Hacker News
Guestbooks: The cozy 90s web fad which shaped the future [video]
Article URL: https://www.youtube.com/watch?v=ZSBYO1BYrDM
Comments URL: https://news.ycombinator.com/item?id=47080335
Points: 1
# Comments: 0
Recycling waste via insect agriculture: Frass impacts on soil and plant health
Article URL: https://acsess.onlinelibrary.wiley.com/doi/10.1002/jeq2.70089
Comments URL: https://news.ycombinator.com/item?id=47080325
Points: 1
# Comments: 0
Reconstructing Biscuit in Clojure
Article URL: https://serefayar.substack.com/p/reconstructing-biscuit-in-clojure
Comments URL: https://news.ycombinator.com/item?id=47080297
Points: 1
# Comments: 0
Gentoo dumps GitHub over Copilot nagware
Article URL: https://www.theregister.com/2026/02/17/gentoo_dumps_github_for_codeberg_over_copilot_nagware/
Comments URL: https://news.ycombinator.com/item?id=47080291
Points: 2
# Comments: 0
Show HN: oMLX – Native Mac inference server that persists KV cache to SSD
I built an open-source LLM inference server optimized for Apple Silicon. The main motivation was coding agents - tools like Claude Code send requests where the context prefix keeps shifting, invalidating KV cache. A few turns later the agent circles back, and your Mac has to re-prefill the entire context from scratch.
oMLX solves this with paged SSD caching. Every KV cache block is persisted to disk. When a previous prefix returns, it's restored instantly instead of being recomputed. This makes long coding sessions significantly faster.
It also supports continuous batching for concurrent requests, multi-model serving (LLM + embedding + reranker) with LRU eviction, block-level KV cache with prefix sharing and copy-on-write, OpenAI and Anthropic compatible APIs, and tool calling. Ships as a signed macOS menubar app with a web dashboard.
GitHub: https://github.com/jundot/omlx
Comments URL: https://news.ycombinator.com/item?id=47080277
Points: 1
# Comments: 0
Single vaccine could protect against all coughs, colds and flus
Article URL: https://www.bbc.com/news/articles/cx2g8rz7yedo
Comments URL: https://news.ycombinator.com/item?id=47080267
Points: 4
# Comments: 0
Show HN:PolyMCP Python Tools with Autonomous Agents
PolyMCP is a framework that exposes functions (in Python or TypeScript) as MCP tools, serves them through standardized MCP servers, and orchestrates them with autonomous agents capable of planning and executing complex workflows.
With PolyMCP, you can: 1. Expose existing functions (in Python or TypeScript) as MCP tools without rewriting the code. 2. Use the PolyClaw agent to dynamically orchestrate tools, break down complex tasks, and adapt to failures, all running in isolated environments via Docker.
PolyMCP is ideal for enterprise automation, DevOps, data pipelines, and internal tool orchestration.
GitHub Repo: https://github.com/poly-mcp/PolyMCP
Comments URL: https://news.ycombinator.com/item?id=47080258
Points: 1
# Comments: 0
Minnesota judge holds federal attorney in civil contempt
Article URL: https://www.cnn.com/2026/02/19/politics/trump-attorney-contempt-minnesota-immigration
Comments URL: https://news.ycombinator.com/item?id=47080255
Points: 6
# Comments: 0
The Observatory of Anonymity
Article URL: https://www.ooa.world/
Comments URL: https://news.ycombinator.com/item?id=47080252
Points: 2
# Comments: 0
A Terminator Ending for Google Privacy Sandbox?
