正在加载视频...

视频加载失败

Unlinkable.

36,564 次观看 • 17 天前 •via X (Twitter)

0 条评论

暂无评论

原始帖子的评论将显示在这里

相关视频

Introducing: Portfolio Privacy-focused, multi-wallet portfolio tracker made for Hyperliquid. Highlights: - Multi-wallet tracking is unlinkable, so you can privately track all your wealth across wallets on Hyperliquid - View aggregated portfolio distribution of all your wallets, including Spot, Perps, DeFi, Staking, and NFTs - No need to connect your wallet - Click to go trade any asset - Portfolio worth updates in real-time Features: - Use the interactive HypeWheel or Heatmap to easily see your wealth distribution across various asset types - View totals per portfolio or across aggregated wallets on the top bar - Merge Core & EVM spot tokens into one list - Check your points on ecosystem protocols - All HyperEVM tokens and NFTs are supported - Track everything on HyperCore: Spot, Perps, Staking, Vaults - Nearly all DeFi protocols supported, with more actively being added - Customize the small-balances threshold and hide them - All global currencies supported Comprehensive DeFi position tracking and ecosystem-wide points data is available thanks to the Hyperfolio API. Massive respect to stableAPY.hl for putting in the hard work to gather this data, and to for putting the ecosystem first and making this API available for builders in the community. 🛡️ Every wallet request is routed through one of five random server regions, and all request logs are disabled. No data remains on our servers that can link multiple wallets to the same visitor. Hyperliquid.

HL Eco

49,254 次观看 • 1 年前

Sharing a super simple, user-owned memory module we've been playing around: nanomem The basic idea is to treat memory as a pure intelligence problem: ingestion, structuring, and (selective) retrieval are all just LLM calls & agent loops on a on-device markdown file tree. Each file lists a set of facts w/ metadata (timestamp, confidence, source, etc.); no embeddings/RAG/training of any kind. For example: - `nanomem add ` starts an agent loop to walk the tree, read relevant files, and edit. - `nanomem retrieve ` walks the tree and returns a single summary string (possibly assembled from many subtrees) related to the query. What’s nice about this approach is that the memory system is, by construction: 1. partitionable (human/agents can easily separate `hobbies/snowboard.md` from `tax/residency.md` for data minimization + relevance) 2. portable and user-owned (it’s just text files) 3. interpretable (you know exactly what’s written and you can manually edit) 4. forward-compatible (future models can read memory files just the same, and memory quality/speed improves as models get better) 5. modularized (you can optimize ingestion/retrieval/compaction prompts separately) Privacy & utility. I'm most excited about the ability to partition + selectively disclose memory at inference-time. Selective disclosure helps with both privacy (principle of least privilege & “need-to-know”) and utility (as too much context for a query can harm answer quality). Composability. An inference-time memory module means: (1) you can run such a module with confidential inference (LLMs on TEEs) for provable privacy, and (2) you can selectively disclose context over unlinkable inference of remote models (demo below). We built nanomem as part of the Open Anonymity project ( but it’s meant to be a standalone module for humans and agents (e.g., you can write a SKILL for using the CLI tool). Still polishing the rough edges! - GitHub (MIT): - Blog: - Beta implementation in chat client soon: Work done with amazing project co-leads Amelia Kuang Coco Xu Erik Chi !!

Ken Liu

73,840 次观看 • 3 个月前

Yellow girl performance 😍
0:48

Sensitive content

Yellow girl performance 😍

V R ♠️

114,971 次观看 • 5 个月前