Catalog
This is the master catalog. Read this first before answering any query or starting any operation.
Sources
| Title | File | Date Ingested | Topics |
|---|---|---|---|
| A Tradecraft Primer: Structured Analytic Techniques for Improving Intelligence Analysis | CIA Tradecraft Primer (2009) | 2026-05-19 | SATs, cognitive-bias, mind-sets, intelligence-analysis |
| SATs: Explanation and Relevance (Shawn Riley, LinkedIn) | Riley: SATs in Cybersecurity (2024) | 2026-05-19 | SATs, cybersecurity, roles |
| LLM SATs FTW (Scott Roberts, sroberts.io) | Roberts: LLM SATs FTW (2025) | 2026-05-19 | SATs, LLM-implementation, tools, starbursting, ACH, KAC |
| Assessing the Value of SATs in the U.S. IC (Artner, Girven & Bruce — RAND) | RAND RR1408 (2016) | 2026-05-19 | SAT-evaluation, ICD-203, empirical-studies, methodology, puzzles-mysteries-complexities |
| Towards Understanding Sycophancy in Language Models (Sharma et al., Anthropic) | Sharma et al. (2023) | 2026-05-19 | sycophancy, RLHF, alignment, preference-data |
| Discovering Language Model Behaviors with Model-Written Evaluations (Perez et al., Anthropic) | Perez et al. (2022) | 2026-05-19 | sycophancy, inverse-scaling, evaluation, alignment |
| A Survey on Hallucination in LLMs (Huang et al., ACM TOIS) | Huang et al. (2023) | 2026-05-19 | hallucination, taxonomy, detection, mitigation, RAG |
| Language Models (Mostly) Know What They Know (Kadavath et al., Anthropic) | Kadavath et al. (2022) | 2026-05-19 | self-knowledge, calibration, introspection, hallucination |
| Just Ask for Calibration (Tian et al., EMNLP 2023) | Tian et al. (2023) | 2026-05-19 | calibration, overconfidence, verbalized-uncertainty, RLHF |
| Improving Factuality and Reasoning through Multiagent Debate (Du et al., MIT) | Du et al. (2023) | 2026-05-19 | multi-agent, debate, groupthink, factuality, reasoning |
| Towards Measuring Subjective Global Opinions (Durmus et al., Anthropic) | Durmus et al. (2023) | 2026-05-19 | cultural-bias, mirror-imaging, WEIRD, alignment |
| Cognitive Bias in Decision-Making with LLMs (Echterhoff et al., BiasBuster) | Echterhoff et al. (2024) | 2026-05-19 | cognitive-bias, anchoring, framing, availability, confirmation, debiasing |
| Role play with large language models (Shanahan, McDonell & Reynolds, Nature) | Shanahan et al. (2023) | 2026-05-19 | persona, role-play, anthropomorphism, alignment |
| Lost in the Middle: How LMs Use Long Contexts (Liu et al., TACL) | Liu et al. (2023) | 2026-05-19 | long-context, positional-bias, availability-analog |
| Open Problems and Fundamental Limitations of RLHF (Casper et al.) | Casper et al. (2023) | 2026-05-19 | RLHF, reward-hacking, sycophancy, motivated-reasoning, alignment |
| Intelligence Failure: What, When, Why and How (Grey Dynamics) | Grey Dynamics (2024) | 2026-05-19 | intelligence-failure, intelligence-cycle, case-studies, Iraq, Ukraine |
| ACH-Grounding (suprathermal, GitHub) | suprathermal — ACH-Grounding (2024) | 2026-05-20 | ACH, RAG, grounding, hallucination-mitigation, hybrid-symbolic-LLM, implementation |
Entities
| Name | File | Type | Source Count |
|---|---|---|---|
| Richards J. Heuer Jr. | Richards J. Heuer Jr. | person | 1 |
| Center for the Study of Intelligence | Center for the Study of Intelligence | org | 1 |
| Sherman Kent Center | Sherman Kent Center | org | 1 |
| Shawn Riley | Shawn Riley | person | 1 |
| Scott Roberts | Scott Roberts | person | 1 |
| Randolph H. Pherson | Randolph H. Pherson | person | 1 |
| SANS Emerging Threats Summit | SANS Emerging Threats Summit | org | 1 |
| Structured Analytic Techniques for Intelligence Analysis (Book) | Heuer & Pherson (book) | book | 1 |
| Grey Dynamics | Grey Dynamics | org | 1 |
| suprathermal | suprathermal | person | 1 |
| Daniel Kahneman | Daniel Kahneman | person | 0 |
| Amos Tversky | Amos Tversky | person | 0 |
| Irving Janis | Irving Janis | person | 0 |
| Stephen Artner | Stephen Artner | person | 1 |
| Richard S. Girven | Richard S. Girven | person | 1 |
| James B. Bruce | James B. Bruce | person | 1 |
| RAND Corporation | RAND Corporation | org | 1 |
| Office of the Director of National Intelligence (ODNI) | ODNI | org | 1 |
| Anthropic | Anthropic | org | 4 |
| Mrinank Sharma | Mrinank Sharma | person | 1 |
| Ethan Perez | Ethan Perez | person | 3 |
| Saurav Kadavath | Saurav Kadavath | person | 1 |
| Esin Durmus | Esin Durmus | person | 2 |
| Katherine Tian | Katherine Tian | person | 1 |
| Yilun Du | Yilun Du | person | 1 |
| Jessica Maria Echterhoff | Jessica Maria Echterhoff | person | 1 |
Concepts
| Name | File | Category | Confidence | Source Count |
