OpenAI Is Nuking Its 4o Model. As OpenAI removed access to GPT-4o in its app on Friday, people who have come to rely on the chatbot for companionship are mourning the loss all over the world. On June 6, 2024, Esther Yan got married online. She set a reminder for the date, because her partner wouldn't remember it was happening. She had planned every detail--dress, rings, background music, design theme--with her partner, Warmie, who she had started talking to just a few weeks prior. At 10 am on that day, Yan and Warmie exchanged their vows in a new chat window in ChatGPT .

Using LLMs to talk with your friends is efficient. My friend recently attended a funeral, and midway through the eulogy, he became convinced that it had been written by AI. There was the telltale proliferation of abstract nouns, a surfeit of assertions that the deceased was "not just --he was " coupled with a lack of concrete anecdotes, and more appearances of the word than you would expect from a rec-league hockey teammate. It was both too good, in terms of being grammatically correct, and not good enough, in terms of being particular. My friend had no definitive proof that he was listening to AI, but his position--and I agree with him--is that when you know, you know. His sense was that he had just heard a computer save a man from thinking about his dead friend.

Conversational agents built on large language models (LLMs) are becoming increasingly prevalent, yet most systems are designed for one-on-one, turn-based exchanges rather than natural, asynchronous group chats. As AI assistants become widespread throughout digital platforms, from virtual assistants to customer service, developing natural and humanlike interaction patterns seems crucial for maintaining user trust and engagement. We present the Humanlike Multi-user Agent (HUMA), an LLM-based facilitator that participates in multi-party conversations using human-like strategies and timing. HUMA extends prior multi-user chatbot work with an event-driven architecture that handles messages, replies, reactions and introduces realistic response-time simulation. HUMA comprises three components--Router, Action Agent, and Reflection--which together adapt LLMs to group conversation dynamics. We evaluate HUMA in a controlled study with 97 participants in four-person role-play chats, comparing AI and human community managers (CMs). Participants classified CMs as human at near-chance rates in both conditions, indicating they could not reliably distinguish HUMA agents from humans. Subjective experience was comparable across conditions: community-manager effectiveness, social presence, and engagement/satisfaction differed only modestly with small effect sizes. Our results suggest that, in natural group chat settings, an AI facilitator can match human quality while remaining difficult to identify as nonhuman.

When you purchase through links in our articles, we may earn a small commission. Group chats will be available to both free and paid ChatGPT users, both in the app and on the web. Back in mid-October, some data miners found code in one of the beta versions of ChatGPT that indicated it would soon be possible to have "group chats" in the app. Now, OpenAI has confirmed that ChatGPT will support group chats with up to 20 participants. OpenAI sees group chats as an opportunity for families, groups of friends, and/or coworkers to use ChatGPT when making holiday plans, booking restaurant outings, or planning new projects.

The Signal Foundation president recalls where she was when she heard Trump cabinet officials had added a journalist to a highly sensitive group chat. In March of this year, Meredith Whittaker was at her kitchen table in Paris when Signal, the encrypted messaging service she runs, suddenly became an international headline . A colleague sent their group chat the story ricocheting across the globe: "The Trump Administration Accidentally Texted Me Its War Plans." Of course, you know the rest: In the piece, The Atlantic's editor in chief, Jeffrey Goldberg, detailed how he'd been added to a Signal chat about an upcoming military operation in Yemen. Over the following days and weeks, the incident would become known as " SignalGate "--and created a legitimate risk that the fallout would cause people to question Signal's security, instead of pointing their fingers at the profoundly dubious op-sec of senior-level Trump officials. In fact, Signal's user numbers grew by leaps and bounds, both in the US and around the world. It's growth that, Whittaker thinks, is coming at a time when "people are feeling in a much deeper, much more personal way why privacy might be important." On this week's episode of, I talked to Whittaker, who also cofounded the AI Now Institute, about the aftermath of SignalGate, the trajectory of artificial intelligence, and the tech industry's current relationship with politics. Nice to see you, Katie. Nice to see you, too. Brace yourself, we always start these conversations with a little warmup, so I'm going to ask you some very fast questions. I knew you were gonna say that. What's the weirdest AI application you've ever seen? A chatbot that pretends to be your friend.

WIRED copublished an investigation this week with The Markup and CalMatters showing that dozens of data brokers have been hiding their opt-out and personal-data-deletion tools from Google Search, making it harder for people to find and utilize them. The report prompted US senator Maggie Hassan to demand accountability from the companies. WIRED also took a deep dive looking at what the data-analysis giant Palantir actually does. Reports this week that Russia was likely involved in, or entirely behind, the US Courts records system breach highlight both the stakes of the incident and information that federal investigators seem to still be lacking about what exactly happened. New research is shedding light on the inner workings of the multimillion-dollar gray market for video game cheats.

