Exactly, also the ECJ is horribly corrupt (search for the corruption scandal revealed by a French journalist few years ago). Nothing happened back them.
This will never become law in my country(Poland). Last time they tried to push it people protested in the millions.
Recently I started getting messages from Clause Code (on a plan). "You're restoring an old session are you sure you don't want to compress the context? This will use a substantial amount of your usage quota"
The author mentions lack of good Web search. I've been using slightly modified crawl4ai and searXNG together with firebase for the rare sites that insist on throwing wrenches in the works of my LLMs.
I also have my fork of metamcp that replaces firebase MCP spec with my own that tells the model to use crawl4ai and SearXNG instead.
I've been using this wia Librechat with every commercial and open weight model I tested.
The search is way better than OpenAI and what ClaudeCode uses, but Gemini is way faster. That will change soon as I'm planning to put these instances in a DC with gigabit pipe.
Firebase is not cheap, but it retrieves everything, bypasses captchas and so on.... As long as one uses it for 1% of Web queries the cost is manageable.
There are no books banned in EU... Some countries have laws that criminalise glorification of nazism or communism, but I never heard any book was "banned" as a result.
Here in Poland we had "Mein Kampf" by certain Austrian painter in my primary school library for example.
Serious programming is dealing with a large knowledge surface area.
So not "implement me a shading algorithm"
But more like: make an multi user app running on a k8 cluster, design the whole thing to be indempotent, scalable, easy to deploy remotely via ipmi/pxe boot.
Then see how it makes stupid mistakes along the way.
Today's AI is pretty amazing when it comes to fixing narrow problems (or creating Web apps with no infra). Give it anything where it needs to go online, download some helm templates and look through them to figure out parameters, as well as write an app and it will make lots of mistakes in seemingly simple stuff.
Opus seems to be the model that works the best with this.
I think there is no reasonably priced machine you could run locally to do serious work with LLMs...
10x rtx6000 Pro in a large workstation is probably the way to go for someone wanting to run GLM5.2.
Other than that it is cloud.
As good as these small models got we are still not "at breakeven" for me.
What is "breakeven" with LLMs? For me it is when I no longer have to read the actual code it wrote. I can trust that if I told it to implement and document a certain architecture it actually did that with no stupid mistakes.
The first model ever that did that for me was the first opus. 4.4 if I remember correctly.
The second model was Gemini 3 Pro preview. For few weeks. Then it was lobotomised. I guess it was too expensive to run and they quantized it too hell.
Only Opus remains. If this GLM model truly rivals even an old opus I'll be very happy when day comes that I'll be able to run it locally.
If we programmers united we had a clouded code alternative that didn't suck :-)
But we're not far.
My requirements:
- a terminal app without advanced tui, not written like "a browser running in a terminal" or a game. There is no need to overcomplicated.
- ability to manage prompts per model, compress context using alternate models, and minimise token costs better - like the YouTube's Sentdex's Minion mini harness (in fact I'm building on top of his as we speak).
- support for agent work fanout
- support for MCP, but switchable off/on depending if needed (I use a single MCP aggregator anyway so mcp tool use doesn't eat my context)
- support for lsp/tree-sitter, again switchable when needed.
- support for OpenAI api and written easily enough so other ones like deepinfra are easy to add.
Nice to have:
- have some sort "prompt library" that would store tweaked versions of prompts for different models so it adjusted the harness as needed depending on which model we call.
Has anyone compared the costs between maxing out a Claude Max x5 subscription (one for €120 euro a month) and same amount of work on GLM5.2 via API at a cost of $4 per mln token out?
I have a feeling Anthropic may still come out cheeper (mainly thanks to enterprises subsidising the Max subscriptions).
But I'm very excited with the possibility of using fully EU based inference rivalling Opus in quality.
It was surprising to see incidence of death by cesarean is almost 13 per 100k. It is commonly thought as the safest way and half of all births in my country are via cesarean.
These companies seem to be led by mind bogglingly short sighted people. Maybe they should be replaced by AI. It can't possibly get any worse than now, right?
> Eventually, when all your savings are burned through, when you might need to sell your house, you really wonder if that's what they wanted and if all that was worth it.
I will never accept a country where things like this happen routinely as civilised.
This will never become law in my country(Poland). Last time they tried to push it people protested in the millions.