gpt-6-luna (AI model): news timeline & CVEs

Exa Launches Agent Ultra: A Subagent Swarm Deep Research API Built for Exhaustive List Building

Exa launched Agent Ultra, a hosted subagent research API it says leads four deep-research benchmarks.

Exa released Agent Ultra, the highest-effort mode of its hosted Exa Agent API, for exhaustive list building, entity enrichment, and multi-source research. It splits tasks across parallel subagents and mixes frontier and faster models, invoked by setting effort to ultra. Exa’s vendor-reported results are WANDR soft recall 81.4%, DeepSearchQA F1 93.9%, WideSearch row-level F1 58.9%, and 2,451 passing entities per Company Find-All task, ahead of Opus 5.5, GPT-6 Astra, and Perplexity Agent. Typical runs take about 30 minutes, very hard tasks up to three hours, at up to $20 per run by default.

MarkTechPostSep 26, 08:04 UTC · 1d agoAI tools & infra

A single function Jev-like wrapper for LLMs, including vision models

A developer blog shows a Jev-style logprob wrapper that scores webcam frames with text and vision LLMs.

A developer blog describes a small Python wrapper that turns LLM token log probabilities into fast structured answers, including for vision models. The prompt asks for a single option letter while requesting top logprobs, then maps those letters to choices, booleans, or scores. The author adds image attachments to a Jev-like JSON format, sends webcam JPEGs, and asks whether a person or plant is visible, whether the scene is indoors, and how bright it is. Locally, Gemma 4 12B on an RTX 3090 processed about one frame per second across three questions, while OpenAI gpt-6-luna reached about 0.2 FPS in the same setup.

Hacker News · AISep 26, 04:20 UTC · 1d agoAI tools & infra HN 42↑ · 2 comments

llm 0.36

llm 0.36 adds GPT-6 Sol and Luna IDs and blocks chat for single-turn models.

Simon Willison released llm 0.36, adding OpenAI model identifiers gpt-6-sol for GPT-6 Sol and gpt-6-luna for GPT-6 Luna. Plugins can declare supports_conversation as false; the tool then raises ConversationNotSupported and refuses chat sessions that include assistant or tool history. The first plugin using the flag is llm-typesafe. Reasoning traces in Markdown log output are now wrapped in HTML details and summary tags, alongside bug fixes from five contributors.

Simon WillisonSep 22, 18:48 UTC · 4d agoAI tools & infra

gpt-6-luna

Timeline3 articles

Appears with

Exa Launches Agent Ultra: A Subagent Swarm Deep Research API Built for Exhaustive List Building

A single function Jev-like wrapper for LLMs, including vision models

llm 0.36