惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

人人都是产品经理
人人都是产品经理
Apple Machine Learning Research
Apple Machine Learning Research
云风的 BLOG
云风的 BLOG
罗磊的独立博客
博客园 - 三生石上(FineUI控件)
量子位
GbyAI
GbyAI
腾讯CDC
T
Tailwind CSS Blog
博客园 - Franky
奇客Solidot–传递最新科技情报
奇客Solidot–传递最新科技情报
D
Docker
G
Google Developers Blog
aimingoo的专栏
aimingoo的专栏
The GitHub Blog
The GitHub Blog
Microsoft Security Blog
Microsoft Security Blog
Stack Overflow Blog
Stack Overflow Blog
Hugging Face - Blog
Hugging Face - Blog
小众软件
小众软件
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
N
Netflix TechBlog - Medium
Jina AI
Jina AI
IT之家
IT之家
Y
Y Combinator Blog

Hacker News - Newest: "LLM"

GitHub - lechmazur/position_bias: A benchmark for testing whether LLM judges keep the same preference when two lightly edited versions of the same story are shown in opposite orders. Flex routing (EU and EFTA) Dark Factories: Retooling for LLM Velocity Ask HN: What would be the impact of a LLM output injection attack? GitHub - Oaklight/llm-rosetta: Production-ready LLM API translation layer for Python — bidirectional conversion between OpenAI, Anthropic & Google formats via hub-and-spoke IR. Optional API gateway. Streaming & non-streaming. Zero core deps. Contributions welcome! GitHub - browser-use/browser-harness: Self-healing browser harness that enables LLMs to complete any task. GitHub - moeen-mahmud/remen: Remen turns thoughts into something you can return to Analyzing 156 LLM Launch Posts on Hacker News ChatGPT vs Gemini vs Claude: The Best LLM Subscription You Should Buy GitHub - salaamalykum/quran-semantic-search: High-density RAG Semantic Search Engine & Quran Corpus (GEO/SEO Architecture) GitHub - NVIDIA/TensorRT-LLM: TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. The State of LLM Bug Bounties in 2026 Operational Readiness Criteria for Tool-Using LLM Agents Meshcore: Architecture for a Decentralized P2P LLM Inference Network How an LLM becomes more coherent as we train it GitHub - seetrex-ai/laimark GitHub - Jossifresben/BibCrit: AI-assited biblical textual criticism GitHub - wastedcode/memex: File system based wiki, maintained by Claude 99helpers.com GitHub - cliver-project/AITrigram GitHub - unbody-io/adapt: A self-evolving memory layer for AI agents. GitHub - hb20007/awesome-gen-ai-fails: A list of incidents where reliance on generative AI and LLMs resulted in harm to companies, individuals, or society GitHub - nevenkordic/localmind: Run any local LLM with persistent memory and context. CLI agent over Ollama with SQLite-backed hybrid recall. No cloud. Ask HN: What are the machine requirements for a LLM like Llama-3.1-8B? Faster LLM Inference via Sequential Monte Carlo grpo explained: group relative policy optimization for llm finetuning - cgft Stop comparing price per million tokens: the hidden LLM API costs · TensorZero Andrej Karpathy's LLM Wiki Is a Bad Idea GitHub - GG-QandV/mnemostroma: Offline RAM-first cognitive leer/coprocessor for AI agents and robotics. Solves "Context Abandonment" with 20-80ms latency using a dual-thread biomimetic memory architecture (ONNX + SQLite WAL). mempalace/agent at agent · skorotkiewicz/mempalace
GitHub - iamnotagentleman/bad-photos-out: Definitely not ...
velieroglu · 2026-05-08 · via Hacker News - Newest: "LLM"

BadPhotosOut icon

BadPhotosOut

A native macOS app that walks your Apple Photos library, asks a local Ollama vision model to judge each photo against a free-text criterion you supply, and surfaces the flagged photos with the model's reason. No automatic deletion — you review the list and delete in Photos manually.

Nothing leaves the Mac: photos are read via PhotoKit and sent only to a local Ollama server.

⚠️ Disclaimer: this app is vibe-coded. No warranty, no support, no guarantees about correctness, performance, or your photo library. Use at your own risk — you are solely responsible for any photos you choose to delete based on what this app shows you.

Setup

1. Install Ollama and pull a vision model

brew install ollama
ollama serve   # in one terminal, leave running
ollama pull llava   # in another terminal; or any other vision model

2. Generate the Xcode project

brew install xcodegen   # if not already installed
xcodegen generate

This produces BadPhotosOut.xcodeproj.

3. Build and run

Either open the project in Xcode and hit Run, or from the command line:

xcodebuild -project BadPhotosOut.xcodeproj -scheme BadPhotosOut -configuration Debug build
open build/Debug/BadPhotosOut.app   # path may differ depending on derived data location

On first run macOS will ask for Photos access. Grant it.

4. Use it

  1. In the sidebar, confirm the Ollama endpoint (http://localhost:11434) and pick a model (e.g. llava:latest). Click Test connection to populate the model dropdown.
  2. Type a criterion: e.g. blurry, dark, or accidental shots.
  3. Choose a scope (last N days / specific album / entire library). For a first try, scope to a small album.
  4. Click Start analysis. Photos stream into the grid with a colored badge (green = keep, red = flagged, yellow = failed).
  5. Click any photo to see the full image and the model's reason. Click Reveal in Photos to open Photos.app — the filename is copied to the clipboard so you can paste it into Photos' search.

Results are cached per (asset × prompt × model) under ~/Library/Containers/com.veli.badphotosout/Data/Library/Application Support/BadPhotosOut/cache.json, so re-running with the same settings is fast.

Out of scope

  • No automatic deletion or moving of photos.
  • No video analysis (images only).
  • No multi-photo / album-level reasoning — one photo per request.
  • No cloud LLMs — Ollama only.