Product: IDE plugins (Next channel)
Today we’re releasing SWE-1.5, our first fast agent model.
What changed
- Today we’re releasing SWE-1.5, our first fast agent model.
- It achieves near-SOTA coding performance while setting a new standard for speed.
- Link to announcement: https://x.com/cognition/status/1983662836896448756
- Fast Context is now available - you can trigger fast context via pressing Cmd + Enter when sending a prompt. For enterprise users, please make sure your organization has turned on Fast Context.
- We’ve trained a first-of-its-kind family of models: SWE-grep and SWE-grep-mini.
- Designed for fast agentic search (>2800 TPS), these models surface the right files to your coding agent 20x faster than before.
- Read the blog: https://cognition.com/blog/swe-grep
- General UI improvements - font sizes in Cascade are more standardized, removed unnecessary close button from Cascade.
Source
- Official notes: https://docs.devin.ai/windsurf/plugins/changelog-next
Why it matters
If you use IDE plugins, skim the official notes above and decide what to try in your next session. Tag the right surface — Cloud vs Desktop vs CLI — before you change workflows.
Fan coverage from Devin Central — not an official Cognition announcement. Devin is a trademark of Cognition.