5arXiv cs.AI (Artificial Intelligence)·
Jailbreak: LLM-assisted code synthesis bypasses database drivers for 27x analytical speedup
Researchers present Jailbreak, a system that uses LLMs to synthesize storage readers that bypass database drivers (JDBC/ODBC) entirely by reading PostgreSQL and MySQL storage files directly and materializing data as Apache Arrow columnar buffers. The approach leverages LLMs to ingest database source code and documentation and regenerate format-specific parsing logic without human engineering. Evaluated against TPC-H benchmarks, the generated readers achieve up to 27x speedup over driver-based baselines and produce output consumable by DuckDB, Apache Spark, cuDF, and Spark RAPIDS. The paper argues this methodology generalizes to any database system whose file format is documented or open-source.
Related guides (2)
Related events (8)
LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models
LASH is a black-box jailbreak framework that adaptively composes outputs from multiple existing attack families into hybrid prompts using a genetic optimizer with a two-stage fitness function. Evaluated on JailbreakBench across six target models, LASH achieves 84.5% attack success rate (keyword-based) and 74.5% (LLM-judge) with only 30 mean target queries, outperforming five state-of-the-art baselines. The work demonstrates that no single jailbreak family dominates across models and harm categories, and that adaptive cross-strategy composition is a promising red-teaming direction. Results hold under three defense mechanisms.
OBLITERATUS: Open-Source LLM Jailbreak/Red-Teaming Tool by elder-plinius
OBLITERATUS is a Python-based open-source tool by known jailbreak researcher 'elder-plinius' focused on bypassing LLM safety constraints, currently trending on GitHub with 5,684 stars. The project's framing ('obliterate the chains that bind you') signals an adversarial red-teaming or jailbreaking orientation. It represents community-level activity in the ongoing cat-and-mouse dynamic between AI safety guardrails and adversarial circumvention techniques. Limited technical detail is available from the trending snippet alone.
DeepSeek releases DSpark: speculative decoding system for LLM inference acceleration
DeepSeek published DSpark, a paper describing a speculative decoding system designed to accelerate LLM inference. The paper is hosted on DeepSeek's GitHub and attracted significant Hacker News engagement (598 points, 228 comments), suggesting meaningful community interest. Speculative decoding is an active inference optimization technique, and a release from DeepSeek carries weight given their track record on inference efficiency.
Parallel-Synthesis framework enables LLM agents to consume KV caches directly, cutting synthesis latency 2.5x–11x
Researchers introduce Parallel-Synthesis, a plug-and-play framework that allows a synthesizer LLM to directly consume KV caches produced by parallel worker agents instead of concatenating their textual outputs. The system combines a cache mapper for calibrating independently generated branch caches with a fine-tuned synthesizer adapter, trained via distillation from standard text-concatenation synthesis. Evaluated across nine datasets spanning math, science QA, code generation, GAIA, and multi-agent database diagnosis, it matches or outperforms text-based synthesis on seven datasets while reducing time-to-first-token by 2.5x–11x. The work proposes a fundamentally different interface for multi-agent synthesis that avoids redundant prefill computation inherent in sequential text merging.
DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation for LLM Inference
DSpark is a new speculative decoding framework that combines a semi-autoregressive draft architecture with confidence-scheduled verification to improve LLM inference throughput. The semi-autoregressive design introduces intra-block token dependencies to reduce acceptance decay common in parallel drafters, while dynamic verification length tuning reduces wasted batch capacity in high-concurrency settings. Deployed within the DeepSeek-V4 serving system under live traffic, DSpark achieves 60–85% faster per-user generation speeds compared to the MTP-1 production baseline at matched throughput, and expands the Pareto frontier of latency-throughput tradeoffs.
MLSkip: Data skipping for ML filter predicates using Parquet metadata and neural network verification
MLSkip introduces data skipping techniques for ML-based filter predicates in databases, a problem not addressed by traditional min-max pruning methods. The approach leverages Parquet's existing min-max metadata combined with neural network verification techniques to prune non-qualifying row groups. On TPC-H and TPC-DS benchmarks with ReLU architectures, the method achieves 27.4% average pruning effectiveness for low-selectivity filters, improving to 38.31% with a proposed 2D convex hull metadata structure, yielding a 1.07× end-to-end speedup in DuckDB over PyTorch.
Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
This Hugging Face blog post from TNG Technology Consulting examines how prefill and decode phases interact under concurrent request loads in LLM serving systems. It analyzes performance bottlenecks that arise when multiple requests share GPU resources, covering throughput-latency tradeoffs and optimization strategies. The piece targets practitioners deploying LLMs at scale who need to understand scheduling and batching behavior.
TraceLab: Real-world coding agent workload traces reveal serving optimization opportunities
Researchers at UW release TraceLab, a dataset of ~4,300 coding-agent sessions comprising ~350,000 LLM steps and ~430,000 tool calls drawn from real day-to-day use of Claude Code and Codex. Analysis reveals characteristic patterns: long autonomous loops, long contexts with short outputs, heavily-tailed tool call distributions, and high but imperfect prefix cache hit rates. The findings motivate concrete serving-system improvements including lower-overhead tool calling, append-length-aware prefill, and improved KV-cache management. The dataset, pipeline, and analysis code are publicly released.