Topic: agents
32 stories found
Today
Recognition, Simulation, and Refusal: A Contamination-Aware Study of Classic Psychological Effects in LLM Agents
The study PsyAgentBench re-runs classic psychology experiments on LLMs to assess their susceptibility to human biases without attributing those biases directly to the models, highlighting the need for contamination-aware analysis. This matters as it provides a framework to understand and mitigate potential psychological effect mimicry in AI systems.
Yesterday

How V7 gives AI agents institutional memory
V7 uses GPT-5.6 to compile company files into a coherent knowledge base for AI agents, enhancing their ability to handle complex tasks with accurate context. This innovation matters because it gives AI systems institutional memory, improving their efficiency and effectiveness in professional settings.
Boosting Deepresearch and LongContext Ability with Self-Generated Deepresearch Rollouts Traces
A new approach aims to enhance deepresearch and long-context abilities by using self-generated rollouts traces, addressing limitations in current agentic reinforcement learning models which struggle with maintaining context over extended interactions. This matters because it could significantly improve how AI agents handle complex, multi-step tasks in dynamic environments.
Friday, September 18, 2026
Show HN: Agentgit – a Git host for AI agents, no account, no token, no key
Agentgit is introduced as a new Git hosting service specifically designed for AI agents, offering seamless access without requiring accounts, tokens, or keys. This innovation aims to simplify the development and collaboration process for AI projects by removing traditional authentication barriers.
Thursday, September 17, 2026
Launch HN: Skillsync (YC W26) – AI chat sessions made portable across agents
Skillsync, a Y Combinator startup from Winter 2026, has launched an AI-driven chat session platform that enables portability of skills and knowledge across different customer service agents, enhancing efficiency and consistency. This innovation matters because it addresses the gap in maintaining uniform quality and expertise among multiple support staff members.
Think Before You Comfort: Reflective Cognitive Alignment for Protocol-Grounded Elderly Stimulation Agents
A new protocol aims to enhance the scalability of Cognitive Stimulation Therapy (CST) for elderly individuals with cognitive impairments by reducing dependency on trained facilitators and addressing data scarcity issues. This advancement is crucial as it could broaden access to non-pharmacological support while respecting privacy concerns.
Wednesday, September 16, 2026
Hex turns complex analysis into visual reports with GPT‑6 Astra
GPT-6 Astra enables Hex's data agents to transform complex analyses into engaging, interactive visual reports, empowering employees to proudly share insights. This tool is significant as it enhances data communication and engagement within organizations.
JuliusBrussee/caveman — 🪨 why use many token when few token do trick. Viral skill + proxy for coding agents that cuts 65% of tokens by talking l
A viral method reduces the number of tokens needed in coding by mimicking caveman-like speech, cutting usage by 65%, showcasing an efficient alternative to complex language in programming.
OpenAI expands ChatGPT ads with Sponsored Agents
OpenAI has expanded its advertising program for ChatGPT by introducing "Sponsored Agents," allowing companies to promote their services through the chatbot. This move is significant as it could enhance ChatGPT's commercial capabilities and revenue generation, potentially influencing user interactions and privacy concerns.

Underwriting Superintelligence: Backing Agents you can Sue — Rune Kvist, AIUC
AIUC's CEO discusses the company's Series A funding round, focusing on making superintelligent agents more legally accountable by allowing them to be sued. This matters because it addresses potential liability issues in an increasingly complex AI landscape.
32 of 32 items shown. Sources: 123 days indexed.