Artificial intelligence researchers have demonstrated that a language model can improve its performance by rewriting its own weights through reasoning, operating without traditional training, gradients, or external assistance. In the study, an open 27-billion-parameter model was provided with its own weights, graded answers, and the ability to execute its code. By testing modifications on practice tasks and retaining only successful adjustments, the model steadily increased its accuracy across eight consecutive se…
Key points
Recursive self-improvement can be achieved through pure forward passes without gradients…: Recursive self-improvement can be achieved through pure forward passes without gradients or reliance on larger external models.
The capability to reliably rewrite internal weights emerges with scale, whereas smaller m…: The capability to reliably rewrite internal weights emerges with scale, whereas smaller models in the same family damaged their parameters.
Direct parameter modification provides a viable path to permanently embed performance gai…: Direct parameter modification provides a viable path to permanently embed performance gains rather than relying on prompt engineering or retraining cycles.
Sources checked by our analysis pipeline: 1
Computer Science > Artificial Intelligence
[Submitted on 16 Nov 2026 (v1), last revised 18 Nov 2026 (this version, v2)]
Title:Language Models Can Rewrite Their Own Weights
View PDF HTML (experimental)Abstract:A language model is trained once and frozen. Making it better takes another training run, or a prompt, a harness or extra computation at inference that is gone once the task ends. We show a third way: to our knowledge for the first time, a language model rewrites its own weights by its own reasoning and becomes better, with no gradients and no training. We call this self-rewriting: the model is its own optimizer. In earlier work, a frontier model edited a much smaller one; here an open 27B model, given its weights, its graded answers and the ability to run itself, diagnoses its own failure and rewrites the weights behind it. It surpasses itself: its own edit makes it 6.6 points more accurate on problems it never saw. It keeps getting better: it tests its edits on practice problems and submits only what works, each edit improving on the last,…
The historic challenge concerning prime numbers carries a $1 million reward from the Clay Mathematics Institute, which requires a rigorous two-year scrutiny process before any claim is recognized. This unverified proposal arrives amid growing disruption across the discipline as advanced artificial intelligence systems are increasingly deployed to tackle foundational mathematical conjectures.
Key Indian-origin leaders Krishna Rao and Rahul Patil directed the financial and technological execution of Anthropic as it officially launched on the Nasdaq exchange. Their operational guidance bridges top-tier Silicon Valley engineering with Wall Street corporate strategy, underscoring the deep executive bench driving the artificial intelligence firm. The high-profile public listing establishes immense personal equity and reinforces the pivotal role international leadership plays across frontier technology compa…
According to U.S. Treasury Secretary Scott Bessent, the administration expects successful technology leaders to support public wealth-building initiatives following major financial windfalls. The planned contribution will direct private capital into an investment vehicle aimed at establishing early financial foundations for young American citizens. This move comes immediately after significant public market success for the artificial intelligence company.