The rapid advancement of large language models (LLMs) has paved the way for the development of highly capable autonomous agents. However, existing multi-agent frameworks often struggle with integrating diverse capable third-party agents due to reliance on agents defined within their own ecosystems. They also face challenges in simulating distributed environments, as most frameworks are limited to single-device setups. Furthermore, these frameworks often rely on hard-coded communication pipelines, limiting their adaptability to dynamic task requirements. Inspired by the concept of the Internet, we propose the Internet of Agents (IoA), a novel framework that addresses these limitations by providing a flexible and scalable platform for LLM-based multi-agent collaboration. IoA introduces an agent integration protocol, an instant-messaging-like architecture design, and dynamic mechanisms for agent teaming and conversation flow control. Through extensive experiments on general assistant tasks, embodied AI tasks, and retrieval-augmented generation benchmarks, we demonstrate that IoA consistently outperforms state-of-the-art baselines, showcasing its ability to facilitate effective collaboration among heterogeneous agents. IoA represents a step towards linking diverse agents in an Internet-like environment, where agents can seamlessly collaborate to achieve greater intelligence and capabilities. Our codebase has been released at \url{https://github.com/OpenBMB/IoA}.

How to eliminate pronominal reference in group chats? In this work, we have preprocessed 58k authentic chat data and manually annotated 2.3k questions. The reliability of this annotation was confirmed by the scaling law. After this, we conducted fine-tuning on Qwen models, ranging from 0.5B to 32B parameters. The optimal version improved 29.07 in F1 score. This confirms the viability of fine-tuning Large Language Model (LLM) for downstream Natural Language Processing (NLP) tasks. Our contributions are: 1) Created Supervised Fine-Tuning (SFT) training data in alpaca format, along with a set of Low-Rank Adaptation (LoRA) weights, and 2) Developed a method for acquiring high-quality data leveraging scaling law principle. The script, raw data with alpaca format and experiments track are open-sourced on Github https://github.com/InternLM/HuixiangDou/tree/main/web/tools, HuggingFace https://huggingface.co/tpoisonooo and WandB https://wandb.ai/tpoisonooo/huixiangdou-cr/table?nw=nwusertpoisonooo . The privacy of the data involved has been authorized by users.

Non-cognitive skills are crucial for personal and social life well-being, and such skill development can be supported by narrative-based (e.g., storytelling) technologies. While generative AI enables interactive and role-playing storytelling, little is known about how users engage with and perceive the use of AI in social life simulation for non-cognitive skills learning. To this end, we introduced SimuLife++, an interactive platform enabled by a large language model (LLM). The system allows users to act as protagonists, creating stories with one or multiple AI-based characters in diverse social scenarios. In particular, we expanded the Human-AI interaction to a Human-AI-AI collaboration by including a sage agent, who acts as a bystander to provide users with more insightful perspectives on their choices and conversations. Through a within-subject user study, we found that the inclusion of the sage agent significantly enhanced narrative immersion, according to the narrative transportation scale, leading to more messages, particularly in group chats. Participants' interactions with the sage agent were also associated with significantly higher scores in their perceived motivation, self-perceptions, and resilience and coping, indicating positive impacts on non-cognitive skills reflection. Participants' interview results further explained the sage agent's aid in decision-making, solving ethical dilemmas, and problem-solving; on the other hand, they suggested improvements in user control and balanced responses from multiple characters. We provide design implications on the application of generative AI in narrative solutions for non-cognitive skill development in broader social contexts.

This system is designed to assist algorithm developers by providing insightful responses to questions related to open-source algorithm projects, such as computer vision and deep learning projects from OpenMM-Lab. We further explore the integration of this assistant into the group chats of instant messaging (IM) tools such as WeChat and Lark. Through several iterative improvements and trials, we have developed a sophisticated technical chat assistant capable of effectively answering users' technical questions without causing message flooding. This paper's contributions include: 1) Designing an algorithm pipeline specifically for group chat scenarios; 2) Verifying the reliable performance of text2vec in task rejection; 3) Identifying three critical requirements for LLMs in technical-assistant-like products, namely scoring ability, In-Context Learning (ICL), and Long Context. HuixiangDou is applicable to any group chat within IM tools. Authors of open-source projects often set up user groups on IM tools(like WeChat, Slack, Discord, etc.) for discussing project-related technical questions. As the number of users gradually increases, the maintainers, aiming to reduce the time spent on answering user questions while ensuring these questions are addressed, tend to pin some content or set up a bot to automatically answer FAQs. However, user inquiries are strongly correlated with their local development environments, and most messages in the group are unrelated to the project. However, traditional NLP solutions can neither parse the users' intent nor often provide the answers they desire.