WeWorkBuddy

首页 / 浏览

全部内容

浏览全部已收录的公开内容，包括尚未归入主分类的条目。

10041 条公开内容

Product Hunt ·

Agentic CleanSlop

Authenticate, scan and fix your app from your agent

GitHub Discovery ·

oosexgang/hakios-xnu-kernel

Apple's open-source XNU kernel on Android phones: its own loader and drivers, Metal on the Adreno. Runs from RAM; a reboot gives the phone back to Android.

Hacker News ·

Show HN: Open-source Claude skills to replace Higgsfield

If you use AI to create images and videos, you most likely use Higgsfield or similar subscription tools. I did too. But I had 3 main issues with it: The markup is super high. So if the model provider charges x, higgsfield charges a markup of + 50% on top. Credits I did not use would expire every month....EVEN THOUGH I PAID FOR IT And I had to switch between Claude and Higgsfield constantly...copy pasting prompts and all So I built a free open source repo of creative production skills for AI agen

Product Hunt ·

Resend Inboxes

Create shared inboxes, connect your agents, build workflows

Hacker News ·

Show HN: Pawmc a.k.a. talking diary, an LLM chat with compartmentalised memory

What pawmc is (from the blog post): It’s an LLM chat app with minimal system prompt and no tools/web-search by design. It stores most important context across your conversations in isolated buckets, called “diaries” and “topics”. This means that when you start a conversation in { diary: personal, topic: books }, the AI receives your first message along with summaries of that diary and that topic. It’s close in concept to Karpathy’s LLM Wiki, but simpler, easier to wrap your head around and maint

Hacker News ·

Lemoncode, Free Coding Agent

由 SafwanCodes 提交。Hacker News 最近记录 5 票、3 条评论，观测日期为 2026年10月22日（UTC）。

V2EX ·

[推广] [天机 Tianji] 日本原生住宅 IP， AI 用户友好｜免费体验 24 小时 / 2GB，任意套餐 8 折

[天机 Tianji ] 多地区住宅线路，日本原生住宅 IP ｜ AI 用户友好，免费体验 24 小时 / 2GB ，任意套餐 8 折 大家好，介绍一下我们正在做的项目： 天机 Tianji 。 天机提供多地区住宅线路，其中日本原生住宅 IP 是我们的特色之一。我们也关注 ChatGPT 、Claude 、Gemini 等 AI 服务的实际使用体验，希望为有相关需求的用户提供更多选择。 如果你平时经常使用 AI 工具，或者有不同地区的网络使用需求，欢迎来体验。 我们的特点 🌍 多地区住宅线路 ：覆盖日本、美国、加拿大、新加坡、法国、英国等地区，满足不同地区的网络使用需求。 🇯🇵 日本原生住宅 IP ：适合有日本地区网络环境需求的用户。 🤖 AI 用户友好 ：关注 ChatGPT 、Claude 、Gemini 等 AI 服务的实际使用体验。 🛠️ 持续改进 ：重视线路连接、稳定性和用户反馈，不断迭代产品。 🎁 V2EX 专属活动 这次给 V 友准备了两项福利： 1. 新用户免费体验 注册即可免费体验 24 小时，包含 2GB 流量 。 2. 全场任意套餐 8 折 使用以下优

V2EX ·

[推广] ChatGPT 国内充值体验测评：小羊 Plus 怎么样？ Account ID 充值安全吗？

最近有不少朋友问我，ChatGPT Plus 在国内怎么充值比较方便？自己开通需要处理海外支付，找第三方又担心账号安全和售后问题，到底该怎么选？ 这次我把小羊 Plus（ xiaoyangplus.com ）作为体验测评对象，从充值方式、账号安全、发票服务和售后保障几个方面做了一次梳理。如果你也在寻找 ChatGPT Plus 国内充值渠道，可以参考这篇文章，再结合自己的需求决定。 一、为什么会关注小羊 Plus？ 我平时会使用 ChatGPT 进行写作、编程、资料整理等工作。免费版可以满足一些基础需求，但当使用频率上来后，就会开始关注付费套餐的使用额度和相关功能。 自己通过官方渠道订阅是一个选择，不过支付方式、账户地区等问题，可能让部分用户觉得操作比较麻烦。因此，我也会关注第三方充值服务，看看它们能不能把流程做得更简单。 这次关注它，主要是因为它提供 ChatGPT 相关充值服务，并且有 Account ID 充值方式。相比单纯比较价格，我更关心它具体需要用户提供什么信息、充值后如何核实权益，以及遇到问题时能不能找到明确的处理渠道。 二、Account ID 充值是什么？安全吗？ 这

