williamzeng0
Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete
https://huggingface.co/sweepai/sweep-next-edit-1.5B
Hey HN, we trained and open-sourced a 1.5B model that predicts your next edits, similar to Cursor. You can download the weights here (https://huggingface.co/sweepai/sweep-next-edit-1.5b) or try it in our JetBrains plugin (https://plugins.jetbrains.com/plugin/26860-sweep-ai-autocomp...).Next-edit autocomplete differs from standard autocomplete by using your recent edits as context when...
Using the JetBrains program structure interface for codebase context
Sweep (YC S23) is hiring to build autocomplete for JetBrains
Decreasing code editing failures by 38% with output normalization
Show HN: Sweep, AI autocomplete for JetBrains that rewrites code
Hi HN, I've been a JetBrains user for the last couple of years, and felt that JetBrains was missing a strong autocomplete tool. Over the last 6 months, we've fine-tuned our own model, built our own inference stack, and integrated it deeply into the IDE. You can use the autocomplete plugin for free (no sign up required) on the JetBrains marketplace.Here's how we got here:We started with standard...
Show HN: Rust BPE tokenizer for Qwen models that's 12x faster than HuggingFace
Teaching LLMs to spell with token healing
Show HN: Building sub-100ms autocompletion for JetBrains IDEs
Show HN: Sweep – Cursor Tab Alternative for JetBrains IDEs
https://plugins.jetbrains.com/plugin/26860-sweep-ai
Hi HN, we’re Kevin and William from Sweep. We’ve spent the last couple of months building a custom tab model (like Cursor/Windsurf) for JetBrains IDEs. You can use the plugin in your favorite IDE via the JetBrains marketplace.Our autocomplete is aware of your recent changes, has full-codebase context, and is exceptionally fast (200ms P50 latency). We’ve deployed this across regions in us-west,...
Re:The IDE isn't going away
on Monday July 21, 2025 @05:12PM (#44640472)
That makes sense! Appreciate the sentiment.
Re:The IDE isn't going away
on Monday July 21, 2025 @05:11PM (#44640462)
Appreciate the comment!
Re:The IDE isn't going away
on Monday July 21, 2025 @05:10PM (#44640453)
Sorry about that everyone! I didn't expect the formatting to look like this. Thanks for summarizing it here.
Re:Coding with LLMs in the summer of 2025 (an update)
on Monday July 21, 2025 @01:26AM (#44632034)
I'm actually building something for JetBrains, it's called https://sweep.dev. We're trying to bring next-edit prediction (like in Cursor) to JetBrains IDEs.
Re:Cognition (Devin AI) to Acquire Windsurf
on Tuesday July 15, 2025 @07:21PM (#44576958)
https://sweep.dev/ is better than Copilot/Windsurf in PyCharm (disclaimer I am one of the founders)
Re:AWS launches Kiro, its Cursor clone
on Tuesday July 15, 2025 @07:19PM (#44576944)
IDEs are here to stay, I built an AI plugin for IntelliJ for that reason (https://sweep.dev/)
Re:AWS launches Kiro, its Cursor clone
on Tuesday July 15, 2025 @07:17PM (#44576931)
Yes but I think they have worse things to worry about, namely Cursor.
Also if you're interested our plugin is https://sweep.dev!
Re:The IDE isn't going away
on Tuesday July 15, 2025 @01:18PM (#44573549)
You can try Sweep here! https://plugins.jetbrains.com/plugin/26860-sweep-ai
The IDE isn't going away
Somehow this is a contrarian opinion, but debuggers, code navigation, and autocomplete still matter. Developers are not being replaced.Starting a codegen companyKevin and I started Sweep two years ago.In 2023 GitHub Copilot was the status quo.We saw it and thought “this is not the final state of software development”."What do we do at our day jobs?" Almost all of our time was spent editing...
Re:AWS launches Kiro, its Cursor clone
on Monday July 14, 2025 @05:21PM (#44565490)
do you mean jetbrains ai team?
Re:Cognition (Devin AI) to Acquire Windsurf
on Monday July 14, 2025 @05:13PM (#44565376)
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.
Re:AWS launches Kiro, its Cursor clone
on Monday July 14, 2025 @04:52PM (#44565119)
Shameless plug but our co is building a AI plugin for JetBrains that has next edit autocomplete + a strong coding agent (sweep dev)
Re:AWS launches Kiro, its Cursor clone
on Monday July 14, 2025 @04:51PM (#44565107)
VSCode is way worse for large codebases and also much worse for Ruby, Golang, etc.
Re:Cognition (Devin AI) to Acquire Windsurf
on Monday July 14, 2025 @04:34PM (#44564943)
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
Re:JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier
on Wednesday April 16, 2025 @01:16PM (#43707903)
not yet - but it's fairly straightforward to implement the UI once you get the AI down. i've been working on an MVP here: https://docs.sweep.dev/autocomplete#next-edit-prediction-in-...
Re:JetBrains IDEs Go AI: Coding Agent, Smarter Assistance, Free Tier
on Wednesday April 16, 2025 @01:14PM (#43707863)
I think they're getting there but missing big features like a high quality "Apply" workflow and next-edit predictions.
I'm working with two of my friends to fill the missing pieces as a JetBrains plugin: https://docs.sweep.dev/
Why AI coding agents belong in the IDE
Re:Show HN: AI in JetBrains that doesn't suck
on Thursday April 10, 2025 @02:12PM (#43646612)
Ah - we do support PhpStorm. Docs will be updated.
We only support Sonnet 3.5/3.7 (we still go back and forth on which one we like), and we also support on-prem deployments!
Re:Show HN: AI in JetBrains that doesn't suck
on Thursday April 10, 2025 @02:09PM (#43646578)
Fixing this! This was a prompting bug re: claude sonnet.
Show HN: AI in JetBrains that doesn't suck
Hi HN! We’re William and Kevin from Sweep AI. We’re building an AI coding assistant for JetBrains IDEs.We previously tried to build an AI junior developer that writes GitHub PRs (https://news.ycombinator.com/item?id=36987454). It was fun, but we ultimately decided to pivot. Here are a couple reasons it didn’t work:1. Our agent really needed a well defined spec to have a >90% success rate on...