# JEV's training pipeline is built around explicit trade-offs

Markdown copy of https://realalpha.app/s/jevs-training-pipeline-is-built-around-explicit-trade-offs/ on Real Alpha, the best minutes from long interviews with the people building AI. Cite and link the page, not this copy.

- Speaker: [Diogo Almeida](https://realalpha.app/builders/diogo-almeida/) · Diogo Almeida is co-founder and CEO of TypeSafe. · Built Jev, a decision model returning typed probabilities; co-invented RLHF and InstructGPT at OpenAI.
- Host: [Sam Charrington](https://realalpha.app/people/sam-charrington/) · Host, The TWIML AI Podcast
- Show: The TWIML AI Podcast
- Episode: [Asking JEV's Creator the Hard Questions About This Hot New AI Model](https://realalpha.app/v/9Aato-NfjoU/), Oct 6, 2026
- Moment: 39:05 to 43:50 of the episode (5 min), playing on https://realalpha.app/s/jevs-training-pipeline-is-built-around-explicit-trade-offs/; the episode from there: https://realalpha.app/v/9Aato-NfjoU/?t=2345

## Quote

> “figure out the North Star, figure out what you're willing to trade off and **remove all the stuff** that is useless for that trade-off”
> — [Diogo Almeida](https://realalpha.app/builders/diogo-almeida/) at [41:45](https://realalpha.app/v/9Aato-NfjoU/?t=2505) · The TWIML AI Podcast

## Takeaways

1. JEV uses multiple open-weight models rather than one base model.
2. TypeSafe intentionally gives up some string-generation ability.
3. Choose a target, define trade-offs, then remove irrelevant components.

## About this segment

Diogo Almeida says TypeSafe combines open-weight models and removes components tied to capabilities it is willing to give up. The pipeline follows a chosen target and its trade-offs rather than preserving general text generation.

From “Asking JEV's Creator the Hard Questions About This Hot New AI Model”, Oct 6, 2026. [Watch the full episode](https://realalpha.app/v/9Aato-NfjoU/)

## Transcript

Transcribed by machine (Whisper) from the episode’s audio, so a word may be off here and there.

[39:10](https://realalpha.app/v/9Aato-NfjoU/?t=2350) Is it a post-train of something else? Is it a ground-up thing? Like, what can you tell us about this thing? I will answer this in a way that is, like, overly precise. Back before RLHF existed, post-training as a concept did not exist, right? Like, we as a team, we didn't name post-training, but, like, that we created the concept of post-training. At the time, fine-tuning existed, and people were like, are you just fine-tuning the model on strings?

[39:43](https://realalpha.app/v/9Aato-NfjoU/?t=2383) And by some definitions, we were fine-tuning the model, but we did a whole lot more, such that at some point it becomes misleading. so i would actually say that um just turning my oh there we go um i would say that calling it post-training is probably going to be seen as inaccurate in hindsight but the field doesn't have a terminology yet for what we are doing so uh that will probably be revealed more in the if you were to invent one right now what would you call it no one likes my ideas in the team um so i've said this elsewhere so i'm okay saying this but we okay back to bitter's lesson we because this is ml we care a lot about the north star and we are willing to do everything for it and i try to be as upfront about the trade-offs as possible and part of that trade-off is being a lot worse at string generation and even like the jev can chat stuff like it's very cute but

[40:43](https://realalpha.app/v/9Aato-NfjoU/?t=2443) it's obviously dumb uh like these are trade-offs we intentionally make so when designing the entire pipeline um post training was a lot easier on top of llms because the shape was very similar like it's strings here it's basically strings there technically there's some structure with like the chat ml format but it's mostly just strings you know so there's a lot of similarity in the stack what we're doing is we're actually like ripping out a lot of fundamental pieces and like rejiggering them and using pieces from other stuff so i have described it as a a frankenstein's monster of models um which i i haven't read the book but i've been told is at least innocent if not the good guy just to be clear because people are like don't call the model a monster and i'm like it's a good analogy though what's the foundational thing that you're applying this unnamed thing to is it like

[41:36](https://realalpha.app/v/9Aato-NfjoU/?t=2496) like an off-the-shelf Quen model or something? A lot of different open source models because they all have different trade-offs to them. So we are actually Frankensteining all over. But the important bit, if we want to be maximally precise and useful, is figure out the North Star, figure out what you're willing to trade off and remove all the stuff that is useless for that trade-off or that is needed for the thing you're giving up and hyper-focus on the thing that matters.

[42:01](https://realalpha.app/v/9Aato-NfjoU/?t=2521) And a lot of it will follow a la first principles with months of research sure but that's that's broad in general and to be concrete and specific it is interesting that like you didn't start from nothing like you started from llms and like transformers and like you're building on these building blocks that have established to be clear um i have said you did or did not i did not say transformers i did say open weight models slight distinction um which i would just want to be precise um so i think that oh man something i want to event well number one it's very obvious we haven't done pre-training like if we could pre-train better than the rest of the world with the budget we've had then um Um, the rest of the world is totally cooked.

[42:56](https://realalpha.app/v/9Aato-NfjoU/?t=2576) Um, like we, like, uh, I, I, I think free trading is not the most efficient thing in the world. And I, it's, it's, you know, exponentially more resources for. debatably linear gains seems very sublinear um it's kind of a bad deal in my opinion unless it's necessary um meaning we've kind of already boiled the ocean of content down into things that are kind of consumable by some downstream process why keep doing it unless you're doing something fundamentally different exactly so we are trying to focus more on like the 10x or more jumps that can be made. And we think that that can be very much done in a budget. Well, we obviously think that because we did. But I think that all AI companies should be held to that same bar