Latest in AI and developer tools

Today's trail

updated 19m ago

Pulse · inquirer.com

inquirer.com · Nov 1

Business leaders are leaning into AI, but they can't do it without hiring humans. Where are the profits?

'Adjusting to AI' goes beyond learning the products; it means you can work your way around an office and a bureaucracy and make yourself understood at different levels of an organization to implement AI agents and systems. For that, you often need to have experience — with meshing systems, and with failures.

Pulse

Top picks this weekarXiv

arXiv

Oct 29

Elucidating the Design Space of LM Data Attribution

Data attribution methods for Language Models (LMs) are typically evaluated using downstream tasks like fact retrieval. However, existing evaluations vary multiple dataset properties simultaneously, making it impossible to isolate exactly why an attribution algorithm fails. To diagnose these failures, we explore the design space of LLM data attribution, with a primary focus on evaluation. We introduce the Controlled Attribution Benchmark (CATT) for fact tracing, in which we fine-tune LLMs on entirely fictitious knowledge, providing unambiguous ground truth for attribution. This synthetic setup allows us to systematically alter one dataset configuration at a time, such as document redundancy and lexical distractors. With this configurable evaluation, we demonstrate that redundancy and distractors consistently degrade attribution performance. Rather than proposing a new estimator, we examine two design choices that are underexplored: the loss used to compute gradients and how per-token attribution scores are aggregated into a document score. We find that the true causal evidence within a training document is highly localized, but standard methods dilute this evidence into noise by…

Top picks

All arXiv Hugging Face GitHub Hacker News

Latest Top this week

arXiv

Sep 19

Enforcing Narrative Reliability and Epistemic Pacing in LLM-Driven Detective Games via Structured Knowledge Trees

Large Language Models (LLMs) enable open-ended dialogue in interactive games, but their non-deterministic outputs make it difficult to preserve authorial control, factual consistency, and the intended sequence of information disclosure. These challenges are particularly…

arXiv

Sep 19

Auditing Political Alignment in LLM Assistants: Engagement, Stance, and User Identity

LLM-based AI systems answer political questions for hundreds of millions of people. Current audits measure what they say to an average user, but their behavior is dynamic. I argue that their political behavior is a set of policies over whom to answer, what to say, and whether…

arXiv

Sep 19

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Spatial reasoning is essential for vision-language models (VLMs) to understand and act in the physical world. Reasoning in dynamic environments requires VLMs to perceive local state transitions caused by object motion and viewpoint changes and integrate them over long…

arXiv

Sep 19

WaveFront Decoding: Parallelized Self-Speculative Decoding for Looped Language Models

Looped language models repeatedly apply a weight-shared block to increase effective depth without increasing parameter count, but the resulting T sequential recurrent-block calls per generated token substantially increase decoding latency. To address the issue, we introduce…

This week in Multimodal

This week

Get the morning digest

Today's trail

Pulse

Top picks

Today's trail

This week in Multimodal

Most active this week

Rising tools