Hacker News

Subscribe to Hacker News feed
Hacker News RSS
Updated: 20 min 38 sec ago

AI's Amazon Moment

Tue, 11/19/2024 - 10:29am
Categories: Hacker News

Take the Big Project

Tue, 11/19/2024 - 10:25am
Categories: Hacker News

Show HN: LlamaPReview – AI code reviewer trusted by 2000 repos, 40%+ effective

Tue, 11/19/2024 - 9:25am

Hi HN! A month ago, I shared LlamaPReview [1] in SHOW HN. Since then, we've grown to 2000+ repos (60%+ public) with 16k+ combined stars. More importantly, we've made significant improvements in both efficiency and review quality.

Key improvements:

1. ReAct-based Review Pipeline We implemented a ReAct (Reasoning + Acting) pattern that mimics how senior developers review code. Here's a simplified version:

```python def react_based_review(pr_context) -> Review: # Step 1: Initial Assessment - Understand the changes initial_analysis = initial_assessment(pr_context) # Step 2: Deep Technical Analysis deep_analysis = deep_analysis(pr_context, initial_analysis) # Step 3: Final Synthesis return synthesize_review(pr_context, initial_analysis, deep_analysis) ``` 2. Two-stage format alignment pipeline

```python def review_pipeline(pr) -> Review: # Stage 1: Deep analysis with large LLM review = react_based_review(pr_context) # Stage 2: Format standardization with small LLM return format_standardize(review) ``` This two-stage approach (large LLM for analysis + small LLM for format standardization) ensures both high-quality insights and consistent output format.

3. Intelligent Skip Analysis We now automatically identify PRs that don't need deep review (docs, dependencies, formatting), reducing token consumption by 40%. Implementation:

```python def intelligent_skip_analysis(pr_changes) -> Tuple[bool, str]: skip_conditions = { 'docs_only': check_documentation_changes, 'dependency_updates': check_dependency_files, 'formatting': check_formatting_only, 'configuration': check_config_files } for condition_name, checker in skip_conditions.items(): if checker(pr_changes): return True, f"Optimizing review: {condition_name}" return False, "Proceeding with full review" ``` Key metrics since launch: - 2000+ repos using LlamaPReview - 60% public, 40% private repositories - 40% reduction in token consumption - 30% faster PR processing - 25% higher user satisfaction

Privacy & Security: Many asked about code privacy in the last thread. Here's how we handle it: - All PR review processing happens in-memory - No permanent storage of repository code - Immediate cleanup after PR review - No training on user code

What's next: We are actively working on GraphRAG-based repository understanding for better in-depth code review analysis and pattern detection.

Links: [1] Previous Show HN discussion: [https://news.ycombinator.com/item?id=41996859] [2] Technical deep-dive: [https://github.com/JetXu-LLM/LlamaPReview-site/discussions/3] [3] Link for Install (free): [https://github.com/marketplace/llamapreview]

Happy to discuss our approach to privacy, technical implementation, or future plans!

Comments URL: https://news.ycombinator.com/item?id=42183760

Points: 1

# Comments: 0

Categories: Hacker News

Agent Toolkit Pay as you go. Any tool, any currency

Tue, 11/19/2024 - 9:23am

Article URL: https://agenttk.kevz.dev/

Comments URL: https://news.ycombinator.com/item?id=42183735

Points: 1

# Comments: 0

Categories: Hacker News

Secret Santa Generator without signup or back end

Tue, 11/19/2024 - 9:17am

Article URL: https://mael.dev/secretsanta/

Comments URL: https://news.ycombinator.com/item?id=42183679

Points: 2

# Comments: 0

Categories: Hacker News

Pages