SHIFT proposes activation gates for RAG conflicts
Published on June 29, 2026, the item describes SHIFT, which adds learnable gates to FFN activations to balance retrieved context and parametric knowledge when they conflict.
Read articleKnowledge you can apply
Radar
Daily bookmarks: relevant news, facts and discoveries.
Strix: open-source AI pentesting tool
Published on June 29, 2026, the entry describes Strix as an open-source AI penetration-testing tool for finding and fixing vulnerabilities in applications.
Read articleVulHunt: detecting vulnerabilities in binaries
Dated June 29, 2026, this bookmark presents VulHunt, a framework from Binarly's REsearch team, and mentions a post series with an example of detecting a remote code execution vulnerability in rsync.
Read articleGeometry of arithmetic representations in LLMs
Published on June 28, 2026, the paper studies representations during multi-operand addition and proposes a geometric account of carries and arithmetic errors in LLMs.
Read articleBlack-box analysis of Xiaomi’s MJA1 secure chip
Published on June 28, 2026, Quarkslab’s work describes analysis of the MJA1 chip, I2C traffic and firmware, and evaluates its security properties.
Read articleReasoning and knowledge stored in LLMs
Published on June 28, 2026, the Google Research text examines how reasoning may help LLMs access knowledge stored in their weights.
Read articleARM/AARCH64 CTF offers 29 exploitation techniques
Updated on June 28, 2026, the exploit_me repository offers a vulnerable ARM/AARCH64 app for CTF-style exploitation practice. The author says obvious symbols were removed for LLM fine-tuning.
Read articleDreamSmooth smooths sparse rewards in model-based RL
Published on June 28, 2026, this item describes an ICLR proposal to smooth rewards over time between steps for model-based reinforcement learning agents.
Read articleFUTEX_PRIVATE_FLAG may reduce lock overhead
Published on June 28, 2026, the summary says FUTEX_PRIVATE_FLAG may reduce lock latency between threads in the same process by letting the kernel ignore a shared global hash table.
Read articleRed Queen Gödel Machine coevolves agents and evaluators
A paper proposes including evaluators in recursive self-improvement of agents, rather than assuming that verifiers, benchmarks, or labeled datasets remain fixed.
Read articleA curated list of computing books
A page attributed to Brendan Gregg collects selected books across computing fields and may help engineers find reading recommendations.
Read articleBINEVAL makes LLM evaluations more interpretable
The method breaks criteria into yes-or-no questions and aggregates the answers into multidimensional scores. The report says it matched or outperformed two methods, without training, on three datasets.
Read articleLinux perf examples for profiling and debugging
A practical reference for exploring Linux perf (perf_events) in performance analysis and debugging of Linux systems, with a range of event sources.
Read articleiLLaDA trains an 8B diffusion model
A paper reports training an 8-billion-parameter Transformer with bidirectional masked diffusion on 12 trillion tokens and compares its results with autoregressive models.
Read articleA packet’s path through the Linux kernel
A publication points to a PDF about how packets travel through the Linux kernel and how that can help analyze network behavior.
Read articleWhy CPU utilization can mislead
In an article published on June 27, 2026, Brendan Gregg discusses the limitations of CPU utilization as a metric for evaluating system performance.
Read articleSurvey maps agents that evolve with experience
Published on June 27, 2026, the survey and a related list examine how agents in production turn interaction traces into durable capabilities, from self-evolution to meta-evolution.
Read articleWindows tokens and privilege escalation
A June 27, 2026 post explains the Windows kernel _TOKEN structure and its relationship to identity, security attributes, and privilege escalation.
Read articleSurvey examines evaluation of agent memory
The article reviews the evolution of memory in language-model agents and highlights limits in current evaluations, which often rely on end-to-end task metrics and treat memory as a black box.
Read articleLecture covers linking, loading and position-independent code
A lecture by Anton Burtsev of the University of California, Irvine, covers linking and loading with position-independent code, a topic relevant to executable layout and security hardening.
Read articleRota Nacional
Bring privacy into your workflow.
30 days, no card, with a starting quota. After that, Pix credit from R$ 10,00.