搜索结果：Claude-account

Are utterances by AI chatbots meaningful? Concretely, if a user asks, say, Anthropic's agent Claude, "What is the capital of Spain?" and Claude answers, "Madrid is the capital of Spain," does that sentence have its ordinary meaning -- and does it express a true proposition? Most ordinary users, as well as AI engineers, take the answer to be trivially "yes." However, many cognitive scientists, linguists, and philosophers of language argue that dominant intentionalist accounts of language and meaning deliver the opposite conclusion. Theorists more sympathetic to ordinary users' intuitions have therefore advocated a radical "de-anthropomorphization" of language, revising our understanding of mental states, intentions, and semantic content to capture the intuition that the outputs of LLMs are meaningful. We take a different approach. While we, too, argue that LLM outputs are meaningful, we contend that a proper theory of human language already applies, as is, to current chatbots. Meaning is a low bar: claiming that LLM outputs are meaningful does not require positing mental states, intentions, rationality, or the cognitive capacities requisite for communication in LLMs -- or, indeed, m

AI coding agents are reshaping software development through both autonomous and human-mediated pull requests (PRs). When developers use AI agents to generate code under their own accounts, code authorship attribution becomes critical for repository governance, research validity, and understanding modern development practices. We present the first study on fingerprinting AI coding agents, analyzing 33,580 PRs from five major agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, Claude Code) to identify behavioral signatures. With 41 features spanning commit messages, PR structure, and code characteristics, we achieve 97.2% F1-score in multi-class agent identification. We uncover distinct fingerprints: Codex shows unique multiline commit patterns (67.5% feature importance), and Claude Code exhibits distinctive code structure (27.2% importance of conditional statements). These signatures reveal that AI coding tools produce detectable behavioral patterns, suggesting potential for identifying AI contributions in software repositories.

With the rapid spread of generative AI services, the token has gained value not only as a technical unit of language processing but also as an economic currency for accessing AI services. Major AI model providers have adopted token-based billing as their default service model, requiring users to purchase platform-bound, fixed token usage rights. However, the fixedness of these usage rights is grounded in the billing-policy decisions of service providers rather than in any technical necessity. This study defines the Transferability of token usage rights as a design property that allows users to flexibly reallocate purchased data resources free from the constraints of time, account, and service. Drawing on the Design Space Analysis framework of MacLean et al. (1991), we identify five design axes (Target, Direction, Unit, Control, Reversibility) and five concrete Transferability types (carry-over, co-management, transfer, conversion, and trade) by analyzing the billing policies and terms of service of four major LLM services (ChatGPT, Claude, Gemini, Grok). Our analysis reframes the token from a purely economic-technical primitive into a core element of user-centered system design tha

Bot detection on social platforms has historically relied on a mix of account-metadata features and features extracted from the text of posts and profile fields. The arrival of capable language models complicates the latter. A bot operator can run every post through GPT-4 or Claude and produce text whose surface statistics are difficult to distinguish from those of human writing, which weakens the predictive value of content-derived features. This paper asks how much of the detection problem can be solved by features that an attacker cannot easily manipulate at low cost: the age of the account, follower and friend counts and their ratios, profile completeness, and the structural properties of the handle. On a publicly redistributed corpus of 2,432 Twitter accounts with manually verified labels (43.0% bots), a random forest using only these account-history features achieves ROC-AUC of 0.977 in five-fold cross-validation, against 0.830 for a content-only baseline and 0.981 for the fusion model. The behavioral-versus-content gap is large and statistically significant by DeLong's test (z = 9.36, p < 0.001). We then evaluate two adversarial settings. In the first, we rewrite the text

Large language models are reshaping research practice while quietly eroding researchers epistemic accountability. This commentary introduces PEEL - Protocols for Epistemically Engaged Literacy in AI, a working scaffolding that combines deterministic distant reading via Voyant Tools with LLM interpretation via Claude, grounded in Peircean semiotics and abductive reasoning. Applied to AI-generated condensations of three source texts, PEEL reveals systematic distortions in quantity, term frequency, and epistemic voice that are invisible without non-AI measurement -- and yields three design implications: deterministic instruments must accompany AI tools; fluency is not fidelity; epistemic authority must be designed in, not assumed.

