Search: “latent-space”

OpenAI has released GPT-5.6 with three variants (Sol, Terra, Luna) in a restricted beta program limited to trusted partners, according to reporting from Latent Space. The restricted access model sugge

According to this Latent Space article, OpenAI has launched GPT 5.6 with variants named Sol, Terra, and Luna, while integrating Codex capabilities into ChatGPT to create a broader superapp platform. T

OpenAI’s Codex, an AI‑powered coding engine, has surged beyond the developer community to reach over 10 million users—combining Codex with its new “ChatGPT Work” platform that turns the model into a g

ChatGPT Work was launched by OpenAI on July 9, 2026 as an agent‑oriented knowledge‑work platform that combines chat, Codex tools and cloud agents across fourteen model configurations. Within three wee

GPT‑6 Astra is a lightweight, high‑performance OpenAI model that can be hired for under $6 an hour and outperforms rivals on tests such as FrontierMath (97.6%) and ARC‑AGI‑3 (99.9%). The authors burne

In September 2026 OpenAI announced that an AI‑assisted team using the Astra‑next model solved the Navier–Stokes Millennium Prize Problem in 88 hours. The effort employed roughly 10,000 agents processi

Good Start Labs experiments show that AI training with gameplay can lead to transferable skills: a version trained on a railroad simulation outperformed peers in financial research. Inspired by Twitch

Radical Numerics, led by CEO Eric Nguyen, is deploying “biological chain‑of‑thought” and multimodal perception techniques to stay ahead of the evolving bio‑defense arms race, enabling rapid design of

Google I/O 2026 featured several new AI model releases including Gemini 3.5 Flash, an Omni model codenamed NanoBanana for video processing, Spark for background agent tasks, and Antigravity 2.0. These

arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre

System-wide Dictation on Apple devices runs entirely on-device, and the speech it transcribes reaches the foundation model through a tokenizer: an encoder that maps short windows of waveform onto the

arXiv:2609.37310v1 Announce Type: cross Abstract: With LLM watermarking being deployed commercially and now required by regulations, improving its reliability and effectiveness has become crucial. Yet

arXiv:2610.02801v1 Announce Type: new Abstract: Model-based reinforcement learning (MBRL) achieves strong sample efficiency by planning within learned latent dynamics, yet its performance degrades sub

From the Bitter Lesson of AI scaling to the unsolved mysteries of protein folding, Google DeepMind’s Pushmeet Kohli and Biohub’s Sal Candido are rethinking what it takes to build AI that truly underst

'Humanity's Last Gasp' is an AI news roundup from the Latent Space newsletter, likely covering significant developments in AI safety, existential risk discussions, or major industry milestones that pr

arXiv:2510.13849v3 Announce Type: replace Abstract: Multilingual Large Language Models (LLMs) often exhibit hallucinations such as unintended code-switching, reducing reliability in downstream tasks.

Tuna-2 is a unified multimodal model that performs visual understanding and generation directly based on pixel embeddings, employing simple patch embedding layers to encode visual input without a VAE

arXiv:2603.17305v2 Announce Type: replace Abstract: We propose CRAFT, a red-teaming alignment framework that leverages model reasoning capabilities and hidden representations to improve robustness aga

Meta released Harness, an open-source framework for evaluating and benchmarking AI model performance across diverse tasks and datasets. The tool enables standardized testing of language models and aim

arXiv:2608.08029v1 Announce Type: cross Abstract: Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-

arXiv:2609.14759v1 Announce Type: cross Abstract: Alignment applied after pretraining is shallow in a measurable way: a single direction in a model's residual stream can be edited out, and the model s

Ahmad Al‑Dahle joined Airbnb as CTO in January 2026 after leading Meta’s Llama generative‑AI models (2023–2025). He is steering an “inside‑out AI” strategy that deploys internal AI tools—such as the c

arXiv:2608.08029v1 Announce Type: cross Abstract: Khatri et al. (2026) [DOI: 10.1109/DSN-W70714.2026.00027] show that lightweight MLP probes on final-layer activations of a single 8B model (LLaMA-3.1-

Video agent models represent the next frontier in AI by extending language model capabilities to process, understand, and act on video content in real-time, enabling autonomous agents to perceive and

SpaceX's AI division has launched Grok 4.5, positioned as their first Opus-class model following the acquisition of Cursor. The release represents a significant capability upgrade in SpaceX's AI offer

arXiv:2609.19113v1 Announce Type: new Abstract: We evaluate six frontier language models on the two-agent log(N)-Questions game. A questioner sees N Wikipedia lead paragraphs and must identify a secre

Moonshot's Kimi K2.6 represents a significant update to their open-source language model, positioning it to compete with Anthropic's Claude Opus 4.6 and potentially ahead of DeepSeek v4. The refresh a

DeepSeek released V4 Pro (1.6T-A49B) and Flash (284B-A13B) models in both base and instruct variants, with optimizations enabling them to run on Huawei Ascend chips. These releases represent updates t

NVIDIA announced three new offerings: Cosmos 3, an advanced video generation model; Nemotron 3 Ultra, an upgraded language model; and RTX Spark, likely a tool or framework for developers. These releas

arXiv:2606.05173v1 Announce Type: new Abstract: Masked language modelling (MLM) has been the dominant pre-training objective for text encoders since BERT, yet it encourages representations that are st

arXiv:2608.05109v1 Announce Type: cross Abstract: Significance. Accurate intraoperative depth perception is important for autonomous and semi-autonomous robotic laparoscopic surgery. Conventional frin

arXiv:2609.37013v1 Announce Type: cross Abstract: Rapid assessment of building damage after natural disasters is essential to support emergency response. Earth Observation satellites can acquire relev

arXiv:2609.39035v1 Announce Type: cross Abstract: Passenger access doors are safety-critical subsystems in railway vehicles, yet detecting abnormal door behavior in real operation is challenging becau