That is the current standard. But it is hard for agents to read efficiently. To access JSON-LD, an agent must download the entire HTML page. This creates a haystack problem where you download 2MB of noise just to find 5KB of data.
Even then, you pay a syntax tax. JSON is verbose. Brackets and quotes waste valuable context window. Furthermore, the standard lacks behavior. JSON-LD lists facts but lacks instructions on how to sell (like @SEMANTIC_LOGIC). CommerceTXT is a fast lane. It does not replace JSON-LD. It optimizes it.
That solves bandwidth. It fails on tokens.
JSON syntax is heavy. Brackets and quotes consume context window.
More importantly, Schema.org is a dictionary of facts. It lacks behavior. It defines what a product is, but not how to sell it.
It has no concept of @SEMANTIC_LOGIC or @BRAND_VOICE. We need a format that carries both data and instructions efficiently. JSON-LD is too verbose and too static for that.
JSON is lean for data exchange between machines.
But in the LLM economy, the currency is tokens, not bytes.
To an LLM tokenizer, every bracket and quote is a distinct cost. In our tests, this 'syntax tax' accounts for up to 30% of the payload.
We chose a line-oriented format to minimize overhead and maximize the context window for actual commerce data.
Who says you need to pipe the entire document with JSON-LD directly into the context window? I agree, that is very wasteful. You can just parse the relevant bits out and convert the JSON-LD data into something like your txt format before presenting it to the LLM. Bake that right into whatever tool it uses to scrape websites.
That solves the Token Tax. It fails the Bandwidth Tax.
To get that JSON-LD, you still download 2MB of HTML. You execute JS. You parse the DOM.
You are buying a haystack to find a needle, then cleaning the needle. We propose serving just the needle.
Furthermore, JSON-LD is strictly for facts. It cannot express @SEMANTIC_LOGIC. It lacks the instructions on how to sell.
> If society no longer values these qualities, then we don't deserve better.
Isn't it more like "if society has time to think about and can afford those qualities"?
If most folks out there have limited finances (CoL-relative, of course) and are just scrapping by, they'll buy the cheapest thing out there that just does the job (vacuums) and tend to ignore any extra luxuries, even if those would be more economically advantageous long-term (repairs/maintenance part of the TCO). That's simply because of the focus - it's more on the account balance, due bills and next paycheck, than on the implications for a more distant future. Crazy volatility and all the global rollercoasters like pandemics, wars, and all the crazy politicians around the world doesn't help regular folks' sensible decision-making at all, of course. The more stressed one is, the less rational they act.
People don't buy cheap junk because they don't value quality. They buy it primarily because of affordability reasons, or because their focus is forced to be elsewhere.
>People don't buy cheap junk because they don't value quality. They buy it primarily because of affordability reasons, or because their focus is forced to be elsewhere.
The focus, thanks to years of advertising, is shifted towards features, new features sell, quality doesn’t, so to keep the price point and “innovate” manufacturers need to lower the quality knowing that a new version will replace the device soon, most consumers see this as normal so when a poorly designed and cheaply made thing for what there’s no replacement parts , no repair info, no software/ firmware fails is just an excuse to purchase the new shiny iteration with all the the bells and whistles (and AI!, copilot toaster!) wich is gonna last les than the previous one but now needs an “app” an activation and a subscription for the premium features .
Energy prices? Unit labour costs? Pisa Scores? VC Investments as percentage of GDP? Number of IPOs? Taxation of Income? Punctuality of public transport?
As far as I understand, the VW Amarok is based on the Ford Ranger, the VW T7 Transporter (their Commercial vehicle) is based on the Ford Transit Custom. The T7 Multivan and California are still built on their own VW platform.
It seems a lot of blame is put on regulation when there is also a lack of a "can do attitude" or a sense or urgency that procedures that might have been okay to take a couple of years in the past have to happen much more quickly nowadays.
The lack of can-do-attitude can be explained by regulations, imho. After you've seen the first few trivial things take ages because somebody has yet to stamp form 23b in triplicate and hand in 1k pages of environmental impact assessment, noise studies and socio-economic impact predictions, you loose the belief that you can do anything here. After you've been stonewalled by a few bureaucrats over a missing comma in their particular interpretation of subsection b12 subparagraph d footnote 11, you start going about your days looking for excuses not do to any work as well. After several people have cited "liability" and "legal risk" as arguments against babysitting their neighours cat for a day, you might start fearing that nebulous liability thing yourself.
The whole culture is poisoned by regulations imho.
Previous poster got a point though. Yes regulations are ridiculous thanks to every German and every EU government piling on more crap.
Zero argument there. 100% true.
But its also true that things CAN get through regulations. 1000 pages of environmental impact assessment takes time. But it doesn't take years. Things can be done in parallel if someone actually gave a fuck.
Sadly no one does because by the time anything starts 2-3 new governments/administrators/mayors have been in place. And people don't like to work on things someone else already took credit for.
> 1000 pages of environmental impact assessment takes time. But it doesn't take years.
Oh, but it does. For example, if there is a suspected hamster population, you need at least one year of data gathering to assess local population state. And then you need a resettlement plan for the hamsters. This alone takes at least a year because of the data gathering, and of course you need an expensive and busy hamster expert to do the gathering and writing.
Oh, and btw, that's just for permitting. After you get your permit, you have to have those hamsters professionally resettled, observed and documented.
You are right that it is theoretically still possible to get stuff done. Prime example is Elon Musks Gigafactory in Brandenburg, where there was enough political and economic pressure to get it done. But that is a rare thing to happen, and lots of those steps you have to do are out of your control and up to some bureaucrat who is of course "very busy" and "cannot at this time give an estimate as to when the permit might be completed". It is just hard to convey how bad it really is...
I'm glad for any initiative that leads to less crap reaching the markets that is either dangerous or has a shelf life of a few months before breaking down. The EU as a whole will become even less competitive if we don't re-gain some level of quality awareness and place quality at the center of the things we consume and produce.
This should not be understood as anti-China but should apply to all products on the EU market. China has some well-respected quality-conscious consumer brands (e.g. Hifiman, Fenix Lights, DJI, Anker, Govee...) but it seems a lot of smaller companies there put easy revenue over any concerns for quality.
I want to emphasise your latter point - I have a Lenovo work laptop, Fenix head torches and various other high quality Chinese products. Any company selling into the EU needs to meet the QC and regulatory requirements, and many well known Chinese brands already do so, and so their products naturally sell at a premium to the cheapest options. A little more thought in purchasing by buyers would go a long way in helping the commissions efforts to reduce harmful goods.
reply