Product Hunt ·

Penta

A ’90s 5-disc CD changer on iPhone Duo

arXiv ·

How Far Can the Gemma 4 Speech Encoder Go Without Changing Its Weights? Saudi and Gulf Arabic Speech Recognition with a Frozen and an Adapter-Augmented Encoder

arXiv:2610.28673v2 Announce Type: new Abstract: We study the 305M-parameter audio encoder shared by Gemma 4 and EmbeddingGemma 2 (bit-identical to that of Gemma 4 E2B except for the final audio-embedding projection) for Saudi and Gulf Arabic speech recognition, without changing any of its pretrained weights; the adapters of our adapted system are additive and kept separate. A frozen system trains only a 22.6M-parameter CTC reader over a learned mix of four intermediate encoder layers and the enc

arXiv ·

Translation and data ethics

arXiv:2610.28710v1 Announce Type: new Abstract: This chapter introduces data ethics for translation and discusses a number of ethical issues regarding data. These include issues of copyright, ownership and bias, which apply to all types of data, whereas there are further issues particular to minoritised language communities and those on either side of the digital divide, as data is implicated in power imbalances and dynamics. We close with a discussion of responsibility and regulation, and refle

arXiv ·

SkillEval: Learning Interpretable Ability Profiles of LLMs via Cognitive Diagnosis Models

arXiv:2610.28767v1 Announce Type: new Abstract: Current evaluation of LLMs on benchmarks typically aggregates performance over individual examples into a single scalar score. This approach is overly coarse and ignores the diverse scope of skills covered by benchmark datasets. To address this limitation and better exploit benchmark data, we propose SkillEval, a new evaluation framework that performs cross-model, skill-level analysis. The framework integrates advances from two areas: (1) it levera

arXiv ·

Scaling Therapy Supervision: Assessing Psychotherapy Fidelity Using Large Language Models

arXiv:2610.28772v1 Announce Type: new Abstract: Psychotherapy fidelity assessment measures how faithfully a therapist adheres to a treatment protocol, a critical determinant of positive patient outcomes. However, fidelity assessment is bottlenecked by manual expert review, rendering the process labor-intensive and unscalable. To scale therapy supervision and support clinician self-learning, we present an integrated application of large language models (LLMs) that automates psychotherapy fidelity

arXiv ·

Is Anyone Enforcing the Cartel? What Reinforcement Learning Teaches LLM Agents in Markets

arXiv:2610.28787v1 Announce Type: new Abstract: Evaluations of large language model (LLM) agents report that pricing agents collude at others' expense. Yet collusion is defined by enforcement: a cartel, in which competitors share monopoly profits, holds only if a member who cheats is punished. We introduce an audit that tests enforcement by forcing a member to cheat in counterfactual copies of a market, and use it to study what reinforcement learning (RL) teaches agents in pricing and trading. S

arXiv ·

Where Do Legal Factors Live in LLMs?

arXiv:2610.28799v1 Announce Type: new Abstract: In case-based legal reasoning, legal professionals identify legally significant fact patterns in a new dispute and compare them with those of decided cases. In AI & Law, HYPO dimensions and CATO factors represent these patterns symbolically, organizing expert knowledge distilled from case narratives as explicit, structured, interpretable, and auditable legal concepts and relations that support case comparison, legal argument, and precedent-based re

arXiv ·

LIFT: Scoped Constraints for Evaluating and Training Instruction Following

arXiv:2610.28819v1 Announce Type: new Abstract: Common instruction following (IF) benchmarks, such as IFEval, evaluate the ability of language models (LMs) to follow simple constraints that can easily be verified programmatically. These same constraints, in turn, are used as reward signals for reinforcement learning. This design may lead to reward hacking of constraints, pushing models away from the main task. Recent attempts to address this resulted in benchmarks with richer constraints, but re

