Giving coding agents file outlines to save tokens on ultra-large filesblog.sweep.dev1 ポイント·投稿者 williamzeng0·5 か月前·0 コメント
Show HN: Sweep, Open-weights 1.5B model for next-edit autocompletehuggingface.co534 ポイント·投稿者 williamzeng0·6 か月前·153 コメント
Using the JetBrains program structure interface for codebase contextblog.sweep.dev3 ポイント·投稿者 williamzeng0·8 か月前·0 コメント
Decreasing code editing failures by 38% with output normalizationblog.sweep.dev3 ポイント·投稿者 williamzeng0·8 か月前·0 コメント
Show HN: Sweep, AI autocomplete for JetBrains that rewrites codesweep.dev5 ポイント·投稿者 williamzeng0·9 か月前·0 コメント
Show HN: Rust BPE tokenizer for Qwen models that's 12x faster than HuggingFacegithub.com5 ポイント·投稿者 williamzeng0·10 か月前·0 コメント
Show HN: Building sub-100ms autocompletion for JetBrains IDEsblog.sweep.dev3 ポイント·投稿者 williamzeng0·10 か月前·1 コメント
williamzeng0·12 か月前·議論https://sweep.dev/ is better than Copilot/Windsurf in PyCharm (disclaimer I am one of the founders)
williamzeng0·12 か月前·議論I think the two big things are privacy mode on by default and zero data retention by default.No code or prompts are stored unless you opt-in. We also have on-prem deployment options but it's much more expensive.
williamzeng0·12 か月前·議論Transparently I'm a founder building a plugin that's like "Cursor for JetBrains IDEs", if you're an windsurf user you might like us: https://plugins.jetbrains.com/plugin/26860-sweep-ai