2026-01-28
Today, we release SERA-32B, an approach to coding agents that matches Devstral 2 at just $9,000. It is fully open-source and you can train your own model easily - at 26x the efficiency of using RL. Paper: https://allenai.org/... Here's how 🧵
SiliconANGLE
Ai2 launches Open Coding Agents, starting with SERA, an open-source family that includes 32B and 8B parameter models designed to adapt to private codebases
SERA is based on two key innovations: 1. You don't need unit tests to generate high-quality code data. 2. Unverified coding data can be equal to verified data. This enables SoTA performance and new repository agents that outperform frontier open models on personal codebases. [image]
SiliconANGLE
Ai2 launches Open Coding Agents, starting with SERA, an open-source family that includes 32B and 8B parameter models designed to adapt to private codebases
2026-01-27
Today, we release SERA-32B, an approach to coding agents that matches Devstral 2 at just $9,000. It is fully open-source and you can train your own model easily - at 26x the efficiency of using RL. Paper: https://allenai.org/... Here's how 🧵
SiliconANGLE
Ai2 launches Open Coding Agents, starting with SERA, an open-source family that includes 32B and 8B parameter models designed to adapt to private codebases
Artificial intelligence is moving swiftly, changing how developers craft, as code flows ever faster into repositories such as GitHub …
SERA is based on two key innovations: 1. You don't need unit tests to generate high-quality code data. 2. Unverified coding data can be equal to verified data. This enables SoTA performance and new repository agents that outperform frontier open models on personal codebases. [image]
SiliconANGLE
Ai2 launches Open Coding Agents, starting with SERA, an open-source family that includes 32B and 8B parameter models designed to adapt to private codebases
Artificial intelligence is moving swiftly, changing how developers craft, as code flows ever faster into repositories such as GitHub …