Giving coding agents file outlines to save tokens on ultra-large filesblog.sweep.dev1 points·by williamzeng0·il y a 5 mois·0 comments
Show HN: Sweep, Open-weights 1.5B model for next-edit autocompletehuggingface.co534 points·by williamzeng0·il y a 6 mois·153 comments
Using the JetBrains program structure interface for codebase contextblog.sweep.dev3 points·by williamzeng0·il y a 8 mois·0 comments
Decreasing code editing failures by 38% with output normalizationblog.sweep.dev3 points·by williamzeng0·il y a 8 mois·0 comments
Show HN: Sweep, AI autocomplete for JetBrains that rewrites codesweep.dev5 points·by williamzeng0·il y a 9 mois·0 comments
Show HN: Rust BPE tokenizer for Qwen models that's 12x faster than HuggingFacegithub.com5 points·by williamzeng0·il y a 10 mois·0 comments
Teaching LLMs to spell with token healingblog.sweep.dev2 points·by williamzeng0·il y a 10 mois·0 comments
Show HN: Building sub-100ms autocompletion for JetBrains IDEsblog.sweep.dev3 points·by williamzeng0·il y a 10 mois·1 comments
williamzeng0·il y a 12 mois·discusshttps://sweep.dev/ is better than Copilot/Windsurf in PyCharm (disclaimer I am one of the founders)
williamzeng0·il y a 12 mois·discussI 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·il y a 12 mois·discussTransparently 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