Knowledge catalogue
One hope for Tinker is that it can handle all the ML infra for posttraining for (approximately) everyone. So, curious, what prevents you from using Tinker for all your posttraining needs? Speed? Cost?
arXiv:2609.21636v1 Announce Type: cross Abstract: Recent work applies human psychometric questionnaires to large language models to elicit moral and value profiles, but it is not clear whether these i
I have been reasonably satisfied with my single R9700 (32GB) as I can run practical quants of Qwen 3.8-27B at good speeds, as well as other similar models in its weight class (Gemma 4 is still my go-t
Jev from TypeSafe AI got me thinking about non-autoregressive decision engines, so I built a small proof-of-concept called AES to test the concept locally on open weights. It uses Qwen/Qwen2.5-1.5B-In
A great example of practical AI solving real-world problems! Faster than ever. Thanks for building with Qwen. @cerebras Try it out for yourself! 🏠 We built Money Agent, a personal finance assistant po
LlamaIndex 发布了一个面向 AI Agent 的文档解析评测基准「ParseBench」 @llama_index 100 种解析方法参与评测（vlm - 67、专用解析器 - 33），2000 页真实企业文档（人工两轮校验），169011 条确定性规则，完全不用 LLM 当裁判，可复现。评测五个维度取无加权平均：表格结构、图表抽取、内容忠实度、格式语义、视觉定位。 https://ww
arXiv:2609.19606v1 Announce Type: new Abstract: This empirical study is an independent reproduction of the dissociation Zhao reported in 2026. The shape of a large language model's chain-of-thought en
arXiv:2609.19585v1 Announce Type: cross Abstract: In mental health care, reasoning over patient journeys is a key task for clinicians. Yet these journeys, encompassing a longitudinal progression of bi
arXiv:2609.19630v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly integrated into vehicle voice assistants. But linking natural-language requests to vehicle functions creat
arXiv:2609.19883v1 Announce Type: cross Abstract: Characterizing LLM reasoning remains an open challenge, as many existing benchmarks isolate specific reasoning skills, rely on external knowledge, or
arXiv:2609.20812v1 Announce Type: cross Abstract: Frontier coding agents are increasingly trusted to work autonomously for long periods, yet an agent's final response is often the only account of that
arXiv:2609.17853v1 Announce Type: cross Abstract: AfriSyCo studies answer switching around African-language factual content with two complementary layers: native-language follow-ups and a controlled c
arXiv:2609.18270v1 Announce Type: new Abstract: Payment operations are a critical financial infrastructure, but the value of large language models in this domain remains unclear because payment rules
arXiv:2609.18068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains such as housing screening. While alignment techniques mitigate explicit
arXiv:2609.18989v1 Announce Type: new Abstract: How many dimensions does a language model's computation actually use? The question is ill-posed until one names a functional. Task-weighted charts make
arXiv:2609.18908v1 Announce Type: new Abstract: Existing legal benchmarks cover diverse tasks, while continuous monetary remedies remain comparatively underexplored. We introduce ECtHR-NPD, to the bes
arXiv:2609.18357v1 Announce Type: new Abstract: Large language model (LLM) pricing agents may respond to how market data is presented, even when its numerical values remain unchanged. We introduce mar
arXiv:2609.17644v1 Announce Type: cross Abstract: Domain-specialized language models are widely used for scientific question answering, but stronger general-purpose systems raise a sharper question: w
arXiv:2609.18283v1 Announce Type: new Abstract: As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large langua
arXiv:2609.17857v1 Announce Type: cross Abstract: Who the judge is can affect an LLM-as-judge result, but measuring that effect without confusing it with candidate quality is difficult. We study four
Banger report from Salesforce. Pretty interesting to see more of these custom enterprise models. Salesforce trained the enterprise agent model from the same files it uses to configure agents. Koa star
arXiv:2609.16501v1 Announce Type: cross Abstract: De-identified resume screening assumes that redacting explicit fields prevents ethnocultural inference; however, recent audits attribute residual leak
arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and
Hugging Face CEO @ClementDelangue, whose company was the victim of an AI-led cyberattack, said existing cyber laws are likely sufficient to govern advanced AI. “I’m not even sure that we need to reinv
We should not treat models as though they have feelings, preferences, rights, or any entitlement to our welfare. Consciousness is the foundation of our ethical, legal, and political systems. To invite
arXiv:2609.16800v1 Announce Type: new Abstract: Large Language Models (LLMs) have achieved remarkable progress across diverse domains, but continual adaptation to evolving tasks and environments remai
arXiv:2609.16247v1 Announce Type: new Abstract: Large language models sometimes behave in ways resembling human emotional responses, and recent work has identified internal representations that may ex
arXiv:2609.17516v1 Announce Type: cross Abstract: Large language models can produce fluent answers when their factual support is weak. This paper introduces Chain-of-Self-Questioning (CoSQ), a prompt-
If a measure of one firm’s impact is based on the company it keeps, then Salesforce Inc. has made a significant leap into the artificial intelligence conversation for 2026. At Dreamforce, the customer
arXiv:2609.14754v1 Announce Type: cross Abstract: Causal claims about large language model (LLM) internals rest on measurements. Those might include a projection, a cosine, an ablation delta, or an in
