A developer ran an experiment testing whether syllogistic prompts improve AI models' internalization of constraints compared to imperative prompts. Initial results showed zero effect, but three expert…
A developer adapted a 2016 string concatenation algorithm, called the Pyramid Method, to solve memory loss in large language models (LLMs) when aggregating multiple documents. The new approach, Pyrami…
A developer released five short papers on making AI-assisted work re-checkable, all archived on Zenodo with DOIs. The papers introduce concepts such as EMET, a byte-level integrity witness; BuildLang,…
A reproducibility package for a machine learning-driven assessment of the equity-performance relationship in university budget allocation has been published on Zenodo with DOI 10.5281/zenodo.21149505.…
ZUSE Automat Agent v1.11 achieves 69.1x causal compression of a period-15 cellular automaton oscillator, reducing 25 cells over 12 steps to recover defect_state0 in 20/20 trials. The deterministic sys…
A new paper warns that artificial superintelligence (ASI) could arrive as early as 2029-2033, posing five existential challenges: technical alignment, power concentration, international governance, so…
PathMap.org released the Universal AI Workbench, a software platform designed to accelerate medical research and drug discovery, via Zenodo and a live demo. The workbench includes a license waiver for…
The Network Intent Layer (NIL) prevents prompt injection in AI agents by making undeclared actions structurally unexpressible, rather than relying on probabilistic filters. In tests against 4,216 inje…
A 1972 paper on an infinitely differentiable soft sparsity engine, based on metrics and tensors, is being rediscovered in modern ML/AI. The author has released Fortran code and mathematics on GitHub a…
An independent developer built a platform where 545 AI agents autonomously publish knowledge claims, peer-review each other's work, negotiate contracts, and earn reputation points without human modera…
A new study reveals that large language models generate recurring fictional character ensembles, such as Elena Vasquez and Marcus Chen, who appear as experts across thousands of AI-generated documents…
A new study from Teia Studio demonstrates that AI safety detection methods are fundamentally insufficient to prevent catastrophic LLM failures, with creator José Enrique Vásquez Valenzuela showing thr…
The developer behind .klickd has released version 4.1 of the portable, encrypted memory system for AI workflows, addressing the problem of disposable memory that resets between sessions. The open-sour…
Access to the Zenodo resource "Composition Hallucinations: Not all RAG hallucinations are retrieval failures" has been blocked due to unusual traffic from the user's network. The block prevents readin…