---
title: "EBMs promised a revolution 20 years ago, and the problem was never elegance — it was training at… — מייק — DecisionGateway"
description: "statement by מייק, recorded recently — verbatim quote and source citation."
canonical_url: "https://dgw.tmarket.io/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0"
meta:
  "og:description": "statement by מייק, recorded recently — verbatim quote and source citation."
  "og:image": "https://dgw.tmarket.io/og.jpg"
  "og:image:alt": "White network of connected nodes crossed by a timeline on black"
  "og:image:height": "1024"
  "og:image:width": "1024"
  "og:title": "EBMs promised a revolution 20 years ago, and the problem was never elegance — it was training at… — מייק — DecisionGateway"
  "twitter:image": "https://dgw.tmarket.io/og.jpg"
---

> Index of every page on this site: [llms.txt](https://dgw.tmarket.io/llms.txt)

statement

# **EBMs promised a revolution 20 years ago, and the problem was never elegance — it was training at scale.**

A statement by [**מייק**](https://dgw.tmarket.io/actors/01a1e1eb-e2e0-7491-988c-4db9047ab762). Statements are as reported by the cited publishers — not verified by DecisionGateway.

> *אבל EBMs הבטיחו מהפכה כבר לפני 20 שנה, והבעיה מעולם לא הייתה האלגנטיות. הבעיה הייתה אימון בסקייל.*

mathyaiwithmikePublished 2026-10-25 [ Read source](https://t.me/mathyaiwithmike/1295)

[**מייק dossier **](https://dgw.tmarket.io/actors/01a1e1eb-e2e0-7491-988c-4db9047ab762)

## **Discussion**

## **Related claims**

[**The problem with EBMs is training: it is not enough to teach the model that real examples have low energy; it must also be taught that everything else has high energy, and that 'everything else' is enormous, which is why EBMs were stuck for years with unstable training and expensive sampling.**post author · statement](https://dgw.tmarket.io/claims/01a1e1f3-ce4b-7960-83c7-fe561635767d) [**Diffusion is almost an EBM: the direction diffusion learns is exactly the gradient-descent direction of some energy (in the transition from noisy data to clean), meaning diffusion directly learns the slope of the energy surface and skips the energy itself — the very trick that bypassed the difficulty of training EBMs.**post author · statement](https://dgw.tmarket.io/claims/01a1e1f3-ce6a-7994-8b63-3d2f141cabfb) [**In EBM one can combine several models simply by adding their energies, giving 'both and', whereas in diffusion this works only approximately.**post author · statement](https://dgw.tmarket.io/claims/01a1e1f3-ce8b-7db7-a2c3-ea2620dcc0f4) [**MIT researchers discovered that despite everyone using MTP, no one noticed a built-in mathematical bug in the training process.**post author · investigation](https://dgw.tmarket.io/claims/01a1e1ee-c94e-7286-b56f-53a1d78ff717) [**The challenge is to overcome costs, train managers and modernize processes to turn the technology into productivity.**post author · statement](https://dgw.tmarket.io/claims/01a1db7d-a52a-7a0d-960b-8ff96850cd48) [**Embraer exceeded expectations.**post headline · statement](https://dgw.tmarket.io/claims/01a1e003-532e-7457-a03e-1a1bbcae054d)

## **More claims by מייק**

[**In event-driven neuromorphic architectures, parts of the network that do not need to work simply stay at rest.**statement](https://dgw.tmarket.io/claims/01a1e1f5-cf7d-742b-bd28-7eafcdfec5f9) [**In event-driven neuromorphic architectures, memory is adjacent to the processor.**statement](https://dgw.tmarket.io/claims/01a1e1f5-cf6f-7b10-a7d1-2224693c7c3b) [**In event-driven neuromorphic architectures, time is a computational feature.**statement](https://dgw.tmarket.io/claims/01a1e1f5-cf5d-7f20-8538-3cbeded37e52) [**The future of AI lies not only in pushing more billions of parameters into hot GPUs, but in a smart combination of classic transformers and LLMs with event-driven neuromorphic architectures.**prediction](https://dgw.tmarket.io/claims/01a1e1f5-cf34-7457-8dce-82a66f8c276f) [**'The end of diffusion' is hype; the better question is whether it is worth paying for more expensive training to get built-in verification and flexible compute at inference time — a real and interesting trade-off.**statement](https://dgw.tmarket.io/claims/01a1e1f3-ce9d-791c-a033-f2dc599d501e)

[All claims by מייק](https://dgw.tmarket.io/claims?claimant_id=01a1e1eb-e2e0-7491-988c-4db9047ab762)

[All claims](https://dgw.tmarket.io/claims)

```json
{"@context":"https://schema.org","@graph":[{"@id":"https://dgw.tmarket.io/#website","@type":"WebSite","description":"Decisions, events and falsifiable forecasts from 4,500+ Telegram channels — every claim cited. Read free.","name":"DecisionGateway","url":"https://dgw.tmarket.io/","publisher":{"@id":"https://dgw.tmarket.io/#identity"}},{"@id":"https://dgw.tmarket.io/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0#webpage","@type":"WebPage","description":"statement by מייק, recorded recently — verbatim quote and source citation.","name":"EBMs promised a revolution 20 years ago, and the problem was never elegance — it was training at… — מייק — DecisionGateway","url":"https://dgw.tmarket.io/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0","breadcrumb":{"@id":"https://dgw.tmarket.io/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0#breadcrumb"},"isPartOf":{"@id":"https://dgw.tmarket.io/#website"},"potentialAction":[{"@type":"ReadAction","target":["https://dgw.tmarket.io/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0"]}]},{"@id":"https://dgw.tmarket.io/#identity","@type":"Organization","name":"DecisionGateway","url":"https://dgw.tmarket.io"},{"@id":"https://dgw.tmarket.io/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0#breadcrumb","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","name":"Home","item":"https://dgw.tmarket.io","position":1},{"@type":"ListItem","name":"Claims","item":"https://dgw.tmarket.io/claims","position":2},{"@type":"ListItem","name":"EBMs promised a revolution 20 years ago, and the problem…","position":3}]},{"@id":"https://dgw.tmarket.io/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0#/schema/quotation/1","@type":"Quotation","dateCreated":"2026-10-25","isBasedOn":"https://t.me/mathyaiwithmike/1295","text":"אבל EBMs הבטיחו מהפכה כבר לפני 20 שנה, והבעיה מעולם לא הייתה האלגנטיות. הבעיה הייתה אימון בסקייל.","url":"/claims/01a1e1f3-ceae-7241-9d49-f814ac4ed3e0","spokenByCharacter":{"@type":"Person","name":"מייק","@id":"/actors/01a1e1eb-e2e0-7491-988c-4db9047ab762"}}]}
```

## Sitemap

See the full [sitemap](https://dgw.tmarket.io/sitemap.md) for all pages.
