OpenAI just launched Reserved Tier for enterprise API customers, letting teams pre-purchase model throughput denominated in dollars per minute. The reservation secures dedicated capacity during peak traffic across Standard and Fast modes without running into rate limits. Usage beyond your reserved ceiling reverts to standard pay-as-you-go rates, while Batch and Flex modes remain unsupported.
Google just unveiled the Gemini 3.5 model family, kicking things off with 3.5 Flash. It beats Gemini 3.1 Pro across key coding and agentic benchmarks while outputting tokens four times faster than rival frontier models. The model is already live in the Gemini app, Google Search AI Mode, and APIs, with 3.5 Pro slated for next month.
Google just connected Project Genie to Street View imagery, letting users and AI agents turn real-world coordinates into playable, stylized simulations like an underwater Golden Gate Bridge. It is a huge step for training embodied AI and robotics in grounded virtual worlds. The prototype is now rolling out to Google AI Ultra subscribers at $200 a month.
Odyssey just dropped two frontier world models, Starchild-1 and Agora-1, pushing generative video into interactive simulation. Starchild-1 generates synchronized audio and video on the fly without fixed runtimes, while Agora-1 lets up to four players interact inside the same live-rendered game world with a shared state. It is a major shift from static clips to real-time playable realities.
Poetiq just revealed results showing its Meta-System, a recursive self-improving harness, boosted GPT-5.5 to a record 93.9% on LiveCodeBench Pro without any model fine-tuning. The system automatically builds optimized execution scaffolding via standard APIs, lifting Gemini 3.1 Pro by 12.3% and outperforming Google's Deep Think. It shows external harnesses can unlock massive gains, though Poetiq remains waitlisted.
Gemini 3.2 Flash reportedly hits 92% of GPT-5.5's coding and reasoning performance while running 15 to 20 times cheaper on inference. Powered by DeepMind's distillation and sparsity techniques, it also reportedly pushes response times below 200ms. If true, developers may get near-frontier capability without the frontier price tag.
Anthropic just made Claude Platform on AWS generally available, giving AWS users access to its full native API without waiting for Bedrock updates. Teams can use their existing IAM credentials, CloudTrail logs, and cloud spend commitments while accessing Managed Agents and code execution on day one. Why it matters: developers no longer have to choose between enterprise cloud billing and frontier model feature parity.
Thinking Machines just announced a research preview of native interaction models. Instead of turn-based chatting with external scaffolding, it processes audio, video, and text in continuous 200ms micro-turns paired with an asynchronous background reasoning model. This lets the AI interrupt, listen, speak, and search simultaneously without awkward pauses.
Google just made Gemini 3.1 Flash-Lite generally available on its Enterprise Agent Platform, pitching it as the fastest and most cost-effective model in the Gemini 3 lineup. The lightweight model is built for high-throughput agent workflows like live coding and customer support—with early adopter Gladly seeing 60% lower costs and 1.8-second p95 latency. Why it matters: multi-agent automation is finally getting cheap and fast enough to run in real time.
OpenAI just launched GPT-5.5-Cyber in limited preview for critical infrastructure defenders, alongside its Trusted Access for Cyber program. Vetted security researchers get fewer classifier refusals to run authorized penetration tests and red teaming without guardrails getting in the way. It is built to level the playing field against attackers, though users must adopt phishing-resistant authentication by June 1, 2026.
OpenAI just rolled out three audio models in its Realtime API, headlined by GPT-Realtime-2, which can deliberate through requests, make parallel tool calls, and hold context across 128K tokens. The drop also includes a live translation model covering 70+ input languages and a streaming Whisper model for instant transcription.
ByteDance just launched Seed 2.0, an updated suite of general-purpose agent models spanning Pro, Lite, and Mini sizes. Pro tackles long-chain reasoning in messy real-world workflows, Mini handles high-concurrency batch tasks, and Lite natively fuses audio, video, and text understanding. Why it matters: Frontier labs are shifting from isolated benchmarks to long-horizon agent execution in enterprise production.
Anthropic just struck a deal with SpaceX to take over all capacity at the Colossus 1 data center, securing over 220,000 NVIDIA GPUs. The massive compute boost allows Anthropic to instantly double Claude Code's rate limits for paid plans, eliminate peak-hour restrictions, and raise Claude Opus API caps, while also exploring future orbital AI compute.
Subquadratic just introduced SubQ, a frontier model featuring a 12 million token context window powered by sub-quadratic sparse attention. At 1MM tokens, it runs 52x faster than FlashAttention at under 5% of Opus's cost, cutting compute by nearly 1,000x.
OpenAI just rolled out GPT-5.5 Instant as the new default model for all ChatGPT users. The update cuts hallucinated claims by 52.5% on high-stakes topics like medicine and finance, trims conversational fluff, and handles personal context from past chats much faster. A new memory sources tool also lets users see and delete the exact history used to shape answers.
xAI just rolled out Grok 4.3 alongside a new web-based voice cloning suite. The flagship model features permanently active reasoning, a 1-million-token context window, and agentic tool use like web browsing and code execution. API pricing has dropped roughly 40% to 60% compared to Grok 4.2, costing $1.25 per million input tokens and $2.50 per million output tokens.
OpenAI's GPT-5.5 just became the second AI model to fully crack UK AISI's enterprise cyberattack simulation, trailing only Anthropic's Claude Mythos. It completed the 32-step penetration test—typically a 20-hour job for human experts—in 2 out of 10 attempts while hitting a 71.4% pass rate on expert-level CTF challenges, though industrial control systems remain unbreached.
OpenAI just explained why its models started obsessing over goblin and gremlin metaphors starting with GPT-5.1. A post-mortem traced the verbal tic to reward training for ChatGPT's "Nerdy" personality, which favored creature words and accidentally leaked into the broader model via RL feedback loops. OpenAI retired the persona in March and cleaned its training data.
NVIDIA just unveiled Nemotron 3 Nano Omni, an open multimodal model unifying vision, audio, and language into a single 30B-A3B architecture. It delivers up to 9x higher throughput than comparable open omni models by eliminating the need to pass data across separate perception models. Why it matters: Agentic workflows like GUI navigation and document processing can now run in real time with far lower latency.
SpAItial just unveiled Echo-2, a frontier world model that turns text prompts or a single photo into persistent, interactive 3D environments rendered via 3D Gaussian Splatting. It supports object-level editing and claims to beat World Labs' Marble 1.1 across all WorldScore benchmark metrics.
DeepSeek just launched and open-sourced DeepSeek-V4 Preview, making a 1M token context standard across its services. It delivers two MoE models—the flagship V4-Pro and the lightweight V4-Flash—built around hybrid compressed attention that slashes KV cache memory to just 2% of standard architectures. It basically tackles the persistent context blowout in long-running coding agents, and the new models are already live in chat and via API.
OpenAI just launched GPT-5.5 and GPT-5.5 Pro, heavily optimized for autonomous coding, knowledge work, and complex computer use. The model matches GPT-5.4's per-token latency while requiring fewer tokens and setting a new high score of 82.7% on Terminal-Bench 2.0. Why it matters: AI assistance is shifting from step-by-step chatting to letting agents independently plan, test, and finish messy engineering projects.
xAI just rolled out Grok Voice 1.0 via API, designed for complex multi-step enterprise workflows like customer support and phone sales. It reasons in the background with zero added latency, handles noisy calls and strong accents across 25+ languages, and is already handling Starlink's support lines.
Google just made Gemini Embedding 2 generally available via the Gemini API. The natively multimodal embedding model can search and reason across text, images, video, and audio in a single pipeline, helping developers move complex multimodal search and analysis projects straight into production.