arXiv:2511.13368v3 Announce Type: replace-cross Abstract: Large language models (LLMs) perform strongly across tasks and languages, yet how improvements in one task or language affect other tasks and
arXiv:2609.13816v1 Announce Type: cross Abstract: JavaScript powers approximately 98.8% of all websites, making vulnerabilities in its code a significant security risk, yet existing detection approach
arXiv:2609.13475v1 Announce Type: new Abstract: Existing pipelines for clinical timeline extraction from case reports are evaluated using an expert reference and are limited by imperfect reference ann
arXiv:2603.29396v2 Announce Type: replace Abstract: Standard evaluations of Large language models (LLMs) focus on task performance, offering limited insight into whether correct behavior reflects appr
arXiv:2609.13980v1 Announce Type: cross Abstract: Arabic large-language-model (LLM) evaluation has matured around Modern Standard Arabic (MSA): aggregated leaderboards such as the Open Arabic LLM Lead
arXiv:2609.14759v1 Announce Type: cross Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model s
arXiv:2609.13582v1 Announce Type: cross Abstract: A clinical agent benchmark can report the same verdict on identical inputs while the agent files a materially different order on each run. Such agents
arXiv:2609.15476v1 Announce Type: new Abstract: Large language models generate text by sampling each token from a predicted distribution, and a temperature parameter sets how far the draw strays from
The future is clearly agent teams. I run several agent harnesses at once, but the hard part is keeping them in sync. Many builders end up copying messages between Claude Code, Codex, and open models b
arXiv:2609.15533v1 Announce Type: cross Abstract: Mechanistic interpretability has become the dominant lens for understanding frontier language models, as their inner workings are complex and inherent
arXiv:2609.13872v1 Announce Type: cross Abstract: As 6G networks transition from theoretical frameworks into operational realities, artificial intelligence (AI) evolves from an add-on optimization too
arXiv:2609.15028v1 Announce Type: new Abstract: In-context learning (ICL) enables models to infer tasks from demonstrations, but existing benchmarks generally lack matched text and image versions need
arXiv:2609.13824v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to evaluate the responses of other language models. This approach, known as LLM-as-a-Judge, is faster
arXiv:2604.05793v2 Announce Type: replace-cross Abstract: In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, t
arXiv:2609.12509v1 Announce Type: new Abstract: Evaluation of vision-language models (VLMs) for multimodal mathematical reasoning remains limited for low-resource languages and for geometry problems t
arXiv:2609.12243v1 Announce Type: new Abstract: Inference-time power sampling via Sequential Monte Carlo (SMC) can substantially improve large language model (LLM) reasoning without requiring post-tra
arXiv:2602.21223v2 Announce Type: replace Abstract: It is not only what we ask large language models (LLMs) to do that matters, but also how we ask them. Phrases like ``This is urgent'' or ``As your s
arXiv:2609.12884v1 Announce Type: new Abstract: A medical claim's correctness often depends not on the claim alone, but on the clinical structure around it. A claim may require a lab reference range,
Lately because of the current hardware shortage, unfortunately or fortunately, we can’t just throw infinite cloud compute at our problems, but we’re forced to actually care about what’s happening unde
Wild 24 hours for AI and lots of different proposals have been made. TLDR; the only *tangible* new fact is that OpenAI and Anthropic are going to have embedded 3rd party evaluators from unknown organi
arXiv:2609.11185v1 Announce Type: new Abstract: Evidence-based medicine demands strict logical consistency, yet current evaluations of large language models (LLMs) prioritize superficial label matchin
arXiv:2609.11319v1 Announce Type: new Abstract: Most of mathematical knowledge has been communicated through so-called informal use of mathematics and natural language. With large language models (LLM
Peak performance across hard benchmarks: • Best or joint-best on 5/8 benchmarks (DeepSWE, Chartography, Toolathon, GDP.pdf, SWEFish) • Chartography: 48.3 (outperforming Opus 5 & Fable 5) • DeepSWE: 74
arXiv:2606.13720v2 Announce Type: replace Abstract: Arditi et al. (2024) has shown that refusal in safety fine-tuned chat models is mediated by a single linear direction in the residual stream, recove
arXiv:2603.09309v3 Announce Type: replace Abstract: Verbalized confidence, in which LLMs report a numerical certainty score, is widely used to estimate uncertainty in black-box settings, yet the confi
The tweet reports on a widely‑cited incident involving OpenAI and Hugging Face, noting that analysts had to use the open‑source GLM 5.2 model to investigate an attack because OpenAI’s proprietary “saf
arXiv:2609.10728v1 Announce Type: new Abstract: Large language models are unreliable at arithmetic, which is a problem for clinical calculators where a single numerical error changes the recommendatio
arXiv:2609.10815v1 Announce Type: cross Abstract: Police body-worn camera (BWC) footage has emerged as a critical aspect of law enforcement that ensures legal transparency, officer accountability, and
arXiv:2609.10413v1 Announce Type: new Abstract: Current LLM memory systems treat all personal facts identically, so stores grow without bound while retrieval precision degrades. The core challenge is
Introducing Fugu Max and Fugu Ultra v2: the next evolution of Sakana Fugu’s multi-agent orchestration system. Try: https://sakana.ai/fugu Blog: https://sakana.ai/fugu-max-release/ The frontier that ac