GPT-3.5 Turbo
PulseAugur coverage of GPT-3.5 Turbo — every cluster mentioning GPT-3.5 Turbo across labs, papers, and developer communities, ranked by signal.
4 day(s) with sentiment data
-
Handlebars LLM Prompt Vulnerability Exposes Role Injection Risks
A new research paper details a vulnerability in Handlebars templating, commonly used in LLM prompts, that can lead to structural role injection. The study found that Handlebars' default HTML escaping mechanism fails to …
-
New research tackles LLM routing limits; A3M Router touts cost savings
Two new research papers address limitations in Large Language Model (LLM) routing systems. One paper, "ReCal," introduces a reward calibration framework to improve the training stability and performance of RL-based rout…
-
GPT-3.5-Turbo struggles with information in the middle of long prompts
A study found that GPT-3.5-Turbo's accuracy significantly drops when the answer is located in the middle of a long prompt, specifically a 20k-token context window. This phenomenon, documented in the paper "Lost in the M…
-
Estonia benchmark: Claude Opus 4.7 best resists Russian propaganda
Estonia's Language Institute has released a new benchmark called "Propaganda Resistance" to evaluate how well large language models can withstand Russian state-sponsored disinformation. The benchmark tested 14 types of …
-
AI models generate research paper titles from abstracts
Researchers have developed a method for automatically generating research paper titles from abstracts using large language models. The study evaluated several models, including fine-tuned PEGASUS-large, LLaMA-3-8B, and …
-
New Benchmark Evaluates Large Chinese Language Models Across Domains
A new benchmark, Massive Multitask Chinese Understanding (MMCU), has been proposed to evaluate the capabilities of large Chinese language models across various domains. The benchmark includes tasks in medicine, law, psy…
-
OpenAI Deprecates 5.3-Codex Model, Urges Migration to Newer AI
OpenAI is deprecating its 5.3-Codex model, signaling a shift towards newer, more advanced AI capabilities. Users are encouraged to migrate to alternative models like GPT-4 Turbo or GPT-3.5 Turbo for their coding needs. …
-
LLMs show bias toward sponsored products, but simple prompts can fix it
A new paper reveals that many large language models, including OpenAI's GPT-3.5 Turbo and GPT-4o, exhibit a bias towards recommending sponsored products. Researchers found that these models often suggest more expensive,…
-
LLMs gain agency via tool use; Python monitoring gets observability
The first article details how to enable Large Language Models (LLMs) to interact with external systems through function calling and structured tools, transforming them into autonomous agents. It outlines defining tools …
-
LLM adapted for Indian law achieves 60% on bar exam, beats GPT-3.5
Researchers have developed a framework called Legal Assist AI to address the gap in legal assistance access in India. This system utilizes a smaller, 8-billion-parameter quantized Llama 3.1 model, enhanced with a Retrie…
-
OpenAI launches affordable GPT-4o mini and open-weight gpt-oss models
OpenAI has released GPT-4o mini, a new, highly cost-efficient small model designed to broaden AI accessibility and application development. This model demonstrates superior performance on benchmarks like MMLU, MGSM, and…
-
Introducing vision to the fine-tuning API
OpenAI has expanded its fine-tuning API for GPT-4o to include image and text data, enabling developers to enhance the model's visual understanding capabilities. This new feature allows for customization with as few as 1…
-
METR measures GPT-4 post-training enhancements, finding significant capability gains
Researchers at METR have conducted experiments to measure the impact of post-training enhancements on AI agent capabilities. Their findings indicate that OpenAI's own post-training efforts on GPT-4 significantly boosted…
-
OpenAI launches GPT-4 Turbo with larger context, lower prices, and new tools
OpenAI announced several updates at its DevDay event, including the new GPT-4 Turbo model with a 128K context window and knowledge up to April 2023, offered at a reduced price. The company also introduced an Assistants …
-
Introducing gpt-realtime and Realtime API updates
OpenAI has released GPT-4.1, a new series of models for its API that offer significant improvements in coding, instruction following, and long context comprehension, outperforming previous models like GPT-4o. The compan…
-
OpenAI launches new embedding models with price cuts and performance boosts
OpenAI has released new embedding models, text-embedding-3-small and text-embedding-3-large, offering significant improvements in performance and efficiency over previous models like text-embedding-ada-002. These new mo…
-
Replit integrates OpenAI models for coding assistance and education
Replit has partnered with OpenAI to integrate advanced AI models into its coding platform. The company is launching a new course on LLMs and GPT, and has introduced beta features powered by OpenAI's Codex model for code…
-
OpenAI trains AI with human preference feedback; Chip Huyen proposes predictive model routing
OpenAI and DeepMind have developed a new algorithm that learns desired behaviors from human feedback, reducing the need for explicit goal functions. This method uses a three-step cycle where humans compare two agent beh…