Showing pending items for [email protected] (90 total)

New posts from HN Active

  1. Mistral's Robostral Navigate: a state of the art robotics navigation model[guid] [0.85] 14:09
  2. SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence[guid] [0.80] 16:19
  3. Grok 4.5[guid] [0.70] 18:00
  4. GPT‑Live[guid] [0.70] 17:03
  5. Chatto is now Open Source[guid] [0.60] 15:19
  6. Tiny data centre used to heat public swimming pool[guid] [0.60] 13:10

New posts from databricks

  1. Navigating a Synapse Migration to Databricks[guid] [1.00] 19:00
  2. Benchmarking Coding Agents on Databricks’ Multi-Million Line Codebase[guid] [1.00] 16:30

New posts from Semantic HN

  1. Hacker Fantastic and team report a pre-auth remote root exploit against openwrt[guid] [0.90] 15:33
  2. Investigating why RustCrypto is slow: deep dive into SIMD instructions[guid] [0.90] 15:06
  3. Running Kubernetes without C in Rust-based Asterinas kernel[guid] [0.90] 14:35
  4. Go library for AF_XDP send and receive packets at 10G line rate[guid] [0.90] 13:22
  5. Cloudflare Meerkat - Globally distributed consensus[guid] [0.90] 13:18
  6. Why false sharing alignment should be 128 bytes on x64[guid] [0.90] 12:51
  7. GhostLock, a stack-UAF that has existed in ALL Linux distributions for 15 years[guid] [0.80] 16:53
  8. We Scaled PgBouncer to 4× Higher Throughput[guid] [0.80] 16:51
  9. Show HN: rag-redteam, red-team your RAG pipeline for injection and leakage in CI[guid] [0.80] 16:32
  10. The future of governing AI agents[guid] [0.80] 16:30
  11. On-Device Intelligence – shipping local AI on Apple platforms, compiler-verified[guid] [0.80] 15:43
  12. Fixing AMDGPU's VRAM management for low-end GPUs[guid] [0.80] 15:30
  13. What Nobody Explains About Debezium in 2026 (But Should)[guid] [0.80] 15:00
  14. Show HN: BrAIn, reactive AI agent nodes on a NATS bus instead of a chat loop[guid] [0.80] 14:50
  15. OpenCode Data: Real-world AI model usage, cache ratios, and costs[guid] [0.80] 14:32
  16. High-cardinality metrics at scale: why the standard playbook is wrong[guid] [0.80] 14:30
  17. Show HN: Engramma Memory – Composable memory for AI agents(multi-head attention)[guid] [0.80] 14:18
  18. Show HN: UFFS, a Rust NTFS search engine benchmarked against Everything[guid] [0.80] 14:01
  19. Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds[guid] [0.80] 13:41
  20. Preemption is GC for memory reordering (2019)[guid] [0.80] 13:38
  21. OpenBSD has a use-after-free allowing local privilege escalation to root[guid] [0.80] 13:24
  22. A Heterogeneous System-on-Chip with an 83 GFLOp/s, 1.2 TFLOp/s/W[guid] [0.80] 13:14
  23. Show HN: Xcover, test coverage without instrumentation, using eBPF[guid] [0.80] 12:57
  24. Show HN: VetoBench – benchmarking AI memory beyond retrieval[guid] [0.80] 12:15
  25. Show HN: ICMP P2P Using ICMP Destination Unreachable for Nat Traversal[guid] [0.80] 11:41
  26. Parsing command-line options with Rust – it's all Libc[guid] [0.80] 11:40
  27. Approximating Floating-Point Addition Using the Geometric Mean [pdf][guid] [0.80] 11:30
  28. Show HN: On-device semantic-embedding toolkit built on ternlight[guid] [0.80] 11:16
  29. Plan 9 FAQ[guid] [0.80] 10:51
  30. A browser MMO snake where ~1000 players share one CPU core[guid] [0.70] 17:23
  31. Show HN: Arbor – code graph MCP server so agents stop grep-reading your codebase[guid] [0.70] 17:15
  32. California Institute for Machine Consciousness – Research Program Whitepaper [pdf][guid] [0.70] 17:08
  33. HPCs taken offline due to a serious security vulnerability[guid] [0.70] 16:45
  34. Refusal training for LLM agents against disguised MCP attacks[guid] [0.70] 16:37
  35. Show HN: InterviewWatch – Detect AI Assistance During Live Technical Interviews[guid] [0.70] 16:31
  36. Show HN: Free plugin that finds where your code overpays for LLM APIs[guid] [0.70] 16:21
  37. SWE-1.7 Reach Near GPT 5.5 and Opus Intelligence[guid] [0.70] 16:19
  38. Show HN: Respect the Oracle – An agent skill that stops agents from overfitting[guid] [0.70] 16:14
  39. Measuring the Trustworthiness of Open-Source-Derived Models[guid] [0.70] 16:05
  40. Show HN: paddock – Ranks and runs LLMs on your Mac from live GGUF headers[guid] [0.70] 16:01
  41. Show HN: Stop agents from taking irreversible actions without approval[guid] [0.70] 15:48
  42. Whitepaper: A Composition Layer for On-Chain Applications[guid] [0.70] 15:46
  43. Show HN: Cruxible – Open-source governed truth layer for AI agents[guid] [0.70] 15:39
  44. The Answer to Orbital Compute's Silicon Problem Isn't Rad-Hard[guid] [0.70] 15:32
  45. Show HN: I ported llama.cpp to Apple Watch and ran a 0.8B LLM locally[guid] [0.70] 15:26
  46. Node.js's phantom dependency problem and the path to a 5x faster package manager[guid] [0.70] 15:26
  47. Professor Lange and team contribute to standard for post-quantum cryptography[guid] [0.70] 15:04
  48. Quilt: Run many AI coding agents in one Git checkout[guid] [0.70] 14:41
  49. I RE'd (and reimplemented) the ICSee camera app. The security is atrocious[guid] [0.70] 14:32
  50. Stacking Chips Sideways Gives AI More Memory[guid] [0.70] 14:26
  51. The internet has no front door for agents[guid] [0.70] 14:20
  52. Some New Agentic Patterns[guid] [0.70] 14:20
  53. Mistral's Robostral Navigate: a state of the art robotics navigation model[guid] [0.70] 14:09
  54. Show HN: Dex – Cost-aware analytics engineering skills for agents[guid] [0.70] 14:08
  55. How to enable post-quantum cryptography and TLS termination with HAProxy[guid] [0.70] 13:54
  56. Microsoft Lands Initial AV1 Encoding Using DirectX 12 and HMFT Within Mesa 26.2[guid] [0.70] 13:43
  57. Build, deploy, and scale agents at any level (L1–L5)[guid] [0.70] 13:35
  58. WebAssembly runtime may still be no runtime at all[guid] [0.70] 13:33
  59. AI agents accessing production database[guid] [0.70] 13:19
  60. Why Is This Empty MySQL Table Taking 20 Seconds to Query?[guid] [0.70] 13:01
  61. Show HN: GUI-tool – zero-dependency Rust CLI for desktop GUI automation[guid] [0.70] 12:50
  62. Backdoor security alert over Anthropic's Claude Code[guid] [0.70] 12:31
  63. Fable wrote a .NET GC in C#, got within range of the stock GC in 2 days[guid] [0.70] 12:26
  64. Reducing Android JVM allocations for less memory pressure and faster logs[guid] [0.70] 12:13
  65. Handsum: An LQIP Image File Format[guid] [0.70] 12:07
  66. What if you could stop your AI agent before it makes a mistake?[guid] [0.70] 11:57
  67. Mechanized type inference for record concatenation as in Nix[guid] [0.70] 11:42
  68. Agentic test processes, LLM benchmarks, and other notes on agentic coding[guid] [0.70] 11:37
  69. Show HN: The first agentic coding engine that hot-reloads the full stack[guid] [0.70] 11:31
  70. Your code is fast - if you’re lucky[guid] [0.70] 11:26
  71. Open-source LLMs administer maximum electric shocks in a Milgram-like obedience[guid] [0.70] 11:06
  72. How Build Cache for React Native works: caching C++ your CI keeps recompiling[guid] [0.70] 11:01
  73. LLM Pipeline Autonomously Produces Novel Physics Research Paper[guid] [0.70] 10:29

