WeSearch
Hub / Search / llm
SEARCH · LLM

Results for "llm".

30 stories match your query across our 700+ source catalog. Ranked by relevance and recency.

30 results for "llm"

PROMPTENGINEERING

Arc Gate — LLM proxy that catches 100% of indirect/roleplay prompt injection attacks (beats OpenAI Moderation and LlamaGuard)

Built an LLM proxy that sits in front of any OpenAI-compatible endpoint and blocks prompt injection before it reaches your model. Benchmarked against OpenAI Moderation API and LlamaGuard 3 8B on 40 ou…

· 3 views
CLAUDEAI

Talkie: a 13B LLM trained only on pre-1931 text used Claude Sonnet to help test the model and judge its output

Researchers Alec Radford (GPT, CLIP, Whisper), Nick Levine, and David Duvenaud just released talkie : a 13 billion parameter language model trained exclusively on text published before 1931. No intern…

· 3 views
AMERICAN AFFAIRS JOURNAL

Understanding the LLM Bubble

If there is no path to superintelligence by 2028, and there is little prospect of the dramatic product improvements needed to drive major short-term revenue growth (including solutions to inaccuracy a…

· 8 views
DEV COMMUNITY

LLM Prompt Engineering in Practice: CoT, Few-Shot, and System Prompt Design

LLM Prompt Engineering in Practice: CoT, Few-Shot, and System Prompt Design Stop getting...…

· 2 views
SEEKING ALPHA

Hillman Solutions Corp. 2026 Q1 - Results - Earnings Call Presentation

2026-04-28. The following slide deck was published by Hillman Solutions Corp.…

· 3 views
ARXIV.ORG

LLMs Corrupt Your Documents When You Delegate

Large Language Models (LLMs) are poised to disrupt knowledge work, with the emergence of delegated work as a new interaction paradigm (e.g., vibe coding). Delegation requires trust - the expectation t…

· 4 views
GITHUB

Sage-Wiki: An LLM-compiled personal knowledge base

An LLM-compiled personal knowledge base. Drop in your papers, articles, and notes. sage-wiki compiles them into a structured, interlinked wiki — with concepts extracted, cross-references discovere...…

· 5 views
NEWSWEEK

Yann LeCun: LLMs Are Nearing the End, but Better AI Is Coming (2025)

Yann LeCun, Chief AI Scientist at Meta, believes LLMs are doomed due to their inability to represent the high-dimensional spaces that characterize our world…

· 5 views
DEV COMMUNITY

We Fixed Karpathy’s LLM Wiki - PENgram Is the Typed Knowledge Graph Pipeline Everyone Asked For

We recently published an article about the gaps in Karpathy's LLM Wiki pattern. The thesis was...…

· 3 views
FORBES - BUSINESS

Centene’s Obamacare Enrollment Drops By 2 Million After Congress Strips Subsidies

Health insurer Centene reported first quarter net income of $1.5 billion despite a 2 million enrollee drop in Obamacare enrollment.…

· 3 views
GITHUB

Show HN: Waiting for LLMs Suck – Give your user a game

Give your user a game while they wait for the LLM to return a result.…

· 4 views
ARXIV.ORG

Don't Make the LLM Read the Graph: Make the Graph Think

We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four LLM families in the cooperative card game Hanab…

· 3 views
ARXIV.ORG

Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis

Large language model (LLM) agents are increasingly tasked with complex real-world analysis (e.g., in financial forecasting, scientific discovery), yet their reasoning suffers from stochastic instabili…

· 3 views
ARXIV.ORG

Towards Automated Ontology Generation from Unstructured Text: A Multi-Agent LLM Approach

Automatically generating formal ontologies from unstructured natural language remains a central challenge in knowledge engineering. While large language models (LLMs) show promise, it remains unclear …

· 3 views
ARXIV.ORG

PhySE: A Psychological Framework for Real-Time AR-LLM Social Engineering Attacks

The emerging threat of AR-LLM-based Social Engineering (AR-LLM-SE) attacks (e.g. SEAR) poses a significant risk to real-world social interactions. In such an attack, a malicious actor uses Augmented R…

· 3 views
ARXIV.ORG

Judging the Judges: A Systematic Evaluation of Bias Mitigation Strategies in LLM-as-a-Judge Pipelines

LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM judges exhibit systematic biases that compromise evaluation reliability. We present a comprehensive empir…

· 4 views
ARXIV.ORG

CAP-CoT: Cycle Adversarial Prompt for Improving Chain of Thoughts in LLM Reasoning

Chain-of-Thought (CoT) prompting has emerged as a simple and effective way to elicit step-by-step solutions from large language models (LLMs). However, CoT reasoning can be unstable across runs on lon…

· 3 views
ARXIV.ORG

LEGO: An LLM Skill-Based Front-End Design Generation Platform

Existing LLM-based EDA agents are often isolated task-specific systems. This leads to repeated engineering effort and limited reuse of successful design and debugging strategies. We present LEGO, a un…

· 3 views
ARXIV.ORG

GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs

Autonomous multi-agent LLM systems are increasingly deployed to investigate operational incidents and produce structured diagnostic reports. Their trustworthiness hinges on whether each claim is groun…

· 3 views
ARXIV.ORG

Expert Evaluation of LLM's Open-Ended Legal Reasoning on the Japanese Bar Exam Writing Task

Large language models (LLMs) have shown strong performance on legal benchmarks, including multiple-choice components of bar exams. However, their capacity for generating open-ended legal reasoning in …

· 3 views
ARXIV.ORG

ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillation

Skill-distillation pipelines learn reusable rules from LLM agent trajectories, but they lack a key signal: how much each step costs. Without per-step cost, a pipeline cannot distinguish adding a missi…

· 3 views
ARXIV.ORG

LLM-Augmented Traffic Signal Control with LSTM-Based Traffic State Prediction and Safety-Constrained Decision Support

Traffic signal control is a critical task in intelligent transportation systems, yet conventional fixed-time and rule-based methods often struggle to adapt to dynamic traffic demand and provide limite…

· 3 views
ARXIV.ORG

Context-Aware Hospitalization Forecasting Evaluations for Decision Support using LLMs

Medical and public health experts must make real-time resource decisions, such as expanding hospital bed capacity, based on projected hospitalization trends during large-scale healthcare disruptions (…

· 3 views
ARXIV.ORG

LLM-Guided Agentic Floor Plan Parsing for Accessible Indoor Navigation of Blind and Low-Vision People

Indoor navigation remains a critical accessibility challenge for the blind and low-vision (BLV) individuals, as existing solutions rely on costly per-building infrastructure. We present an agentic fra…

· 3 views
HACKER NEWS (NEWEST)

Disaggregated Serving for Hybrid SSM Models in vLLM

· 0 views
HACKER NEWS (NEWEST)

LLMs Can't Generate Influence

· 1 view
R/CSCAREERQUESTIONS

Are people using AI/LLMs in Defense or Secure Environments?

· 1 view
HACKER NEWS - NEWEST: ""AI" "L

Monitoring LLM behavior: Drift, retries, and refusal patterns

· 3 views
PROMPTENGINEERING

Tool for inline annotation of LLM-generated specs and prompts (works with any MCP client)

I'm a product manager and spend a lot of time iterating on long prompts and specs that AI agents then act on. The review loop has been the worst part. When the model gives me a 5-page draft, leaving f…

· 12 views
GIZMODO

Talkie Is a ‘Vintage LLM’ Trained on Pre-1930 Data to Help Facilitate ‘Time Travel’

· 0 views