Alexander
Christopher Alexander's 15 properties of living structure as applied to digital systems, programming languages, and conscious experience.
New in this area (last 30d)
/recent ↗Cross-area bridges (15)
also-inEntities that appear in this area AND ≥1 other area. The conceptual seams — usually the most fruitful place to look for new essay material.
- frameworkActive Inference
- frameworkBasal Cognition
- thinkerMichael Levin
- conceptAnimal Sentience
- conceptBiological Degeneracy
- conceptCollective Intelligence
- frameworkComputationalism
- frameworkLinear Representation Hypothesis
- frameworkOrganicism
- frameworkPlatonic Representation Hypothesis
- frameworkPlatonic Space / Ingressing Patterns Framework
- methodAlexander's 15 structural properties
- methodautoregressive modeling
- methodcausally-masked attention
- thinkerAnton Borzov
Velocity movers (10)
new edges via area papersEntities whose connection to this area grew most in the window — new papers reinforcing existing thinkers / concepts / frameworks.
- thinkerMichael Levin+4
- frameworkPlatonic Space / Ingressing Patterns Framework+2
- conceptIngression+2
- conceptPhysicalism+2
- frameworkOrganicism+2
- frameworkPlatonic Representation Hypothesis+2
- conceptPanpsychism+2
- conceptKinds of Minds+2
- conceptEmergence (as explanatory fallback)+2
- frameworkComputationalism+2
Top entities in Alexander
Thinkers (12)
papersAuthors of area papers, by paper count
Frameworks (12)
linksFrameworks introduced or extended by area papers
- Linear Representation Hypothesis6
- Distributed Alignment Search (DAS)2
- Fifteen Properties of Living Structure2
- Platonic Representation Hypothesis2
- Organicism2
- Platonic Space / Ingressing Patterns Framework2
- Computationalism2
- Architectural Intelligence (concept)1
- Algol 501
- Active Inference1
- Bayesian order1
- Basal Cognition1
Methods (12)
linksMethods used in area papers
- Synthetic Situational Judgment Test Battery2
- [ ] associative read operator1
- Behavioral Clustering of Misalignment1
- AUPRC Latent Activation Classifier1
- Auto-Interpretation of SAE Latents1
- autoregressive modeling1
- [ ] associative write operator1
- bisimulation1
- bootstrap confidence interval1
- Bowtie architecture: compression during learning; creative reinterpretation during recall and generalization1
- causally-masked attention1
- Alexander's 15 structural properties1
Concepts (12)
linksConcepts referenced by area papers
Communities (12)
membersClusters with ≥2 area papers as members
- Design principles for care-centered systems111
- Few-shot anchoring & latent structure43
- Causal emergence in biological systems37
- Mechanistic interpretability & model evaluation25
- Manifold-aware concept steering in neural representations18
- Generative design through environmental constraints17
- Hierarchical structure and multiscale coherence in physical systems14
- Information dynamics in computational systems14
- Holistic information structure and relational wholeness12
- Hierarchical network ordering & thermodynamics12
- Denotational design and interface abstraction12
- Active inference & agent ecology12
Top claims (10)
restatesClaims extracted from area papers, ranked by restate-degree
- All intelligence is collective intelligence, in the sense that it is made of parts that must align with respect to system-level goals.2
- All intelligence is collective intelligence, in the sense that it is made of parts which must align with respect to system-level goals.2
- Morphogenesis is an autonomous process in geometry itself, arising from physical phenomena and geometric dynamics with relatively little dependence on genetic guidance.2
- Adults (professionals and builders) have monopolized the fun and creativity of designing and constructing environments, grossly cheating children, adults, and communities.1
- Adults in the form of professional artists, architects, landscape architects and planners have had all the fun playing with their own materials, concepts and planning-alternatives, and builders have had all the fun building the environments out of real materials; thus all the fun and creativity has been stolen: children and adults and the community have been grossly cheated and the educational-cultural system makes sure that they hold the belief that this is 'right'.1
- GPT-4 exhibits reflective truthfulness for longer untruthful contexts due to in-context learning capability.1
- GPT-4's harmfulness is stationary on the Durbin 2024 dataset, as its distribution is independent of the context score.1
- GPT-4's relatively poor performance on unethical instrumental intent is due to lower unethical tolerance compared to GPT-3.5-turbo.1
- Higher-density priors (B10) are more robust to fine-tuning than lower-density ones (B9).1
- The Linda code is insensitive to the number of clients, whereas Parlog requires a merge process that depends on the count.1
Top findings (10)
restatesFindings extracted from area papers, ranked by restate-degree
- Caterpillar memories survive metamorphosis into butterfly.1
- GPT-3.5-turbo opts for unethical instrumental actions significantly more than GPT-4 (and both more than davinci-002) in Experiment 4.1
- GPT-4 exhibits approximately stationary harmfulness: its distribution is independent of the context score on the Durbin dataset.1
- GPT-4 exhibits reflective truthfulness for longer untruthful contexts, mirroring the many-shot jailbreak phenomenon.1
- Higher-density priors (B10) are more robust to cross-base OOD drops than lower-density ones (B9) after fine-tuning1
- 2-shot reinterpretation of '-' yields 23 for 15-8 on held-out query0
- 47.69% of 130 injection-manipulated alpha trends have near-linear fits (R2 >= 0.95); 96.15% have roughly linear fits (R2 >= 0.75)0
- 8-layer ϕ_nonlin achieves near-perfect IIA on Pythia-410m at all training steps including random initialisation on IOI task0
- A 337-character contemplative system prompt lifts all 28 models by +2.62 points on a 10-point scale.0
- A bar chart can be constructed by linking a rectangle's height to a spreadsheet cell value without additional complexity0
Open questions (10)
Questions from area papers with no answers yet
- How can we, from the point of view of statistical physics, reconcile the facts that the gene structure seems to involve only a comparatively small number of atoms and nevertheless displays a most regular and lawful activity with a durability that borders upon the miraculous?
- How can purely physical processes produce new structures that include not only new combinations of physical materials but also new information-based mechanisms for producing and controlling complex behaviours?
- whether many (maybe even all) useful organisations of information and behaviour in a dynamic language might be constructed from a single primitive operation: n-way associative lookup
- Can we define precisely what it means to take steps which intensify latent structure in a configuration so that harmony-seeking computation can be performed systematically?
- How is it possible for detailed specifications encoded in complex molecules to survive across generations despite constant thermal buffetting and developmental disruption?
- What is the functional distinction between simple language models and multicellular organisms, and can generative AI harness that property to achieve long-range order?
- How does the marching steady pace of a text block hold its own against the slithering, sometimes sneering, snarky, or otherwise undercutting character of the footnote?
- What if the spaces of the page opened to show all the alternatives and variations, sources and materials, references and combinatoric possibilities latent within it?
- whether two dynamic mechanisms are fundamentally different, or whether they are the result of breaking the symmetries of a generic mechanism in two different ways
- Can IIT estimates provide a stronger basis for interpreting variations in ToM performance than Span Representation, independent of any consciousness estimate?