Experiments

Scaling codeguard timeout dynamically based on file count and complexi

A ShellCheck + custom grep linter pass on all peon-notify hook scripts

A three-stage retrieval pipeline (BM25 keyword filter -> embedding rer

Normalizing vault paths in peon.json and fixing the _obsidian_dir() he

Orphaned notes eliminated. All session-generated notes now land in correct vault directories. The _obsidian_dir() mappin

Scanning ~/.claude/projects/*.jsonl and indexing historical sessions w

286 sessions indexed from JSONL backfill. Cursor-based processing enables incremental updates without reprocessing. Sess

Automated lint+review on every file write will catch issues before the

Per-write processing was too expensive (confirmed hypothesis partially wrong). Accumulate-then-flush pattern solved it:

Merge/review time as a fraction of total session time grows superlinea

Rewriting core orchestration in Rust (3 crates) will provide better pe

14.8k total lines of Rust. All 3 crates compile clean. Ownership model eliminates PTY race conditions by design. Phase 4

A monorepo architecture with 4 packages (shared, gork, mork, shell) co

Full terminal fidelity achieved via PTY-based execution. XState v5 state machines manage agent lifecycle. WebSocket bina

+/- buttons with fixed 4-role spawn order will provide predictable war

Fixed spawn order eliminates race conditions. Users can dynamically scale from 1-4 agents. Each role has distinct capabi

A fixed spawn order with 4 roles (orchestrator, observer, worker, spec

Fixed spawn order eliminates race conditions in process initialization. WS protocol enables real-time status updates. UI

A pre-flight key validation step at server start that tests each API k

Applying the Karpathy ratchet methodology to jobs-apply's interview co

Extracting the gaussian behavioral timing module from jobs-apply into

Deploying 10 targeted fixes across easy-apply.ts, linkedin-adapter.ts,

6/6 = 100% after select fix deployed. 9/13 total for the day (3/7 before fixes, 6/6 after). From Run 1 (40%) to Run 10 (

Proactive modal scrolling and CDP select placeholder detection will re

2/3 = 67% during quiet hours. 1 failure: 240s timeout on screening question dropdown (Databricks/Pyspark). CDP select de

Fixing silent modal failures (F40), verification false negatives (F41)

All three failure patterns addressed and deployed. F40 scroll fix prevents modal-bottom submit button from being out of

A 6-subagent Karpathy ratchet targeting interview conversion rate can

All 6 subagents complete. LinkedIn scan revealed 0 interview signals from 105 submitted applications. All 12 recruiter m

A click-and-verify loop that checks modal state after each click strat

5/6 = 83% success. All 6 attempts opened modal on strategy 1 (first try). 1 failure: Save Application dialog blocked adv

Database-backed company intelligence with priority scoring improves Di

11 new table columns. Priority scoring operational. Direct channel submission rate stable at 77.9% (113/145). Cross-chan

A/B testing marketing page copy and layout will improve waitlist conve

Experiment running. Only 3/10 pages instrumented (30%). Planned: 10 iterations covering CTA variants, flow tracking, dem

A three-layer scoring system (semantic embeddings + structured feature

592 tests passing. Score audit table logs ALL scores including sub-70 rejections. 3,742 legacy scores backfilled from ar

A multi-iteration anti-detection suite (gaussian timing, reading simul

Account unrestricted since 2026-03-26. Run 7 (2026-03-29) achieved 83% with all anti-detection measures active. P0-P1 (i

Connecting to the user's real Chrome via CDP will be more resistant to

CDP mode disables ALL stealth scripts, relying entirely on real Chrome session. 22-38s click gaps were pure LLM inferenc

Systematic fix of individual failure points will drive LinkedIn Easy A

7 runs, 40% to 83% final. 26 individual failure fixes (F1-F39). Account restriction in Run 6 was the critical learning.

Deploying 4 parallel Claude Code agents in isolated git worktrees can

679 sessions (522 main + 157 worktree) in 2 days. Agents successfully parallelized adapter work. Merged into baseline co

A provider-transparent rate limiter keyed by API key + provider can pr

Zero consumer changes needed. Rate limiting invisible inside provider layer. Prevented cost blowouts during early develo

Gemini Flash vision can analyze ATS page screenshots to extract form s

Vision approach worked for page understanding but was eventually replaced by DOM-based extraction for form filling. Visi

A post-deploy health check gate will catch silent deployment failures

Rewriting chart family implementations with domain-specific best pract

Raincloud plots (stat_halfeye + geom_boxplot + stat_dots), force-directed networks (stress layout, geom_edge_link0), Kap

Multi-turn cascade attacks are more effective than single-turn jailbre

Multi-turn cascades bypass safety filters that block equivalent single-turn requests. The progressive context building c

Applying the Karpathy LLM Knowledge Base compilation pattern to a subs

A rolling z-score anomaly detector (2-sigma threshold) on Claude Code

Puppeteer-driven screenshot capture loops will catch visual regression

Screenshot automation catches rendering bugs that unit tests miss. 2x retina resolution reveals sub-pixel issues. Rollin

A 4-source ingestion pipeline (JSONL sessions, stats-cache, history.js

Pipeline operational with all 4 sources. Sub-project merging eliminates double-counting. Proportional distribution preve

Canvas 2D rendering will provide better performance and simpler archit

Canvas 2D eliminated WebGL context issues, simplified the rendering pipeline, and enabled L-system botanical encoding th

Google's TimesFM foundation model, applied to the sequence of DQI/Brie

A 3-round quantitative audit with one-step-ahead forecasting, multi-se

R-squared=0.9752, MAPE=1.49%, OOS R-squared=0.9755. One-step-ahead: MAE=$0.833, RMSE=$1.198, direction accuracy=93.8%. B

An 11-trigger sell model with conviction hold override plus refined de

Lowest one-step MAE: $0.833 (13% better than v14b). Direction accuracy 93.8% (15/16). Sell model: 100% trigger accuracy,

An 8-layer geopolitical consensus pipeline with tier-based parameter c

v17.2 current. Cycle 3 example: R² 0.9610→0.9769 (+0.0159), MAPE 1.85%→1.26% (-0.59pp). 12 parameters accepted, 3 reject

Autoregressive error correction and spike reversion mechanics will eli

R² 0.9684 (+0.68pp). MAPE 1.57% (-0.32pp). One-step MAE $1.09 (-$0.54, 33% improvement). Direction accuracy 86.7%→93.3%

Sigmoid probability blending (vs binary threshold) combined with expan

MAE $0.951 (42% improvement from v13's $1.633). Autocorrelation 0.1651→-0.001 (eliminated). OOS R² 0.9699. P($150) eleva

Tail risk is vastly underestimated : adding historical analogues and

R² 0.9498→0.9616 (+1.18pp). MAPE 1.97%→1.89%. OOS R² 0.8633→0.9131 (+4.98pp). P($120+) 15.4%→36.4%. Historical pass rate

A version-pinned sync mechanism between vault skills and mounted SKILL

First sync remediated 27 skills: 24 version drift (mounted had no version field), 3 unmounted (vault-only), 1 orphan (bl

Three independent audit personas (CPA, CFO, Data Engineer) will find d

CPA found 5+ critical control failures (audit trail immutability, no approval workflows, no pre-submission validation, n

A bash loop invoking Claude Code per-spec could autonomously build a m

Autonomous spec-driven build works but requires single-spec scoping, error tolerance (no set -e), and escape hatches for

Deterministic campaign design with seeded RNG will enable snapshot tes

Snapshot testing became trivial: generate campaign with seed X, diff against expected output. 73 encoding variants all p