Article URL: https://blog.zgp.org/terminator-ending-for-privacy-sandbox/
Comments URL: https://news.ycombinator.com/item?id=47080245
Points: 1
# Comments: 0
Claude Hero – play Guitar Hero while Claude generates code
Article URL: https://github.com/nhestrompia/claude-hero
Comments URL: https://news.ycombinator.com/item?id=47080243
Points: 1
# Comments: 1
Human Flatus Atlas
Article URL: https://www.flatus.info
Comments URL: https://news.ycombinator.com/item?id=47080241
Points: 1
# Comments: 0
Data Science Weekly – Issue 639
Article URL: https://datascienceweekly.substack.com/p/data-science-weekly-issue-639
Comments URL: https://news.ycombinator.com/item?id=47080237
Points: 1
# Comments: 0
Conductor removing support for Claude subscription authentication
Article URL: https://twitter.com/charlieholtz/status/2024585923619590497
Comments URL: https://news.ycombinator.com/item?id=47079531
Points: 1
# Comments: 0
A review of tumor-treating electric fields (TTFields): clinical advancements
Article URL: https://pmc.ncbi.nlm.nih.gov/articles/PMC10476910/
Comments URL: https://news.ycombinator.com/item?id=47079514
Points: 1
# Comments: 0
What's next for Chinese open-source AI
Article URL: https://www.technologyreview.com/2026/02/12/1132811/whats-next-for-chinese-open-source-ai/
Comments URL: https://news.ycombinator.com/item?id=47079471
Points: 1
# Comments: 0
Show HN: CursorLens – Open-source screen recorder/editor for product demos
Hi HN — I built CursorLens, a free and open-source screen recorder/editor for product demos and walkthroughs.
It started as a fork of OpenScreen, but I reworked a lot of the capture/editing pipeline for a more native macOS workflow.
Current features:
full-screen or window recording native cursor hide/show behavior on macOS camera overlay + microphone recording timeline editing (trim/crop/zoom/cursor effects/annotations) subtitle generation + rough-cut workflow multi-aspect export (16:9, 9:16, 1:1) and batch export audio export controls (gain, loudness normalization, limiter) It’s still in beta, so stability can vary by machine.
Repo: https://github.com/blueberrycongee/CursorLens Releases: https://github.com/blueberrycongee/CursorLens/releases
I’d really appreciate feedback on:
recording reliability across setups editing UX (especially rough cut/subtitles) export speed/quality tradeoffs
Comments URL: https://news.ycombinator.com/item?id=47079466
Points: 1
# Comments: 0
Ask HN: What makes AI agent runtime logs defensible under adversarial audit?
Modern AI agents can execute tools, write to databases, and trigger irreversible actions.
Most teams rely on traditional logging (OpenTelemetry, SIEM, DB audit logs). But under adversarial conditions (audit, litigation, incident response), those logs depend on platform trust and cannot typically be verified independently of the system that produced them.
I’m exploring whether agent runtime evidence should be:
-deterministically canonicalized
-hash-chained
-signed
-optionally externally timestamped
-verifiable offline
The goal isn’t observability. It’s defensibility.
Open questions:
1.Is RFC 3161-style timestamping sufficient to deter practical backdating, or is some form of multi-witness anchoring necessary?
2.In real distributed agent systems, where does replayability break down?
3.At what scale or risk threshold does this move from overengineering to necessary?
Not looking for blockchain/ledger answers — more interested in models that integrate with existing infrastructure.
Trying to understand whether this addresses a real integrity gap in production systems.
Comments URL: https://news.ycombinator.com/item?id=47079460
Points: 1
# Comments: 0
Show HN: Auto-scrolling for WhatsApp group chats
I got tired of scrolling through endless WhatsApp group chats, so I built a browser extension that does the scrolling for me. You can tag contacts as "important" to scroll slower when their messages are in view. You can also hide messages from specific users (click-to-unhide like Slack has).
Comments URL: https://news.ycombinator.com/item?id=47079430
Points: 1
# Comments: 0
A Yale Professor's Investment Formula Says You Need More Stocks
Article URL: https://www.wsj.com/finance/investing/yale-james-choi-portfolio-formula-stocks-02a96afb
Comments URL: https://news.ycombinator.com/item?id=47079419
Points: 1
# Comments: 0