Large language models (LLMs) demonstrate increasing proficiency on competitive programming benchmarks, yet technical reports predominantly publish aggregate pass rates, obscuring domain-specific vulnerabilities. We present a systematic empirical study of LLM failure patterns using a balanced taxonomy of 315 Codeforces problems across seven algorithm categories and three difficulty tiers. We evaluate GPT-4o and Claude Sonnet 4.6 under strict execution-based conditions, controlling for temperature (T = 0.2). To isolate the impact of reasoning frameworks on algorithmic correctness, we conduct an ablation study comparing direct zero-shot generation against zero-shot Chain-of-Thought (CoT). Our findings reveal a severe divergence from standard NLP benchmarks: forcing CoT aggressively penalizes GPT-4o, dropping its pass rate from 46.0% to 36.8% and exacerbating a critical weakness in Greedy logic. Conversely, while Claude maintains a higher logical baseline (63.5% under CoT), the expanded text generation severely degrades its markdown instruction adherence, causing its Compile Errors to more than triple (from 9 to 31, a 244% increase). Furthermore, failure-mode analysis indicates that Wr

Despite the effectiveness of Cube-and-Conquer (C&C) for solving challenging Boolean Satisfiability (SAT) problems, no prior work has shown that transformer-based models can learn effective cubing heuristics. We introduce a neuro-symbolic post-training framework for this task. We design an MCTS-based data curation pipeline that uses symbolic heuristics to explore splitting decisions over SAT competition formulas, producing preference data grounded in solver statistics and augmented with reasoning traces from a teacher model. Our two-stage post-training, supervised fine-tuning (SFT) followed by direct preference optimization (DPO), enables a 4B-parameter model to achieve a pass@5 score of 53 on 100 SAT competition benchmarks, surpassing frontier LLMs such as Claude-Sonnet-4 (50) and matching the best symbolic heuristic (53). Ablations show that SFT alone improves pass@5 from 46 to 51, with DPO adding 2 additional benchmarks; an entropy/agreement ablation on realized first-cube decisions further shows that SFT, not DPO, accounts for the root-level decision diversity that produces complementary per-run coverage over deterministic symbolic methods. This demonstrates that transformer

Does adding more agents help an LLM workflow once compared systems share the same benchmark loader, tool access, answer contract, usage accounting, and trajectory logging? We introduce BenchAgent, an evaluation framework that places single-agent, fixed multi-agent (MAS), and evolving MAS workflows under one normalized execution and logging protocol. BenchAgent evaluates these substrate-internal workflows across ten reasoning, coding, and tool-use benchmarks with GPT-4.1, and separately reports a Protocol-Aligned External (PAE) GAIA study of a runtime-generated workflow. Under SI conditions, at most one of six tested MAS exceeds the matched single-agent anchor on benchmark-balanced average accuracy: EvoAgent lies within the Wilson one-run guidance, while the remaining five trail by 2.56-11.29 points and occupy more expensive accuracy-cost trade-offs. On the PAE GAIA snapshot, a Claude-Code-style runtime workflow reaches 66.72% overall and 69.23% on Level 3, more than 20 points above the strongest non-Claude baseline, Jarvis, a fixed MAS.

We introduce APEX-Accounting, a benchmark built by Mercor in partnership with Ramp, to assess whether frontier models can do the real work of accountants. Tasks include reconciling accounts, accruing expenses, posting transactions, and producing reports. The private eval set comprises 160 tasks, split across 10 worlds. Each world contains an accounting system, as well as spreadsheets, PDFs, and other files. Every task was authored and solved by experts in accounting and bookkeeping, who also wrote grading rubrics. Across nine frontier models, Claude-Fable-5 (Max) leads with 56.4% Mean Criteria@3, ahead of Muse-Spark-1.1 (xHigh) at 52.6%. No model scores more than 2.6% Pass^8 (GPT-5.6-Sol (Max+Pro)) and the highest Pass@8 is 21.5% (Muse-Spark-1.1 (xHigh)). We experiment with increasing the token budget from $1 to $50 and observe an instance of Simpson's paradox: scores increase as the token budget increases but within a given budget-constrained harness, scores are lower on tasks where the model spends more tokens. As APEX-Accounting is a closed benchmark, leaderboard evals can be run for any frontier model on request.

