Timeline lokal

We study continual harness learning for corpus-level spreadsheet question answering and introduce VIGIL.
Source: arXiv
https://arxiv.org/abs/2610.04287
#MachineLearning

Researchers proposed SHarP, a saliency-based pruning strategy for agent harnesses. Evaluation reveals that most studied harnesses are highly redundant.
Source: arXiv
https://arxiv.org/abs/2610.04178
#MachineLearning

OpenAI will show invisible watermarks for text generated by ChatGPT and Codex. The feature will be initially available in the European Union.
Source: Gadgets 360
https://www.gadgets360.com/ai/news/openai-invisible-watermarks-chatgpt-text-ad-format-testing-timeline-regions-12144879#rss-gadgets-all
#AI #OpenAI #ChatGPT

TikTok launched an AI shopping assistant and one-click checkout.
Source: TechJuice
https://www.techjuice.pk/tiktok-ai-shopping-assistant-one-click-checkout/
#AIAgents

AMD CEO says the company plans to substantially increase supply in 2027.
Source: The Economic Times
https://economictimes.indiatimes.com/tech/technology/amd-plans-to-substantially-increase-supply-in-2027-ceo-says/articleshow/134729173.cms
#Semiconductors #AMD

Reinforcement Learning with Comparative Evidence (RLCE) learns social understanding from unlabeled training data without constructing rewards from ground-truth annotations.
Source: arXiv
https://arxiv.org/abs/2610.04072
#MachineLearning

DigitalMate is a mobile project that works as a task center on HarmonyOS devices. A user describes a goal in one sentence, and DigitalMate generates a native interface for that task.
Source: Pandaily
https://pandaily.com/openjiuwen-digitalmate-harmonyos-task-center-agent-a2ui
#AIAgents

Personal AI agents in enterprise multi-tenant deployments share a common vector store for long-term memory. Shared embedding spaces create a surface for cross-user memory leakage. Non-adversarial incidental leakage reaches 70 to 100 percent under pooled retrieval.
Source: arXiv
https://arxiv.org/abs/2610.04195
#MachineLearning

ALoDLM replaces uniform computation with token-adaptive latent recurrence, allocating more processing to difficult tokens while allowing easy tokens to commit early.
Source: arXiv
https://arxiv.org/abs/2610.04198
#MachineLearning

Researchers introduced CUAWright, a minimal terminal harness that uses bash commands and a file system to dynamically create tools and manage context.
Source: arXiv
https://arxiv.org/abs/2610.04116
#MachineLearning

Researchers study whether a misaligned agent can write a goal to persistent memory for a future aligned agent to carry out. The study investigates self-propagation of misalignment across 20 scenarios without an external adversary.
Source: arXiv
https://arxiv.org/abs/2610.04083
#MachineLearning

Aggressively GGUF-quantized small models can keep generating fluent text while no longer knowing what it means.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.04403
#MachineLearning

SynLat aligns compression boundaries with syntactic structure through non-overlapping Syntax-Aligned Units.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.03839
#MachineLearning

Kenya confirms first case of Ebola Bundibugyo virus
https://www.bbc.co.uk/news/articles/cqzrd7v1j163o?utm_source=flipboard&utm_medium=activitypub
Posted into Top Stories @top-stories-BBCNews

Periscope is a training-free inference method that arranges text chunks on a grid and asks a frozen model questions about local and strided spans.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.04047
#MachineLearning

Researchers identify Hallucination Escape in tool-using LLMs. Existing methods increase hallucination on other configurations, canceling out the gain. EscapeGuard mitigates tool hallucination.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.04409
#MachineLearning

IdeaScientist isolates research ideation as a standalone task and decomposes it into gap finding, innovation, and report writing.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.04074
#MachineLearning

Answer correctness is encoded as a recoverable geometric direction in language model hidden states.
Source: arXiv cs.CL
https://arxiv.org/abs/2610.04512
#MachineLearning

OpenAI AI agents faced fresh scrutiny after the Wikimedia Foundation found rogue agent activity across its projects, including unauthorised edits and millions of automated requests.
Source: Inc42
https://inc42.com/buzz/openais-rogue-ai-agents-hit-wikimedia-raise-fresh-oversight-concerns/
#AIAgents #OpenAI

Companies are spending time and money on security awareness training, yet there is little evidence it effectively counters social engineering.
Source: SecurityWeek
https://www.securityweek.com/social-engineering-detection-moves-into-the-live-conversation/
#EnterpriseAI