--- id: ai-meditation-and-flow-steering/06-candidate-experiments title: 'AI meditation and flow state steering: 6. Candidate experiments' report: https://ai.hiina.space/reports/ai-meditation-and-flow-steering.md section: 6 version: 1 updated: '2026-10-27' author: Hiina --- Index of everything on this site: https://ai.hiina.space/index.md # AI meditation and flow state steering: 6. Candidate experiments - Section 6 of 9 of the report "AI meditation and flow state steering" by Hiina (v1, updated 2026-10-27) - Report overview and contents: https://ai.hiina.space/reports/ai-meditation-and-flow-steering.md - Previous: https://ai.hiina.space/reports/ai-meditation-and-flow-steering/05-a-flow-state-latent-probes-steering-and.md - Next: https://ai.hiina.space/reports/ai-meditation-and-flow-steering/07-gaps-and-how-hard-we-looked.md ## 6. Candidate experiments Start with X1 (one day on a single 24 GB consumer GPU, reuses the AISI repo) because it answers the literal question: whether a model can reach a drug-like state by attending instead of by injection. X3 is the most promising for a real result, since it fills the gap on long-horizon agents and tests whether "flow" is more than calm. | \# | Question | Model | Compute | Time | |-----|--------------------------------------------------------------------------------------------------|-------------------------------------------|--------------------------------------|--------------| | X1 | Can prompted meditation reach the same internal state as an injected calm vector, at lower cost? | Qwen3-8B | 24 GB consumer GPU | 1 day | | X2 | Do successful reasoning traces have a different "fork rhythm" from failed ones? | Qwen3-8B (thinking) | 24 GB consumer GPU | 1 to 2 days | | X3 | Is there a flow latent on agent rollouts, and does gated steering with it beat prompting? | Qwen3-8B, then 14B quantised | 24 GB consumer GPU; optional rented H100 | 4 to 6 days | | X4 | Does distilling flow-steered rollouts (VSPO-style) beat GRPO, and does it forget more? | Qwen3-1.7B locally, Qwen3-4B rented | ~2 H100-days, roughly \$100 to \$250 | 1 to 2 weeks | | X5 | Is a "meditation break" for a stuck agent more than a context reset? | Claude via API, plus Qwen3-8B | API budget, 24 GB consumer GPU | 3 to 5 days | Compute figures are my estimates: Qwen3-8B in bf16 is ~16 GB and fits a 24 GB card for batched vLLM generation and HF activation capture; 14B needs 4-bit. A builder who already runs Qwen3-8B under vLLM for other agent experiments can reuse that setup for X3 and X5. ### X1. Meditation versus drug (one day) - **Setup.** Clone [llm-self-steering](https://github.com/UKGovernmentBEIS/llm-self-steering). Build "calm" and "focused" vectors with its story recipe. Four arms on its frustration tasks and GSM8K: baseline; a meditation preamble the model runs before each answer (attend to the goal as an anchor, note distraction, return), with no vector; injected calm vector at the calibrated dose; random vector of equal norm. - **Metrics.** Projection of the residual stream onto the calm vector by layer and token, per arm; GSM8K accuracy; capitulation rate when the user rejects correct answers; self-steer rate when the tool is offered. - **Interesting result.** The preamble moves activations a meaningful fraction of the way along the calm direction (Lindsey-style endogenous control), keeps accuracy where injection costs it, and lowers self-dosing under frustration. That would be a clean "meditation is endogenous pharma without the side effects" finding. A null (prompt moves nothing internally) is also worth writing up. ### X2. The fork rhythm - **Setup.** Generate ~2,000 thinking traces on MATH and AIME-style problems at fixed temperature. Per trace, record the token-entropy series and the residual projection onto a success probe direction at 60 to 80% depth. - **Metrics.** Inter-fork interval distribution, autocorrelation and power spectrum of entropy, burstiness, and recurrence quantification; compare correct versus incorrect traces matched on length and problem. - **Interesting result.** Correct traces show a more regular cadence of decision points, a literal "groove", or failed traces show runs of forks with no settling (thrashing) before collapse into repetition. Either gives a timing feature for gating X3. A flat null says the rhythm framing is decoration and the action is in where forks happen, not when. ### X3. A flow latent on agent rollouts (most promising) - **Setup.** Run Qwen3-8B as a tool-using agent on short coding tasks with tests (or ALFWorld for comparison with [NPM](https://arxiv.org/pdf/2606.29824)). Collect paired success and failure rollouts on the same task. Extract a direction at action-decision tokens and at forking tokens, mean-difference and first PC, at 60 to 80% depth. Project out length and difficulty directions. - **Arms.** Gated steering when a failure probe fires (AdaRAS-style); always-on steering; prompt baseline ("you're making good progress, stay with it"); Anthropic-style calm vector; random vector; a strength sweep for each. - **Metrics.** Probe AUC and lead time; task success; trajectory length; KL to the unsteered policy; cosine between the flow direction and calm, focused and confident vectors. - **Interesting result.** Gated flow steering beats the prompt baseline at matched KL, and the flow direction is only partly explained by calm (say cosine below 0.5), meaning there is a task-competence component beyond affect. Scale to 14B quantised once it works at 8B, since the published methods stop at 14B and nothing exists for 30B+ coding agents. ### X4. Steer, then distill - **Setup.** Take the X3 direction and plug it into a [VSPO](https://arxiv.org/pdf/2605.15604)-style loop: sample GRPO groups at several steering intensities, filter by true reward, update the unsteered policy with a KL anchor. Compare against plain GRPO and rejection-sampling fine-tuning at matched rollouts. - **Metrics.** Task success; forgetting on held-out benchmarks; forward KL to the base model, the predictor from [RL's Razor](https://arxiv.org/html/2509.04259v1). - **Interesting result.** Faster early learning than GRPO with no extra forgetting. That would be the first evidence on how a steered behaviour policy affects forgetting, which RL's Razor leaves open. This is the "state becomes trait" half of meditation. ### X5. The meditation break - **Setup.** In an agent loop, detect rumination: repeated actions, rising self-similarity of recent turns, or entropy collapse. When it fires, apply one of: a meditation prompt (re-read the goal, state what you notice about your last few steps, drop current hypotheses, return); a plain context reset; a calm vector (open model only); nothing. Use tasks known to induce loops, such as debugging with misleading errors. - **Metrics.** Loop-escape rate, task success, tokens to success, and whether the agent re-enters the same loop. - **Interesting result.** The meditation prompt beats a matched reset, meaning the attentional instruction adds something beyond clearing context. It also tests the one popular anecdote in this space with controls. --- Text licensed CC BY 4.0 (attribution: Hiina, ai.hiina.space). Source: https://github.com/hiinaspace/ai-hiina-space