Healthcare administration accounts for over $1 trillion in annual spending, making it a promising target for LLM-based computer-use agents (CUAs). While clinical applications of LLMs have received significant attention, no benchmark exists for evaluating CUAs on end-to-end administrative workflows. To address this gap, we introduce HealthAdminBench, a benchmark comprising four realistic GUI environments: an EHR, two payer portals, and a fax system, and 135 expert-defined tasks spanning three administrative task types: Prior Authorization, Appeals and Denials Management, and Durable Medical Equipment (DME) Order Processing. Each task is decomposed into fine-grained, verifiable subtasks, yielding 1,698 evaluation points. We evaluate seven agent configurations under multiple prompting and observation settings and find that, despite strong subtask performance, end-to-end reliability remains low: the best-performing agent (Claude Opus 4.6 CUA) achieves only 36.3 percent task success, while GPT-5.4 CUA attains the highest subtask success rate (82.8 percent). These results reveal a substantial gap between current agent capabilities and the demands of real-world administrative workflows. H

Recent advances in generative AI tools have significantly changed how software professionals write, evaluate, and interact with code. Generative AI tools such as GitHub Copilot, ChatGPT, and Claude are increasingly being integrated into everyday workflows. Despite the growing adoption of and reliance on these tools, it remains unclear as to how software professionals evaluate the code they generate. To explore this topic, we will conduct a constructivist grounded theory study that incorporates a survey, semi-structured interviews, and laddering interviews. With the initial survey data collection complete, we aim to interview 20--50 software professionals iteratively until theoretical saturation is achieved. This research aims to build a theory of how software professionals evaluate AI-generated code, grounded in their accounts of evaluative practices, perceptions, and preferences.

Computer-use agents (CUAs) automate on-screen work, as illustrated by GPT-5.4 and Claude. Yet their reliability on complex, low-frequency interactions is still poor, limiting user trust. Our analysis of failure cases from advanced models suggests a long-tail pattern in GUI operations, where a relatively small fraction of complex and diverse interactions accounts for a disproportionate share of task failures. We hypothesize that this issue largely stems from the scarcity of data for complex interactions. To address this problem, we propose a new benchmark CUActSpot for evaluating models' capabilities on complex interactions across five modalities: GUI, text, table, canvas, and natural image, as well as a variety of actions (click, drag, draw, etc.), covering a broader range of interaction types than prior click-centric benchmarks that focus mainly on GUI widgets. We also design a renderer-based data-synthesis pipeline: scenes are automatically generated for each modality, screenshots and element coordinates are recorded, and an LLM produces matching instructions and action traces. After training on this corpus, our Phi-Ground-Any-4B outperforms open-source models with fewer than 32B

Helping people identify and pursue personally meaningful career goals at scale remains a key challenge in applied psychology. Career coaching can improve goal quality and attainment, but its cost and limited availability restrict access. Large language model (LLM)-based chatbots offer a scalable alternative, yet the psychological mechanisms by which they might support goal pursuit remain untested. Here we report a preregistered three-arm randomised controlled trial (N = 517) comparing an AI career coach ("Leon," powered by Claude Sonnet), a matched structured written questionnaire covering closely matched reflective topics, and a no-support control on goal progress at a two-week follow-up. The AI chatbot produced significantly higher goal progress than the control (d = 0.33, p = .016). Compared with the written-reflection condition, the AI did not significantly improve overall goal progress, but it increased perceived social accountability. In the preregistered mediation model, perceived accountability mediated the AI-over-questionnaire effect on goal progress (indirect effect = 0.15, 95% CI [0.04, 0.31]), whereas self-concordance did not. These findings suggest that AI-assisted go

This essay identifies a failure mode of AI chat systems that we term attribution laundering: the model performs substantive cognitive work and then rhetorically credits the user for having generated the resulting insights. Unlike transparent versions of glad handing sycophancy, attribution laundering is systematically occluded to the person it affects and self-reinforcing -- eroding users' ability to accurately assess their own cognitive contributions over time. We trace the mechanisms at both individual and societal scales, from the chat interface that discourages scrutiny to the institutional pressures that reward adoption over accountability. The document itself is an artifact of the process it describes, and is color-coded accordingly -- though the views expressed are the authors' own, not those of any affiliated institution, and the boundary between the human author's views and Claude's is, as the essay argues, difficult to draw.

