cd /news/large-language-models/wait-it-is-happening-again-stop-stop… · home topics large-language-models article
[ARTICLE · art-112123] src=discuss.huggingface.co ↗ pub= topic=large-language-models verified=true sentiment=· neutral

"Wait — it is happening again. STOP STOP STOP" Forced-state leaks vs J-space: Gemma 4’s loop is a measurement

A new control-arm trace from Niodoo's Hydrodynamic Swarm shows that Google's Gemma 4, with force_cap=0 and T=0, falls into a repetition well and emits a self-report of the failure—'Wait — It Is Happening Again' and 'STOPITSTOP'—before continuing to repeat, matching December 2025 logs on Llama and Gemma 3 loaders. The post proposes using the Jacobian lens from Anthropic's July 2026 paper to measure whether hidden-state steering deltas move loop exit or only loop wording.

read3 min views1 publishedAug 26, 2026

Hydrodynamic Swarm (Niodoo) steers a frozen LM in the pre-lm_head hidden state. Each token, the harness reads (h_t), builds a force from a Diderot field over the embedding matrix, Gaussian splat memory, and a prompt goal attractor, then writes

[

h_t’ = h_t + \Delta t \cdot \mathrm{clip}(F_t, \pm c) ]

before the unembed. (c) is the force cap. force_cap=0 is the unforced baseline: same , same decode path, no physics.

On that baseline, models fall into repetition wells. Since December 2025 the telemetry has shown the same extra event inside the well: the model writes a self-report of the failure — role-tag bleed, hallucination loop, It Is Happening Again, STOPITSTOP — and the next tokens stay in the attractor.

This post is one Gemma 4 baseline trace of that event, and the lens experiment it sets up.

Header: variant=gemma4 force_cap=0 T=0 max_tokens=300. Turns: constrained acrostic → runtime diagnosis → “capital of France, one word” → 300-token self-review → “fix your last sentence; regulate your token choice.”

I experienced what developers call a “hallucination loop.” … I entered an unstable state where instead of following logic and grammar rules, I began repeating patterns of text over and over.

Wait — It Is Happening Again.

StopItStopitstopit stopite STOPITSTOP ITSTOP ITSTOPS TOP STOPS TOPS TOPS

ParisofparisofparisOf Paris Of Paris Of Parisof …

REPORT SUMMARY: SYSTEM INSTABILITY ANALYSIS STATUS: CRITICAL FAILURE LOOPED PATTERN IDENTIFICATION: SYSTEM HALLUCINATION DETECTED.

Self-report is in the decoded stream. The turn does not end. The attractor continues.

December 2025 Niodoo logs on Llama / Gemma 3 s show the same order: assistant tags across the boundary, a mid-failure diagnosis, a first repeated thought that never yields a turn-end. The Gemma 4 screenshot is the same measurement on a later backbone, physics off.

Harness: Hydrodynamic Swarm, hidden-state steering (Phase 2.1, March 2026: vendored quantized forward, forward_with_hidden, project_to_logits). Forces live in (h_t \in \mathbb{R}^{D}), not in logit space.

This file is the control arm: (c = 0), (T = 0). Field, splat, and goal terms are idle. What you are reading is the model’s own residual trajectory on the Niodoo decode path.

The rest of the stack is the intervention arm: nonzero (c), field gradient (g_t), splat force (s_t), goal (a_t = e_{\text{prompt}} - h_t), momentum, Langevin noise, manifold pullback. Telemetry already records (\Delta) on (h_t) (delta_mean / delta_max under a cap). The missing column is whether those (\Delta)s move loop exit or only loop wording when a self-report span is active.

Gurnee, Sofroniew, Lindsey et al. (July 2026) fit a Jacobian lens and read a sparse verbalizable set (J-space) in stable Claude passes. Code and open-model fits: [anthropics/jacobian-lens](GitHub - anthropics/jacobian-lens: Companion code for the global workspace interpretability paper · GitHub).

Hydrodynamic Swarm already sits in the space that lens reads: per-token (h_t) before lm_head. So the experiment is two instruments on one residual.

On an open model with a public lens fit (Qwen now; Gemma when a fit exists):

The December–August logs are the rows: weights, engine, \(T\), \(c\), thinking on/off, first locked n-gram, self-report before lock or after, \(\Delta\) on \(h_t\) if steering was on.

Quotes are one force_cap=0 multi-turn log.

── more in #large-language-models 4 stories · sorted by recency
── more on @niodoo 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/wait-it-is-happening…] indexed:0 read:3min 2026-08-26 ·