considering the case in which you’re not blindly doing that.
Fun fact: In the default setup, the agent can fully edit all of the harnesses files, including permissions and session history. So it’s pretty trivial for it to a) escalate privileges and then even b) delete evidence of something nefarious happening.
It’s pretty reckless and even pretty easy to solve with chroot and user permissions. There just has been (from what I see currently) relatively little interest from the project in solving this issue.
reply