this post was submitted on 07 Mar 2025
281 points (97.6% liked)

Buy European

5229 readers
1991 users here now

Overview:

The community to discuss buying European goods and services.


Matrix Chat


Rules:

  • Be kind to each other, and argue in good faith. No direct insults nor disrespectful and condescending comments.

  • Do not use this community to promote Nationalism/Euronationalism. This community is for discussing European products/services and news related to that. For other topics the following might be of interest:

  • Include a disclaimer at the bottom of the post if you're affiliated with the recommendation.

  • No russian suggestions.

Feddit.uk's instance rules apply:

  • No racism, sexism, homophobia, transphobia or xenophobia
  • No incitement of violence or promotion of violent ideologies
  • No harassment, dogpiling or doxxing of other users
  • Do not share intentionally false or misleading information
  • Do not spam or abuse network features.
  • Alt accounts are permitted, but all accounts must list each other in their bios.

Benefits of Buying Local:

local investment, job creation, innovation, increased competition, more redundancy.

European Instances

Lemmy:

Matrix:


Related Communities:

Buy Local:

Continents:

European:

Buying and Selling:

Boycott:

Countries:

Companies:

Stop Publisher Kill Switch in Games Practice:


Banner credits: BYTEAlliance


founded 2 months ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
[โ€“] [email protected] -3 points 1 month ago (1 children)

Devs are aware. This was a quick n dirty prototype and they alright knew the issue with using chatgpt. They did it to make something work asap. In an interview (Danish) the devs recognized this and is moving toward using a LLM developed in French (I forget the name but irrelevant to the point that they will drop chatgpt).

[โ€“] [email protected] 40 points 1 month ago (2 children)

If that's their solution, then they have absolutely no understanding of the systems they're using.

ChatGPT isn't prone to hallucination because it's ChatGPT, it's prone because it's an LLM. That's a fundamental problem common to all LLMs

[โ€“] [email protected] 25 points 1 month ago (1 children)

Plus I don't want some random ass server to crunch through couple hundred watt hours if scanning the barcode and running that against a database would not just suffice but also be more accurate.

[โ€“] [email protected] 15 points 1 month ago (1 children)

More accurate, efficient, environmentally friendly. Why are we trying to solve all of this with LLMs?

[โ€“] [email protected] 3 points 1 month ago (1 children)

Its easier to program I suppose, just setup a prompt and give back the result of that

[โ€“] [email protected] 1 points 1 month ago

Exactly, developers can't just come up with a complete database of all products in existence and where they come from, whereas LLMs are already trained on basically all data that is available on the Internet, with additional capabilities to browse the web if necessary. This is a reasonable approach.

[โ€“] [email protected] 0 points 1 month ago (1 children)

phi-4 is the only one I am aware of that was deliberately trained to refuse instead of hallucinating. it's mindblowing to me that that isn't standard. everyone is trying to maximize benchmarks at all cost.

I wonder if diffusion LLMs will be lower in hallucinations, since they inherently have error correction built into their inference process

[โ€“] [email protected] 4 points 1 month ago

Even that won't be truly effective. It's all marketing, at this point.

The problem of hallucination really is fundamental to the technology. If there's a way to prevent it, it won't be as simple as training it differently