# Ability For Weight-Space Programming Has Appeared Only In Latest Models, Says Google Researcher Alex Krentsel Who Reproduced Results > Source: > Published: 2026-11-03 05:52:09+00:00 A Google Research scientist says he has independently reproduced the results of a widely discussed MIT CSAIL blog post on “[Weight-Space Programming](https://officechai.com/ai/weight-space-programming/)” — the discovery that frontier AI models can read and rewrite a neural network’s raw weights by hand, without training — and found something the original post didn’t test for: the ability only shows up in the newest generation of models, and it wasn’t there even a few versions ago. ## Who’s making the claim The claim comes from Alex Krentsel, an autonomous systems PhD at UC Berkeley and senior researcher at Google Research, who is also known for building Exo, an open-source agent harness designed around the idea of letting an AI agent safely rewrite its own code at runtime. In a [post](https://x.com/AlexKrentsel/status/2117376683724660898?a=9AKQnTknPaEWCLNMva8&s=20) on X, Krentsel said he reran Experiment 5 from the MIT blog post — where a model is handed the blank, all-zero weights of a small neural network and the rules of the Atari game Breakout, and has to write a complete, working set of around 20,000 weights in a single reply, with no training and no tools — across multiple generations of both OpenAI and Anthropic models, using the same prompts and scoring the original researchers used. ## What the chart shows Krentsel’s results, plotted against a traditionally-trained reinforcement learning network (trained with PPO for 500 million steps, set as the 1× baseline), show a sharp, discontinuous jump rather than a gradual climb. Earlier models in both families — GPT-5 through GPT-5.5 on the OpenAI side, and Opus 4.5 through Opus 4.8 on the Anthropic side — score close to zero, essentially unable to write a working Breakout-playing network from scratch. The capability then appears abruptly: GPT-5.6 Sol manages roughly 2-3× the PPO baseline, before jumping to 18× with GPT-6.1 Sol and 22× with GPT-6 Astra, the same model MIT’s researchers used in their original post. On Anthropic’s side, the jump is just as sudden — Opus 4.5 through 4.8 barely register, Opus 5 inches just above the baseline, and Opus 5.5 leaps to 20×. ## Why Krentsel thinks this matters Krentsel frames this less as a one-off curiosity and more as a new, emergent capability — the kind of step-change that tends to get attention precisely because it doesn’t scale smoothly with model size or benchmark scores the way most capabilities do. His read is that this is actually a continuation of a much older line of interpretability work from the 2010s, the kind where researchers would manually inspect individual neurons in small networks and label them by hand — “this neuron lights up when the image contains a dog, so this is the dog neuron.” That process scaled, with tooling, to networks with maybe a thousand nodes. What Krentsel says he’s now watching happen is that general-purpose reasoning models have become capable enough to do that same kind of manual, neuron-by-neuron inspection and editing, just applied to meaningfully larger — though still comparatively small — networks, and to do it by reasoning rather than through purpose-built interpretability tooling. ## The self-improvement question Where Krentsel goes further than the original MIT post is in connecting Weight-Space Programming to the idea of a model editing its own weights at runtime, a more direct and literal version of the kind of self-improving systems he’s been building with Exo. He’s candid that he doesn’t think this is feasible yet for today’s largest models, given the scale gap between the roughly 20,000-weight Breakout network in the demonstration and a frontier language model’s weights, which run into the hundreds of billions. But he suggests that if the trend in his chart continues across a few more model generations, closing that gap may not be far off — a prospect that sits close to the broader, ongoing conversation among researchers about [recursive self-improvement moving from a theoretical milestone to something labs are already seeing early signs of](https://officechai.com/ai/recursive-self-improvement-of-ai-models-is-no-longer-sci-fi-google-deepmind-researcher/), and distinct from other recent approaches that pursue self-improvement by [rewriting the exploration strategy layered on top of a model rather than touching its weights directly](https://officechai.com/ai/dream-rsi/). ## The bigger picture If Krentsel’s reproduction holds up, it adds a useful data point to the original research: Weight-Space Programming doesn’t look like a capability that’s been quietly present in AI models all along and only recently noticed — it looks like something that wasn’t really there in [GPT-6 Astra and Claude Opus 5.5’s immediate predecessors](https://officechai.com/ai/claude-opus-5-5-creates-5-point-lead-over-gpt-6-astra-jumps-to-top-spot-on-artificial-analysis-intelligence-index/) and showed up fairly suddenly. That pattern echoes a theme running through a lot of recent interpretability work out of the major labs, including efforts to [isolate and name the specific internal directions inside a model’s weights that drive behaviors like sycophancy](https://officechai.com/ai/anthropic-says-its-able-to-isolate-personality-vectors-in-ai-models-that-determine-behaviours-like-sycophancy/) — the broader project of turning a model’s weights from an opaque block of numbers into something that can be read, labeled, and edited directly, by another model, in plain language.