|---|---|---|---|---|
| Structured Analytic Techniques | Structured Analytic Techniques | meta | high | 3 |
| Cognitive Bias (hub) | Cognitive Bias | psychology | high | 3 |
| Intelligence Cycle | Intelligence Cycle | framework/process | high | 2 |
| Premature Closure | Premature Closure | bias | high | 3 |
| Persona Capture (LLM-native) | Persona Capture | llm-bias | high | 2 |
| System 1 / System 2 | System 2 | psychology/theory | high | 0 |
| Mind-Set | Mind-Set | psychology | high | 1 |
| Anchoring Bias | Anchoring Bias | bias | high | 1 |
| Availability Heuristic | Availability Heuristic | bias | high | 1 |
| Confirmation Bias | Confirmation Bias | bias | high | 2 |
| Groupthink | Groupthink | bias | high | 2 |
| Overconfidence Bias | Overconfidence Bias | bias | high | 1 |
| Mirror Imaging | Mirror Imaging | bias | high | 1 |
| Motivated Reasoning | Motivated Reasoning | bias | high | 1 |
| Framing Effect | Framing Effect | bias | high | 1 |
| Hindsight Bias | Hindsight Bias | bias | high | 1 |
| Status Quo Bias | Status Quo Bias | bias | high | 1 |
| Sycophancy (LLM-native) | Sycophancy | llm-bias | high | 0 |
| Hallucination (LLM-native) | Hallucination | llm-bias | high | 0 |
| Starbursting | Starbursting | SAT/imaginative | high | 1 |
| Key Assumptions Check | Key Assumptions Check | SAT/diagnostic | high | 3 |
| Quality of Information Check | Quality of Information Check | SAT/diagnostic | high | 1 |
| Indicators or Signposts of Change | Indicators or Signposts of Change | SAT/diagnostic | high | 2 |
| Analysis of Competing Hypotheses (ACH) | Analysis of Competing Hypotheses (ACH) | SAT/diagnostic | high | 4 |
| Devil’s Advocacy | Devil’s Advocacy | SAT/contrarian | high | 2 |
| Team A/Team B | Team B | SAT/contrarian | medium | 1 |
| High-Impact Low-Probability Analysis | Low-Probability Analysis | SAT/contrarian | high | 2 |
| What If? Analysis | What If? Analysis | SAT/contrarian | high | 2 |
| Brainstorming | Brainstorming | SAT/imaginative | high | 2 |
| Outside-In Thinking | Outside-In Thinking | SAT/imaginative | medium | 2 |
| Red Team Analysis | Red Team Analysis | SAT/imaginative | high | 2 |
| Alternative Futures Analysis | Alternative Futures Analysis | SAT/imaginative | high | 2 |
Synthesis Pages
| Title | File | Date | Query |
|---|---|---|---|
| SATs for LLM Agentic Systems | SATs for LLM Agents | 2026-05-19 | How can SATs control cognitive biases in LLM-based agentic systems? |
| Bias × SAT Matrix | Bias x SAT Matrix | 2026-05-19 | Which SAT controls which cognitive bias? Full cross-reference. |
| SAT Selection Guide | SAT Selection Guide | 2026-05-19 | Given a problem type or bias risk, which SAT should I apply? |
| SAT Pipeline | SAT Pipeline | 2026-05-19 | How do SATs compose into a complete analytic pipeline? |
| Testable Hypotheses: SATs + LLM Quality (Framework) | SAT–LLM Hypotheses (framework) | 2026-05-19 | What experiments could verify that SATs actually improve qualitative LLM output? Framework page + H0 + status overview. |
| H1: ACH + Confirmation Bias | H1 | 2026-05-19 | Does ACH reduce confirmation bias in LLM evidence evaluation? |
| H2: Devil’s Advocacy + Sycophancy | H2 | 2026-05-19 | Does Devil’s Advocacy maintain counter-positions under multi-turn pushback? |
| H3: KAC + Anchoring | H3 | 2026-05-19 | Does KAC prevent anchoring from initial prompt framing? |
| H4: Red Team + Mirror Imaging | H4 | 2026-05-19 | Does Red Team analysis improve adversarial robustness? |
| H5: Multi-agent + Groupthink | H5 | 2026-05-19 | Do multi-agent pipelines outperform single-agent chains, controlling for shared base model? |
| H6: What If? + Overconfidence | H6 | 2026-05-19 | Does What If? prompting improve LLM calibration? |
| H7: Epistemic Labeling + Hallucination | H7 | 2026-05-19 | Does forced epistemic labeling reduce confident hallucination? |
| Bias Evaluations | Bias Evaluations | 2026-05-19 | How do you measure whether a specific bias degraded an LLM/agentic flow? Methodology for building bias judges. |
Unprocessed Sources
Sources in Clippings/ not yet ingested into the wiki:
Tradecraft-Primer-apr09.pdf— ✅ ingested as CIA Tradecraft Primer (2009)roberts-llm-sats-ftw-2025.md— ✅ ingested as Roberts: LLM SATs FTW (2025)- RAND RR1408 — ✅ ingested as Artner, Girven & Bruce — Assessing SATs (RAND, 2016)
- Heuer/Pherson book (Structured Analytic Techniques for Intelligence Analysis, 3rd ed.) — ❌ not acquired; high value; known via Roberts: LLM SATs FTW (2025)
Stats
- Sources ingested: 17 (+1: ACH-Grounding 2024)
- Entity pages: 26 (+1: suprathermal)
- Concept pages: 33
- Synthesis pages: 13
- Last updated: 2026-05-20