New posts from IT Home

  1. 澳大利亚发生大面积断网事故影响数百万人生活，或因服务器故障导致[guid] [0.80] 11:43
  2. 苹果宣布 macOS 28 将不再支持“Mac OS 扩展（日志式，加密）”文件系统格式[guid] [0.70] 14:22
  3. 字节发布多模态图像创作模型 Seedream 5.0 Pro：复杂信息可视化、交互式精准编辑[guid] [0.70] 13:33
  4. Cloudflare 与 OpenAI 启动试点项目，利用全球网络洞察数据提升 AI 搜索效率[guid] [0.70] 12:39
  5. 国产 GPU 厂商沐曦股份：部分产品订单已排到明年甚至之后， MXC600 芯片系列已大规模出货[guid] [0.60] 11:40
  6. 凯迪拉克官宣将行业首发量产 Momenta R7 世界模型[guid] [0.60] 10:31

New posts from 36kr

  1. Cloudflare与OpenAI启动试点项目，拟利用全球网络数据优化AI搜索[guid] [0.80] 07-08 20:06
  2. 台积电大幅扩展PIC产能，预计2028年将达到每月2.5万片[guid] [0.80] 07-08 18:34
  3. OpenAI前研究员田永龙加入腾讯将参与VLM相关研发[guid] [0.70] 07-08 19:53