Skip to content

AI 速递 2026-07-05

生成时间:2026/7/5 09:52:55(UTC: 2026-07-05T01:52:55.401Z)

Program-as-Weights: A Programming Paradigm for Fuzzy Functions

Section titled “Program-as-Weights: A Programming Paradigm for Fuzzy Functions”

👍 72 · arXiv

Many everyday programming tasks resist clean rule-based implementation, such as alerting on important log lines, repairing malformed JSON, or ranking search results by intent, and are increasingly out…

AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents

Section titled “AgenticSTS: A Bounded-Memory Testbed for Long-Horizon LLM Agents”

👍 44 · arXiv

Memory for a long-horizon LLM agent is a contract about what each future decision is allowed to see. The simplest contract appends past observations, tool calls, and reflections to every prompt, which…

EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments

Section titled “EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments”

👍 41 · arXiv

Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended soft…

PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception

Section titled “PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception”

👍 38 · arXiv

We introduce PerceptionRubrics, a rubric-based evaluation framework that addresses the gap between saturated benchmark scores and real-world brittleness. Shifting evaluation from holistic semantic mat…

👍 37 · arXiv

Hybrid attention models improve long-context efficiency by retaining only a subset of full-attention layers and replacing the remaining layers with linear attention. However, the effectiveness of Tran…

  • @modelcontextprotocol/server-everything@2026.7.4
  • @modelcontextprotocol/server-filesystem@2026.7.4
  • @modelcontextprotocol/server-sequential-thinking@2026…

链接https://github.com/modelcontextprotocol/servers/releases/tag/2026.7.4

Release 0.143.0-alpha.36

链接https://github.com/openai/codex/releases/tag/rust-v0.143.0-alpha.36

GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance

Section titled “GPT-5.5 Codex reasoning-token clustering may be leading to degraded performance”

Article URL: https://github.com/openai/codex/issues/30364 Comments URL: https://news.ycombinator.com/item?id=48789428 Points: 145

来源Hacker News AI

AI has torched the market for junior programmers

Section titled “AI has torched the market for junior programmers”

Article URL: https://seldo.com/posts/ai-has-torched-the-market-for-junior-programmers/ Comments URL: https://news.ycombinator.com/item?id=48788361 Points: 85

来源Hacker News AI

2026 Unslop AI-Written Fiction Contest Results

Section titled “2026 Unslop AI-Written Fiction Contest Results”

Article URL: https://www.hyperstitionai.com/unslop-results Comments URL: https://news.ycombinator.com/item?id=48782890 Points: 60

来源Hacker News AI

New serious vulnerabilities spiked around release of Claude Mythos Preview

Section titled “New serious vulnerabilities spiked around release of Claude Mythos Preview”

Article URL: https://epoch.ai/data-insights/cve-severity-spike Comments URL: https://news.ycombinator.com/item?id=48780056 Points: 151

来源Hacker News AI

Kagi Changelog (July 2): Heads, tails, and an AI toggle

Section titled “Kagi Changelog (July 2): Heads, tails, and an AI toggle”

Article URL: https://kagi.com/changelog#10959 Comments URL: https://news.ycombinator.com/item?id=48779352 Points: 65

来源Hacker News AI

AI saves about 3% of your hours, and almost none of it reaches the money

Section titled “AI saves about 3% of your hours, and almost none of it reaches the money”

Article URL: https://okaneland.com/study/ai-productivity-roi-at-work/ Comments URL: https://news.ycombinator.com/item?id=48777257 Points: 76

来源Hacker News AI

Instead of banning AI, I made a classroom contract with my students

Section titled “Instead of banning AI, I made a classroom contract with my students”

Article URL: https://www.science.org/content/article/instead-banning-ai-i-made-classroom-contract-my-students Comments URL: https://news.ycombinator.com/item?id=48775499 Points: 89

来源Hacker News AI

Article URL: https://www.elenaverna.com/p/please-stop-the-ai-confidence-theater Comments URL: https://news.ycombinator.com/item?id=48774414 Points: 232

来源Hacker News AI