How can we reliably check whether or not giant language fashions really perceive Indian languages and tradition in actual world contexts? OpenAI has launched IndQA, a benchmark that evaluates how effectively AI fashions perceive and cause about questions that matter in Indian languages throughout cultural domains. Why IndQA? OpenAI states that about 80 p.c of…
How can consistency coaching assist language fashions resist sycophantic prompts and jailbreak model assaults whereas protecting their capabilities intact? Large language fashions typically reply safely on a plain immediate, then change conduct when the identical process is wrapped with flattery or position play. DeepMind researchers suggest constant coaching in a easy coaching lens for this…
Code-oriented massive language fashions moved from autocomplete to software program engineering methods. In 2025, main fashions should repair actual GitHub points, refactor multi-repo backends, write checks, and run as brokers over lengthy context home windows. The foremost query for groups will not be “can it code” however which mannequin matches which constraints. Here are seven…
Can giant language fashions collaborate with out sending a single token of textual content? a workforce of researchers from Tsinghua University, Infinigence AI, The Chinese University of Hong Kong, Shanghai AI Laboratory, and Shanghai Jiao Tong University say sure. Cache-to-Cache (C2C) is a brand new communication paradigm the place giant language fashions alternate data via…
Postman recently released a comprehensive checklist and developer guide for building AI-ready APIs, highlighting a easy fact: even essentially the most highly effective AI fashions are solely nearly as good as the info they obtain—and that information comes via your APIs. If your endpoints are inconsistent, unclear, or unreliable, fashions waste time fixing unhealthy inputs…
In this tutorial, we develop a complete benchmarking framework to consider varied sorts of agentic AI programs on real-world enterprise software program duties. We design a suite of numerous challenges, from knowledge transformation and API integration to workflow automation and efficiency optimization, and assess how varied brokers, together with rule-based, LLM-powered, and hybrid ones, carry…
OpenAI has launched a analysis preview of gpt-oss-safeguard, two open weight security reasoning fashions that permit builders apply customized security insurance policies at inference time. The fashions are available in two sizes, gpt-oss-safeguard-120b and gpt-oss-safeguard-20b, each high-quality tuned from gpt-oss, each licensed underneath Apache 2.0, and each obtainable on Hugging Face for native use. https://openai.com/index/introducing-gpt-oss-safeguard/…
How do you construct a language mannequin that grows in capability however retains the computation for every token virtually unchanged? The Inclusion AI team from the Ant Group is pushing sparse massive fashions in a methodical approach by releasing Ling 2.0. Ling 2.0 is a reasoning based language model family constructed on the thought that every…
Can a compact late interplay retriever index as soon as and ship correct cross lingual search with quick inference? Liquid AI launched LFM2-ColBERT-350M, a compact late interplay retriever for multilingual and cross-lingual search. Documents could be listed in a single language, queries could be written in lots of languages, and the system retrieves with excessive…
Can we render lengthy texts as photos and use a VLM to attain 3–4× token compression, preserving accuracy whereas scaling a 128K context towards 1M-token workloads? A staff of researchers from Zhipu AI launch Glyph, an AI framework for scaling the context size through visual-text compression. It renders lengthy textual sequences into photos and processes…