AI NEWS.ccAI is happening. The future is updating.
English
中文English日本語한국어
EXPLORE · DISCOVER · CONNECT

AI News

datasette-llm 0.1a9

Release: datasette-llm 0.1a9 I have some big upgrades to Datasette Agent in the pipeline, but in the meantime here's a tiny user experience improvement to the underlying datasette-llm plugin. It now picks up the default model used by LLM, which means you can start using Datasette Agent without needing to explicitly configure a default model: uvx --with datasette-agent datasette content.db --internal internal.db Previously you would also need to specify a model with -s plugins.datasette-agent.default_model gpt-6-astra. Tags: datasette, llm, datasette-agent

China‑bound Apple Intelligence enters beta testing in 4 days! Alibaba officially announces full integration of Qwen.

Author: Li Shuiqing | Editor: Xin Yuan — According to Zhidongxi (WeChat official account: zhidxcom), on October 31, Alibaba announced a partnership with Apple to integrate Qwen into Apple Intelligence. Chinese users will be able to directly access Qwen’s capabilities for text and image understanding, content generation, and more, within Siri, writing tools, and visual intelligence features. These functions will begin beta testing starting November 4 alongside the latest iOS Developer Beta version, and...

dbreunig/nesformer

dbreunig/nesformer Inspired by qwenputer by Divyansh Agrawal, Drew Breunig baked a working emulator for a Nintendo Entertainment System 6502 CPU into the weights of Qwen3.5-4B. You can now play NES ROMs such as Super Mario Bros (very slowly) running inside Qwen! In a comment on Hacker News Drew reveals the Opus 5.5 prompts he used to build this system: Read this article and any relevant source code: https://divagr.com/blog/qwenputer. Then explore if you could emulate the chip and ram in a Nintendo Entertainment System (as people do today with FPGAs in MISTRs) using this technique. If so, what size model would you have to build and if you could use smaller faster ones, could you get it to be at the standard clockspeed. Followed by: I think we should build it! Just for fun. It's okay if it's

NVIDIA has released the large-scale speech transcription model Nemotron 3.5 Transcribe, which can accurately recognize speech even when eight people speak simultaneously.

NVIDIA has officially open-sourced its new large-scale speech transcription model, Nemotron 3.5 Transcribe. Designed for professional voice processing, this model leads the industry in key metrics such as multilingual transcription accuracy, long-audio handling, and multi-speaker separation. It employs a Mixture of Experts (MoE) architecture with approximately 34 billion total parameters, activating only a subset of these parameters during each forward pass to enhance efficiency. Overall, it provides a new open-source option for professional speech transcription.

FlatCake: A Flat KVCache Storage Architecture for LLM Serving

arXiv:2610.38355v1 Announce Type: new Abstract: KV cache reuse accelerates LLM serving, but existing systems manage host DRAM and NVMe SSD as a tiered hierarchy where DRAM acts as an intermediate cache. Production LLM workloads break both premises of this hierarchy. First, bimodal reuse defeats DRAM temporal filtering, since workloads are dominated either by one-shot blocks with long reuse distances or by multi-gigabyte agentic sessions that exceed DRAM capacity, putting SSD on the critical read path. Second, DRAM staging and eviction-ordered layout bottleneck SSD restoration. Holding host staging buffers for in-flight prefixes causes contention under load that aborts prefetches, while incremental eviction scatters a session's blocks across the SSD and prevents large sequential reads. We p

Evaluating and improving AI agents for sequencing protocol understanding

arXiv:2610.37851v1 Announce Type: new Abstract: Existing scientific-agent benchmarks rarely evaluate whether agents can reconstruct the exact molecular structures and generation workflows specified by sequencing protocols, a capability critical for analyzing customized sequencing assays. We introduce LibStructBench, a document-grounded benchmark for reconstructing sequencing-library structures and molecular workflows. Our experiments show that frontier agents often produce approximately correct reconstructions but remain unreliable at exact reconstruction, particularly in molecular-state representation and workflow connectivity. Switching the underlying language model produced larger average performance differences than switching agent harnesses, with a statistically significant difference

