Hacker News

Article URL: https://www.weforum.org/publications/four-futures-for-jobs-in-the-new-economy-ai-and-talent-in-2030/

Comments URL: https://news.ycombinator.com/item?id=47073826

Points: 1

# Comments: 0

Article URL: https://twitter.com/scottbelsky/status/2024481376402120733

Comments URL: https://news.ycombinator.com/item?id=47073813

Points: 1

# Comments: 0

Article URL: https://journals.sagepub.com/doi/10.1177/1024529420910382

Comments URL: https://news.ycombinator.com/item?id=47073810

Points: 2

# Comments: 1

Article URL: https://www.bitdefender.com/en-us/blog/hotforsecurity/dutch-police-arrest-man-hacking-accidentally-sending-confidential-files

Comments URL: https://news.ycombinator.com/item?id=47073783

Points: 3

# Comments: 0

Hi HN, Built llm-use: a lightweight Python toolkit for efficient agent workflows with multiple LLMs. Core pattern: strong model (Claude/GPT-4o/big local) for planning + synthesis; cheap/local workers for parallel subtasks (research, scrape, summarize, extract…). Features: • Mix Anthropic, OpenAI, Ollama, llama.cpp • Smart router: cheap/local first, escalate only if needed (learned + heuristic) • Parallel workers (–max-workers) • Real scraping + cache (BS4 or Playwright) • Offline-first (full Ollama support) • Cost tracking ($ for cloud, 0 local) • TUI chat + MCP server mode • Local session logs Quick example (hybrid):

python3 cli.py exec \ --orchestrator anthropic:claude-3-7-sonnet-20250219 \ --worker ollama:llama3.1:8b \ --enable-scrape \ --task "Summarize 6 recent sources on post-quantum crypto"

Or routed version:

python3 cli.py exec \ --router ollama:llama3.1:8b \ --orchestrator openai:o1 \ --worker gpt-4o-mini \ --task "Explain recent macOS security updates"

MIT licensed, minimal deps, embeddable. Repo: https://github.com/llm-use/llm-use Feedback welcome on: • Routing heuristics you’d find useful • Pain points with agent costs / local vs cloud • Missing integrations? Thanks!

Comments URL: https://news.ycombinator.com/item?id=47073778

Points: 1

# Comments: 0

Article URL: https://salt-lang.dev/

Comments URL: https://news.ycombinator.com/item?id=47073776

Points: 3

# Comments: 0

Article URL: https://blog.vtemian.com/post/vibe-infer/

Comments URL: https://news.ycombinator.com/item?id=47073773

Points: 4

# Comments: 0

Article URL: https://cerebro.vip

Comments URL: https://news.ycombinator.com/item?id=47073772

Points: 1

# Comments: 1

Article URL: https://www.youtube.com/watch?v=TsoFrer-IOA

Comments URL: https://news.ycombinator.com/item?id=47073763

Points: 1

# Comments: 0

Article URL: https://github.com/HKUDS/ClawWork

Comments URL: https://news.ycombinator.com/item?id=47073754

Points: 1

# Comments: 0

Article URL: https://github.com/KD-MM2/libinput-smoothscroll

Comments URL: https://news.ycombinator.com/item?id=47073750

Points: 2

# Comments: 0

For each video, you guess how others react by dropping a point on a 2D pad: Y represents resonance with the content, X represents certainty in that resonance.

The closer your guess is to the crowd’s evolving consensus (which is itself based on others’ guesses), the higher your score. These scores then aggregate into your intuition level - a metric that allows content consumers to be compared.

The idea is to turn the current passive scrolling state of social media into a prediction game where users can compete for social capital through prediction skill rather than content production alone.

Comments URL: https://news.ycombinator.com/item?id=47073749

Points: 1

# Comments: 0

Hi HN,

I'm a solo developer based in Tbilisi, Georgia, and I've been building SnapAPI for the past few months. It's a REST API that does four things: screenshots, PDFs, video recording, and structured data extraction from web pages.

*Why I built it:* I was working on a project that needed link previews. I tried self-hosting Playwright — it works, but managing browser contexts, memory leaks, cookie banners, and crash recovery is a surprising amount of operational work for what should be a simple task. The existing APIs (ScreenshotOne, Urlbox) are solid but expensive and fragmented — you need separate services for screenshots vs. data extraction.