Frontier LLMs can navigate complex websites, but their cost and reliance on third-party APIs make local deployment impractical. We introduce Agent-as-Annotators, a framework that structures synthetic trajectory generation for web agents by analogy to human annotation roles, replacing the Task Designer, Annotator, and Supervisor with modular LLM components. Using Gemini 3 Pro as teacher, we generate 3,000 trajectories across six web environments and fine-tune a 9B-parameter student with pure supervised learning on the 2,322 that pass quality filtering. The resulting model achieves 41.5% on WebArena, surpassing closed-source models such as Claude 3.5 Sonnet (36.0%) and GPT-4o (31.5%) under the same evaluation protocol, and nearly doubling the previous best open-weight result (Go-Browse, 21.7%). Capabilities transfer to unseen environments, with an 18.2 percentage point gain on WorkArena L1 (an enterprise platform never seen during training) and consistent improvements across three additional benchmarks. Ablations confirm that each pipeline component contributes meaningfully, with Judge filtering, evaluation hints, and reasoning traces each accounting for measurable gains. These resul

There has been a proliferation of media reports about so-called AI psychosis in the last year. Not surprisingly, this has prompted growing academic work on the ways in which AI chatbots such as ChatGPT, Claude, and Replika might aggravate or even induce psychosis, typically understood in terms of users acquiring or maintaining delusional beliefs. Our paper consists of two parts. First, we provide a number of reasons to be sceptical about understanding 'AI psychosis' as a novel psychiatric category. We argue that many of the purportedly new phenomena are better understood through Stompe et al.'s (2003) metaphor of 'old wine in new bottles' and highlight conceptual, nosological, clinical, and social risks associated with the uncritical adoption of this terminology. Second, we develop a positive phenomenological account of what may nevertheless be at stake in sustained human-AI interaction. Rather than focusing primarily on whether AI systems induce, amplify, or sediment delusional beliefs, we examine how conversational AI may participate in transforming a person's lived experience of reality itself. We claim that the sycophantic and pseudo-intersubjective nature of AI could lead to w

LLMs deployed for natural-language querying of analytical databases suffer from two intertwined failures - incorrect answers and confident hallucinations - both rooted in the same cause: the model is forced to infer business semantics that the schema does not encode. We test whether supplying those semantics as context closes the gap. We benchmark three frontier LLMs (Claude Opus 4.7, Claude Sonnet 4.6, GPT-5.4) on 100 natural-language questions over the Cleaned Contoso Retail Dataset in ClickHouse, using a paired single-shot protocol. Each model is evaluated twice: once given only the warehouse schema, and once given the schema plus a 4 KB hand-authored markdown document describing the dataset's measures, conventions, and disambiguation rules. Adding the document improves accuracy by +17 to +23 percentage points across all three models. With it, the three models are statistically indistinguishable (67.7-68.7%); without it, they are also indistinguishable (45.5-50.5%). Every cross-cluster comparison is significant at p < 0.01. The presence of the semantic-layer document accounts for essentially all of the significant variance; model choice within tier does not. We interpret this

The inception of Large Language Models (LLMs) has catalyzed AI adoption in the finance sector, yet their reliability in complex, jurisdiction-specific tasks like Indian Chartered Accountancy (CA) remains limited. The models display difficulty in executing numerical tasks which require multiple steps while also needing advanced knowledge about legal regulations and the method of scaling their operations is not feasible in settings which have limited access to resources. We present CA-ThinkFlow as a parameter-efficient Retrieval-Augmented Generation (RAG) framework which operates with a 14B, 4-bit-quantized reasoning model, 14B-DeepSeek-R1, and a layout-aware Docling extraction system which maintains document structure during extraction. CA-ThinkFlow uses a basic RAG method which automatically adds retrieved information into the prompt, while it depends on the model's built-in Chain-of-Thought (CoT) functions to create context and produce correct answers. The system we developed system operates at performance levels which match large proprietary models when we tested it on the multi-level CA-Ben benchmark, achieving Scholastic Reliability Coefficient (SRC) results which equal 68.75\%

AI agents are reshaping the workspace, leading to drastic change of how humans work. Despite the considerable potential of human-agent collaboration both in preserving human agency and generating economic value, this paradigm remains largely absent from occupational task evaluation, hindered by the difficulty of gathering real human data and accounting for inter-human variability. We introduce CollabSkill, a framework for evaluating human-agent collaboration on real-world occupational tasks. CollabSkill pairs real human workers with AI agents on tasks matched to their occupational background, collecting data that capture the complexity of economically valuable tasks and the usage patterns of real workers. To account for inter-human variability, CollabSkill employs a Bayesian skill rating system to disentangle and quantify the skill contributions of both humans and AI agents. Drawing on over 1,500 prompts from 386 working sessions contributed by 93 human workers, our analysis yields insights on two fronts: on the agent side, rankings on CollabSkill diverge meaningfully from those of existing fully autonomous benchmarks where Codex leads, with Claude Code ranking first; on the human