Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Mistral AI Releases Forge

mistral.ai

Post reply on HN
Print view View original

81–90 of 210 posts

Re: Mistral AI Releases Forge

#81

Post by ithkuil »

Centigonal wrote: post #54
zby wrote: post #52

My bet is that the solution to continuous learning is with external storage. There is a lot of talk about context engineering - but I have not seen anyone taking context as the main bottleneck and building a system around that. This would show that even context engineering is kind of wrong term - because context does not enter the llm in some mysterious way - it goes through prompt and the whole model of passing chat…

What do you mean when you say "external storage?"

A form of context engineering

Re: Mistral AI Releases Forge

#83

Post by sunaookami »

schubidubiduba wrote: post #68
jstummbillig wrote: post #65

Earlier quoted context omitted.

Why would that be? Most big EU companies use ms teams or google workspace, for example.

They use those because the decision to use them was made years ago. Things have changed since then

No they haven't. Every company just buys ChatGPT Enterprise.

Re: Mistral AI Releases Forge

#85

Post by menaerus »

charcircuit wrote: post #80
menaerus wrote: post #78

Earlier quoted context omitted.

Even that doesn't make sense. Why would you not build a vector database to complement your RAG engine?

For coding use cases you may want a way to search for symbols themselves or do a plain text exact match for the name of a symbol to find the relevant documents to include. There is more to searching than building a basic similarity search.

Sorry but who mentioned coding as a use-case? My comment was general and not specific to the coding use-case, and I don't understand where did you get the idea from that I am arguing that building a similarity search engine would be a substitute to the symbol-search engine or that symbol-search is inferior to the similarity-search? Please don't put words into my mouth. My question was genuine without making any presumptions.

Even with the coding use-case you would still likely want to build a similarity search engine because searching through plain symbols isn't enough to build a contextual understanding of higher-level concepts in the code.

Re: Mistral AI Releases Forge

#86

Post by copirate »

dash2 wrote: post #49

I think it’s interesting what this approach suggests about who will profit from AI. I’m sceptical that having huge numbers of GPUs is a moat. After all, real humans – even geniuses – are trained on much much less data than the whole Internet. But proprietary and specialised data could very well be a moat. It’s hard to train a scientist/lawyer/analyst without reading a lot of science/law/finance. Companies’ proprietar…

> After all, real humans – even geniuses – are trained on much much less data than the whole Internet.

It's certainly different data, but one could argue that real humans have been trained on 3.5 billion years of evolution data.

Re: Mistral AI Releases Forge

#87

Post by Manfred »

kioleanu wrote: post #71

I like Mistral, it hits the exact sweet spot between cost and my data staying in the EU, withouth a significant drop in quality, but man are their model naming conventions confusing af. They mention they have a model called Devstral 2, which is neither Codestral nor Devestral. I want to use it, but the api only lists devstral-2512, devstral-latest, devstral-medium-latest, devstral-medium-2507, devstral-small, devstra…

I had the same experience. It's even more confusing when you want to create an API key because they are separated by product, maybe?

Re: Mistral AI Releases Forge

#89

Post by hk__2 »

schubidubiduba wrote: post #68
jstummbillig wrote: post #65

Earlier quoted context omitted.

Why would that be? Most big EU companies use ms teams or google workspace, for example.

They use those because the decision to use them was made years ago. Things have changed since then

Not at all. We continue taking that decision today.

Re: Mistral AI Releases Forge

#90

Post by kioleanu »

Manfred wrote: post #87
kioleanu wrote: post #71

I like Mistral, it hits the exact sweet spot between cost and my data staying in the EU, withouth a significant drop in quality, but man are their model naming conventions confusing af. They mention they have a model called Devstral 2, which is neither Codestral nor Devestral. I want to use it, but the api only lists devstral-2512, devstral-latest, devstral-medium-latest, devstral-medium-2507, devstral-small, devstra…

I had the same experience. It's even more confusing when you want to create an API key because they are separated by product, maybe?

no, the key is actually universal, you can't choose a specific product
Post reply on HN