Exposure Is Not Commitment: Double-Stratified Evaluation of Latent Monitors for Tool-Using Agents

arXiv:2610.37679v1 Announce Type: new Abstract: Tool-using language agents are vulnerable to indirect prompt injection, and a growing literature probes model internals to catch unsafe actions before they execute, with sharply conflicting results. We argue much of the conflict is an evaluation artifact, and propose a double-stratification protocol: separate injection exposure from behavioral commitment, in both the evaluation and the training population. On the primary Qwen AgentDojo grid, monitors trained on the naive mixed unsafe-versus-rest contrast mostly learn exposure: they flag exposed trajectories whether or not the agent complies, and barely predict which cases turn unsafe. Retrained on exposed cases only, the same probe families predict the model's own unsafe tool call up to two s

Seq@K: Evaluating Language Models Under Sequential Feedback

arXiv:2610.37859v1 Announce Type: new Abstract: Language-model agents differ fundamentally from prior intelligent systems in their ability to learn from natural language in context. This capability enables agents to iteratively refine their answers in response to feedback, a prevalent mode of operation in modern agentic workflows. However, the community primarily ranks models by metrics such as Pass@1 or Pass@K, which cannot capture how they utilize feedback on prior attempts. We introduce Seq@K, a natural evaluation protocol that measures whether a model can solve a problem within K sequential attempts, provided feedback after each previous failure. Unlike multi-turn agentic benchmarks that examine long-horizon planning, Seq@K isolates and formalizes the core capability of refinement from

Scoring Explanations Without Reading Them: Structural Shortcuts in Automated-Interpretability Evaluation Data

arXiv:2610.37676v1 Announce Type: new Abstract: Automated interpretability scores an explanation of a sparse-autoencoder (SAE) feature by asking a model to predict, token by token, where the feature fires on evaluation examples or to judge whether marked tokens fit it. We find that the evaluation data standard pipelines build can be scored without reading the explanation. On Neuronpedia's stored fuzzing runs for 500 random GPT-2 small features, 91.3% of activating examples are cropped with the peak on the centre token, and a rule that says "yes" when the centre token is marked reaches balanced accuracy 0.979, against 0.838 for the stored LLM scorers (recomputed from the stored per-item verdicts, on marks rebuilt from the pipeline's code); a rule reading only the mark count reaches 0.969. T

FilingLoop: Evaluating and Evolving LLM Agents for Corporate Disclosure Review and Revision

arXiv:2610.37905v1 Announce Type: new Abstract: Public disclosure repositories such as SEC EDGAR support informed investment through web access to corporate filings. Supporting their review with language model agents requires discovering unstated deficiencies across related documents, acquiring missing company facts, and verifying that requested revisions satisfy evidence-backed requirements. Existing financial question-answering evaluations provide limited evidence of these interactive capabilities. We introduce \textbf{FilingLoop}, an interactive benchmark and a self-evolving agent framework for corporate disclosure review and revision. Grounded in historical U.S.\ Securities and Exchange Commission correspondence, FilingLoop reconstructs 380 predominantly IPO review tasks from 96 compan

Claude gets in the car: After CarPlay integration, you can ask AI questions by voice even while driving

On October 29, Anthropic announced an update to the Claude mobile app, covering iPhone, iPad, Android, Chromebook, as well as web and desktop platforms. The highlight is that the iPhone version’s voice mode now integrates with Apple CarPlay, allowing drivers to directly ask AI questions without taking their hands off the wheel—enabling them to check routes, find information, and organize their thoughts during commutes. The in-car scenario is seen as the most imaginative aspect of this upgrade.

Say goodbye to tedious exporting! Google Gemini gets a major upgrade: it now supports directly generating and editing multi-format files within conversations.

Google has announced a significant upgrade to its conversational AI large model, Gemini, adding the ability to directly edit files within the conversation. All users can now generate, preview, and fully edit multiple mainstream file types in real time on both web and mobile platforms—no longer limited to exporting. This update covers formats such as PDF, Google Docs, Sheets, Slides, Markdown, and more, aiming to enhance AI-assisted productivity and smoother interaction.

DouBao Work has officially integrated with DeepSeek, Kimi, and GLM, making enterprise procurement hassle-free.

On October 29, according to Kuai Technology, DouBao Work under ByteDance launched a brand-new third-party large model service for corporate clients. This service breaks the previous practice of companies separately purchasing models from different vendors; users can now seamlessly switch among multiple mainstream large models within the same workspace, tailored to tasks such as long-text processing, code writing, and logical reasoning. The initial rollout includes three industry-leading models.