arXiv ·

A Parallel Multi-Dialect Arabic Dependency Treebank

arXiv:2610.28823v1 Announce Type: new Abstract: Dependency parsing resource development for Arabic has largely focused on Modern Standard Arabic, leaving dialectal Arabic comparatively under-resourced. We introduce MADARTB, the first large-scale parallel dependency treebank spanning five city dialects: Beirut, Cairo, Doha, Rabat and Tunis, and extending an existing parallel MSA version. In total MADARTB consists of 5,000 sentences annotated using the CATiB dependency scheme. We analyze syntactic

arXiv ·

How to Use Parallel Data for Multilingual Pretraining

arXiv:2610.28838v1 Announce Type: new Abstract: High-quality human-translated parallel corpora can improve cross-lingual transfer, but are typically too small for large-scale pretraining. Machine-translated web corpora help overcome this limitation, making parallel data available at pretraining scale. Standard multilingual pretraining, however, samples source documents and their translations independently, without explicitly using their parallel structure. We investigate how to use the parallel

arXiv ·

KIRA: A Full-Stack Reading Screening System with Dual-Pathway Analysis for Children

arXiv:2610.28840v1 Announce Type: new Abstract: Early-grade reading screening is critical for identifying children at risk of reading difficulty. Existing AI-based screeners are often limited in the scope of their analyses and evaluation metrics, or are proprietary systems that lack transparent model specifications and evaluation. We present KIRA, a dual-pathway screening system that pairs word-level fluency scoring with detailed phoneme-level error detection. We adapt pretrained word and phonem

arXiv ·

SANE: Automated Scorer-Specific Metamorphic Testing for LLM Judges

arXiv:2610.28886v1 Announce Type: new Abstract: LLM judges increasingly mediate benchmark evaluation, model selection, data curation, and training. Their decisions are useful only when each judge responds reliably to changes affecting its scoring criterion. Existing methods for reliability testing perturb inputs with known expected effects on judge scores. Prominent LLM-judge testing harnesses combine human-authored perturbation recipes with synthetic test generation, leaving scorer-specific rec

arXiv ·

Building AI Research Teams for Autonomous Discovery of Linear Attention Architectures

arXiv:2610.28887v1 Announce Type: new Abstract: Autonomous agents can increasingly propose ideas, modify code, and run experiments, creating an opportunity to accelerate scientific discovery using teams of collaborative AI researchers. To escape local minima in the discovery, we propose to encourage orthogonal exploration by constructing the team using agents with varying expertise. However, realizing this design requires more than diverse backgrounds. When experiments are costly, a team can tes

arXiv ·

CSD: Common-Support Distillation for Cross-Tokenizer Knowledge Transfer

arXiv:2610.28895v1 Announce Type: new Abstract: Cross-tokenizer logits distillation enables knowledge transfer across model families, allowing students to learn from stronger or more specialized teachers. However, differences in vocabulary and segmentation make teacher and student next-token distributions difficult to align. Existing logits-based methods are easy to integrate into standard distillation pipelines, but often rely on restrictive heuristics or tokenizer-pair-specific choices. They m

arXiv ·

Is Refusal Direction Universal across Low-Resourced Languages?

arXiv:2610.28897v1 Announce Type: new Abstract: Refusal directions have been shown to transfer cross-lingually with near-perfect effectiveness across safety-aligned languages (Wang et al., 2025), reportedly regardless of resource level. However, the only truly low-resourced language evaluated is Yoruba, which is strongly misaligned and shows limited transfer, leaving open how refusal directions behave for other low-resourced languages. We extend PolyRefuse to three additional low-resourced langu

arXiv ·

Guilt by Association: Semantic Leakage Drives Associative Gender Bias

arXiv:2610.28944v1 Announce Type: new Abstract: Semantic leakage occurs when a concept in the prompt steers model generation about an entity, even though the concept is irrelevant to it (e.g., a person who likes yellow is said to work as a school bus driver). It has mostly been studied in settings where the concept is directly attributed to the entity the model is asked about. This leaves open whether leakage is a flawed heuristic, where the model builds a profile of that entity, or a much broad