AstaBrief 8B: How AllenAI Trained a Small Open Model to Generate Cited Scientific Reports

·1 views

AstaBrief 8B: How AllenAI Trained a Small Open Model to Generate Cited Scientific Reports The Allen Institute for AI (Ai2) released AstaBrief 8B on October 2, 2026 — an open-weights model that takes a research question and a set of retrieved literature excerpts and produces a fully cited scientific report in a single forward pass. The model is now live as "Fast mode" inside Asta, Ai2's agentic platform for scientific work, and the weights, training data, and example workflows are all available on Hugging Face under an Apache 2.0 license. The release is interesting not just because of what the

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Build a Colorful Wave of Cubes on the GPU with bgfx

GPU Implementation with bgfx is a series about building a variety of GPU effects and techniques with bgfx. We'll start with small, working demos and explore animated shapes, drawing many objects efficiently, image effects, and GPU computation. Each article will connect what you see on screen to the code that makes it happen, explaining how the CPU and GPU share the work along the way. For this first installment, let's make something move. The scene below contains a 25 × 25 grid of cubes.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

SvelteKit 3 Just Shipped. Here Is Your Migration Checklist.

Yesterday the Svelte team shipped SvelteKit 3.0, and by this morning the announcement was sitting on the Hacker News front page with over 350 points and more than 150 comments. That is a strong signal. When a framework whose previous major version came out in 2022 jumps a whole number, thousands of production apps have a migration in their future, and the comment section fills up with people comparing notes on what broke. I write TypeScript and Svelte as part of my daily toolkit, so this release matters to me directly. Full disclosure though: I have not yet run this migration on a production a

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Goal drift: how a multi-agent crew ends up solving a different problem

Originally published on Loop & Retry — field notes on building LLM agents that survive production. A single agent that drifts keeps working: loop drift is the failure mode where an agent stays busy — narrating progress, burning tokens, taking actions — without getting any closer to done. A multi-agent crew has a stranger version of the same failure, and it's arguably worse, because nothing about it looks stuck. Every agent in the crew is making real, forward, individually defensible progress. The crew keeps shipping outputs.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

Google’s AI Contribution Pilot Could Create a New Revenue Path for Publisher Content

Google is testing a new way to compensate websites whose material helps make its generative AI responses fresh and factual. The initiative, described publicly as part of broader publisher partnership experiments and reported as the invitation-only AI Contribution Pilot, links potential publisher earnings to content that grounds answers in Google AI experiences such as AI Overviews, AI Mode and Gemini-driven products. The development matters because it explores a revenue model beyond conventional search traffic, advertising and content licensing. Google has not published payment rates, a formul

0 comments Read more at DEV Community