*Architecture:*

- *Fastify* handles the API layer. Chose it over Express for the schema validation (I use it as the single source of truth for request validation) and the ~2x throughput difference under load. - *Playwright* over Puppeteer. The cross-browser support doesn't matter for this use case, but Playwright's `browser.newContext()` isolation and the built-in auto-wait are more reliable for capturing pages at the right moment. - *BullMQ + Redis* for job queuing. Screenshot requests go into a queue, a separate worker process picks them up. This decouples the API from the heavy rendering work and lets me set per-request timeouts without blocking the event loop. - *LRU cache* (in-memory + Redis) with content-hash keys. Same URL + same options = cache hit. This alone handles ~40% of requests on busy days. - *S3-compatible storage* for result delivery. Screenshots get uploaded to object storage, the API returns a pre-signed URL. Files auto-expire after 24h. - *Cookie banner blocking* uses @ghostery/adblocker-playwright with custom filter lists. It's not perfect (nothing is), but it catches ~90% of GDPR popups. For the rest, I inject custom JS to detect and dismiss common consent frameworks (OneTrust, CookieBot, etc.).

The whole thing runs on a single 4-core/8GB VPS in Amsterdam. Playwright is the bottleneck — each browser context uses ~80-120MB — so I cap concurrent renders at 6 and queue the rest. Under normal load (~500-1000 requests/day currently), p95 latency is around 3 seconds for a full-page screenshot.

*What's different from existing services:*

- Combined screenshot + PDF + video + data extraction in one API (most services only do screenshots) - AVIF output format (50-80% smaller than PNG, not widely supported elsewhere) - `extract` endpoint that returns clean markdown, plain text, or structured metadata — useful for RAG/LLM preprocessing pipelines - Starts at $9/month instead of $29-99/month

*What I'm still figuring out:*

- Video recording (MP4 of a browsing session) is the newest feature and the least optimized. FFmpeg encoding after capture adds 2-5 seconds of overhead. - Scaling beyond one server. Playwright doesn't cluster well — I'll probably need to go multi-server with a load balancer routing to render nodes. Haven't needed it yet. - Whether the $9 price point is sustainable. The compute cost per screenshot is ~$0.001, but there's a lot of variance depending on page complexity.

Free tier: 100 requests/month, no credit card. I'm not trying to bait-and-switch — the free tier is genuinely useful for side projects and testing.

Docs: https://snapapi.pics/docs.html

Happy to discuss the architecture, Playwright quirks, or the economics of running a screenshot API. I've learned a lot about browser automation edge cases that I didn't expect going in.

Comments URL: https://news.ycombinator.com/item?id=47073746

Points: 1

# Comments: 0

Article URL: https://arstechnica.com/science/2026/02/rare-gifted-word-learner-dogs-like-to-share-their-toys/

Comments URL: https://news.ycombinator.com/item?id=47073744

Points: 2

# Comments: 0

Not my first time starting a podcast, but definitely the most fun. I enjoy talking to folks about their work, and highlighting trends in semiconductors. I'm starting with some mems companies, and then moving over into covering open source subjects for a bit. If you know someone working on open source silicon, please send me a message!

Comments URL: https://news.ycombinator.com/item?id=47073322

Points: 1

# Comments: 0

Article URL: https://bernsteinbear.com/blog/toy-tbaa/

Comments URL: https://news.ycombinator.com/item?id=47073299

Points: 1

# Comments: 0

Article URL: https://www.ystrickler.com/building-private/

Comments URL: https://news.ycombinator.com/item?id=47073297

Points: 1

# Comments: 0

Article URL: https://www.youtube.com/watch?v=cnX5zJ_qGz0

Comments URL: https://news.ycombinator.com/item?id=47073295

Points: 1

# Comments: 0

Article URL: https://substack.com/home/post/p-188009135

Comments URL: https://news.ycombinator.com/item?id=47073293

Points: 1

# Comments: 0

Article URL: https://economist.com/united-states/2026/02/12/alabama-offers-three-tricks-to-fix-poor-urban-schools

Comments URL: https://news.ycombinator.com/item?id=47073288

Points: 1

# Comments: 0