EA Forum Podcast (Curated & popular)2 Feb

[Linkpost] “Evidence that Recent AI Gains are Mostly from Inference-Scaling” by Toby_Ord

This is a link post.

In the last year or two, the most important trend in modern AI came to an end. The scaling-up of computational resources used to train ever-larger AI models through next-token prediction (pre-training) stalled out. Since late 2024, we’ve seen a new trend of using reinforcement learning (RL) in the second stage of training (post-training). Through RL, the AI models learn to do superior chain-of-thought reasoning about the problem they are being asked to solve.

This new era involves scaling up two kinds of compute:

the amount of compute used in RL post-training
the amount of compute used every time the model answers a question

Industry insiders are excited about the first new kind of scaling, because the amount of compute needed for RL post-training started off being small compared to the tremendous amounts already used in next-token prediction pre-training. Thus, one could scale the RL post-training up by a factor of 10 or 100 before even doubling the total compute used to train the model.

But the second new kind of scaling is a problem. Major AI companies were already starting to spend more compute serving their models to customers than in the training [...]

---

First published:
February 2nd, 2026

Source:
https://forum.effectivealtruism.org/posts/5zfubGrJnBuR5toiK/evidence-that-recent-ai-gains-are-mostly-from-inference

Linkpost URL:
https://www.tobyord.com/writing/mostly-inference-scaling

---

Narrated by TYPE III AUDIO.

---

Images from the article:

Apple Podcasts and Spotify do not show images in the episode description. Try Pocket Casts, or another podcast app.

Denne episoden er hentet fra en åpen RSS-feed og er ikke publisert av Podme. Den kan derfor inneholde annonser.

Episoder(250)

“Let’s taboo the V-word” by lincolnq

“How long have you been v*g*n?” This is one of the most common icebreakers at animal protection events. It's a baseline assumption, and it mostly holds true: if you’re out advocating for animals not t...

14 Jul 12min

“Giving What We Can’s first YouTube Video is out now!” by JustinPortela

Hello! I'm Justin Portela. I got hired by GWWC to make YouTube videos after AI in Context did such a kickass job. My channel is using that same cinematic, high-production value beauty to talk about e...

9 Jul 1min

“I’m never satisfied” by Ajeya

Note: This post was crossposted from Planned Obsolescence by the Forum team, with the author's permission. The author may not see or respond to comments on this post. But we get the job done I was twe...

8 Jul 6min

“Maybe do the thing you wish CEA would do” by alejoacelas 🔸

I used AI to fix transcription errors, rerrarange the ideas, and suggest tweaks to the title and some sentences. Three of the most exciting projects to come out of EA in recent years are, in a vague s...

8 Jul 4min

“Mabye do the thing you wish CEA would do” by AlejoAcelas🔸

8 Jul 4min

“Possible mistake EAs are making and shout out to Pause AI UK” by Michelle_Hutchinson

I think right now EAs might be making a significant mistake by paying insufficient attention to the political realm. As EAs we tend to figure out what's most impactful for us to work on and focus hard...

29 Jun 6min

“Coming Around To Political Donations” by Jeff Kaufman 🔸

Five years ago I read a post on the EA Forum arguing that "election campaign contributions might be a way in which you can have a substantial impact as a small donor". It struck me as weird but plausi...

12 Jun 4min

“animal welfare has an evidence problem” by matthes

Why I stopped donating to animal welfare charities but feel more motivated than ever to redirect money and talent to the cause. I have wanted to write this post for a while. It is an uncomfortable thi...

6 Jun 26min