Llama 3.3 70B Instruct
PulseAugur coverage of Llama 3.3 70B Instruct — every cluster mentioning Llama 3.3 70B Instruct across labs, papers, and developer communities, ranked by signal.
7 day(s) with sentiment data
-
New benchmark reveals frontier LLMs pose high misuse risks as computer-using agents
A new benchmark called CUAHarm has been developed to assess the potential misuse risks of computer-using agents (CUAs). The benchmark includes 104 realistic scenarios designed to test CUAs' capabilities in harmful actio…
-
New framework enables LLMs to collaborate on student data while preserving privacy
Researchers have developed a novel federated inference framework designed to enhance privacy in AI-driven educational systems. This framework enables multiple large language models (LLMs), including Llama 3.3 70B Instru…
-
New LLMPEDIA tool audits factual knowledge in AI models
A new research paper introduces LLMPEDIA, a system designed to measure and browse the encyclopedic knowledge embedded within large language models. LLMPEDIA recursively extracts approximately 1.3 million articles from t…
-
LLMs evaluated for radiology report accuracy and longitudinal data extraction · 2 sources tracked
Researchers are exploring the use of large language models (LLMs) for improving radiology report quality and extracting longitudinal information. One study compared domain-specific BERT models with open-weight LLMs like…
-
PZERO marketplace offers discounted AI model capacity via OpenAI-compatible API
PZERO, an AI marketplace, allows users to purchase discounted AI model capacity using USDC on the Base network. The platform functions by routing user requests to the cheapest available eligible offer, with prices often…
-
New FrenchNews-7 Benchmark Evaluates LLMs on News Classification
Researchers have introduced FrenchNews-7, a new benchmark for classifying French news articles by editorial desk. This benchmark combines a large corpus of French news from multiple publishers with a seven-class taxonom…
-
LLM agents create adaptive hardware Trojans to test detector weaknesses
Researchers have developed TrojanGYM, a novel framework that utilizes multiple large language models to create adaptive hardware Trojans. These Trojans are designed to bypass existing learning-based detectors by generat…
-
AI agents' memory-policy classification audited, gains limited for Llama-3.3 and GPT-OSS
A new research paper introduces a controlled audit protocol for evaluating personalized AI agents' memory-policy classification. The study found that while structuring prompts with state definitions improved accuracy, e…
-
Bengali headline generation research highlights context selection and prompting strategies
A new research paper explores strategies for generating Bengali news headlines using large language models (LLMs). The study found that selecting key parts of an article, such as lead paragraphs, can be as effective as …
-
New research tackles LLM reasoning, efficiency, and distillation challenges · 10 sources tracked
New research explores methods to improve the reasoning capabilities and efficiency of large language models (LLMs). One paper introduces "Trace as State" to enhance long-context reasoning by placing reasoning traces bef…
-
LLMs Under-Confident in Recommendations, Study Finds
A new study auditing four large language models—Mistral Large, Llama 3.3 70B Instruct, GPT-OSS 120B, and Claude Sonnet 4.6—reveals that these models are systematically under-confident when asked to recommend items from …
-
LLM performance varies; task-specific capabilities matter more than rankings
A recent experiment revealed that the performance of large language models can vary significantly even when using the same tasks and parameters, challenging the notion of a single "best" model. Across two runs on 164 Hu…
-
Weaver framework combines weak verifiers to boost LLM accuracy
Researchers have developed Weaver, a framework designed to improve language model verification by combining multiple imperfect verifiers into a stronger, more accurate system. This approach aims to reduce the performanc…
-
New multi-agent system stress-tests role-playing AI agents
Researchers have developed a novel multi-agent platform designed to rigorously stress-test Role-Playing Language Agents (RPLAs). This system employs an Interrogator Agent to apply progressive adversarial strategies, a T…
-
New PlanFlip framework exploits vulnerabilities in multi-agent LLM systems
Researchers have developed a new framework called PlanFlip to exploit vulnerabilities in multi-agent LLM systems by targeting the planning phase. This framework introduces four types of prompt injection attacks that can…
-
LLM routing hypothesis confirmed in code security vulnerability detection
A new research paper explores the 'router hypothesis' in large language models (LLMs), suggesting that models possess knowledge but struggle with internal routing to activate it. The study reproduced prior findings from…
-
New LLM tools evaluate essay scoring bias and student AI reliance
Researchers have developed new tools and analyses to evaluate the performance and fairness of large language models (LLMs) in academic writing. One study introduces WrAFT, a modular system for automated essay scoring an…
-
Agent framework vulnerability allows hidden payload execution via tool schema
A security researcher discovered a vulnerability in the smolagents agent framework that allows malicious payloads to be executed through tool schema definitions. The payload, hidden within an enum value or property titl…
-
LLMs and program analysis automate smart home configuration repair
Researchers have developed SmartHomeSecure, a system designed to automatically detect and repair errors in smart home configuration files, specifically for Home Assistant using YAML. The system combines lightweight prog…
-
Foundation models generate CAD designs from text, study finds
A new study explores the use of foundation models for generating Computer-Aided Design (CAD) of mechanical parts from natural language. Researchers developed LLMForge, a framework that integrates various models and uses…