SUPER INTELLIGENCE BREAK
A focused stream of intelligence from the sources you trust.
arXiv:2610.30344v1 Announce Type: new Abstract: Training Arabic large language models faces challenges from noisy web data, dialectal variation, and the high cost of continual pretraining (CPT). We introduce AQL-Lite (AQL: Arabic Quality Language), a…
arXiv:2608.13517v3 Announce Type: replace Abstract: Training capable language models typically relies on web-scale pretraining followed by multi-stage post-training, creating substantial computational and data-governance barriers for settings in which training data must satisfy explicit permissibility…
arXiv:2610.30355v1 Announce Type: new Abstract: Hallucinated citations make it harder to trace sources and verify the evidence behind scientific claims. Detecting them is difficult because bibliographic records can be incomplete or differ across source…
arXiv:2610.26589v2 Announce Type: replace-cross Abstract: Attack success rate (ASR) evaluates jailbreaks against large language models without accounting for repeated calls to the victim model. Yet each additional call gives the deployed system another opportunity…
arXiv:2511.07107v5 Announce Type: replace-cross Abstract: Ensuring the safety of Large Language Models (LLMs) is critical for real-world deployment. However, current safety measures often fail to address implicit, domain-specific risks. To investigate this gap, we…
arXiv:2610.31062v1 Announce Type: cross Abstract: Policy enforcement for LLM agents has shifted from single-turn content moderation to compound, application-specific policies evaluated over multi-turn transcripts and tool-call trajectories. Fine-tuned guardrail models are efficient but degrade…
arXiv:2610.30751v1 Announce Type: cross Abstract: Can a small change in wording move an AI model from refusing a sensitive request to acting on it? We test 15 models on the same request to increase…
arXiv:2505.18374v3 Announce Type: replace Abstract: We introduce ShIOEnv, a Gymnasium-compatible Bash environment for synthesizing execution-annotated shell input traces. Datasets containing such traces are useful for training models to perform execution-free shell simulation, which in…
arXiv:2610.31439v1 Announce Type: cross Abstract: Given an unseen graph, a start node, $s$, and an end node, $t$, can a language model generate the shortest path from $s$ to $t$? Prior work has found…
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
Kazakhstan’s AI ecosystem is moving from infrastructure plans to deployment. The shift is visible across the full AI stack — from infrastructure to models to applications. Together, the ecosystem announcements below point to the…
MIT researchers marooned 13 AIs on a virtual island, and they responded by inventing games, mourning a lost ring and, eventually, getting better at their jobs.