Why do we need to train the model to solve for retrieval within the org, so we have to keep training it whenever new dataset is introduced , or am I missing something here ?

It's a matter of cost. Did you see the 100x cheaper?

If you have a workload that is going to be very heavy, incurring a large training cost to make a cheaper model work well with the dataset will be dramatic cost reduction. Most large AI workloads can't afford, or truly need, the expense or capability of GPT 5.6 Sol when cheaper models can do.

Of course you could skip that and just use GPT-5.6 Sol everywhere instead. If you're running a fast food restaurant you could hire Michelin star chefs to make your burger and fries without further training. Or you could have a training program for teenagers, a sourcing program, etc. to scale up to your chain to still get consistent quality without needing that level of cost in each store, but replacing it with a centralized repeatable process.

(founder of castform here) the model you post-train should ideally learn general patterns & search strategies over your dataset that should transfer to new docs you add to the search corpus (unless its super out of distribution)

i'm a little confused by this, should most piles of company documentation look pretty similar? what are we getting by tuning at the org level?

what if you have a bunch of teams or apps that have different documentation patterns?

how much does this degrade over time, it beats leading models with that static data set but clearly this edge will degrade with data drift, how quickly does that happen?

also, any "this is 100x cheaper" blogpost means nothing if not discussing TCO (I know your team didn't write this.) I don't care what inference costs are if I don't know training/overhead costs. what's the breakeven point. and again, how long is this RAG stack going to be worth keeping, you beat 5.6 Luna but at some point un-tuned models will beat you, so this is a temporary solution that needs to be re-upped at some point. benchmarks against data drift would help there

very useful questions here!

- if you have teams that have totally different documentation patterns, yes i think a model trained one teams' docs probably won't directly transfer to another. but let's say you have a model trained on SEC 10-K filings, it should work well as new 10-K filings are added (since terminology & structure of these docs are similar) - on TCO, the training costs for the experiments you saw were <$200 - you bring up a good point on data drift, don't have concrete numbers/experiments here. something we should defn look into (though i imagine this also changes a lot based on use-case and company)

could you share more about what you mean by "general patterns & search strategies"? I can think of it being along the lines of searching over specific tables or databases for queries in certain context. It's an exciting line of work and I'm interested because I need something like this for the problem I'm solving atm. So, I'd like to understand how the training generalizes

yup! it’s mostly about getting better at using the right search keywords.

for more complex multi-hop question, it's also about knowing which sections of a document to look up and in what order.

Only thing which bothers me about over-the-ear headphones is the hot climate. How are they in the hot climate of Singapore, where it's very humid?

All the best , I always wanted to build something like this for myself.

Maltitol is a bit different, because it is actually quite caloric. It just digests slower.

Idk whats the point of eating a protein bar as an occassional treat? They taste like shit but have high protein. If youre gonna have an occasional treat, have an actual treat. A cookie or snickers or something

They didn’t give you any indication of their rate of consumption. Why are you making assumptions?

I am not sure about how other Whatsapp MCP servers build , but I like the design here : Go server to integrate with Whatsapp , scan the QR etc which acts like a bridge and lightsql to store some data APP MCP server : To interact with the data , app and LLM

Pardon my ignorance , how is it different from MCP servers and having a supervisor agent selecting and executing the right MCP tool

Not ignorant at all! This is our favorite question. MCP is taking a stateful approach, where every client maintains a 1:1 connection with a server. This means that for each user/client connected to your platform, you'd need a dedicated MCP server. We're used to writing software that interfaces with APIs, as stateless and deployment agnostic. agents.json keeps it that way.

For example, you can write an web-based chatbot that uses agents.json to interface with APIs. To do the same with MCP, you'd spin up a separate lambda MCP or process MCP server for each user.

All the best , let me check this out

I am collaborating with a group of veterinarians to address pet health concerns.

Assuming that AI adoption is more prevalent in the technical domain, could this be one of the reasons why it is leaning towards computer and technical usage?

Maybe not directly related , I find genertic algorithms and other optimisation algorithms such as Ant Colony Optimisation algorithms intersecting with this approach of self-play and leading to robust autonomy.

True , for the matter if jsut like a privacy feature , we can turn off certain features which are not required and it can significantly maintain the battery. Yes, we do have Iphone battery power save mode but I am just curious how efficiently it can optimise battery power saving