AI模型选择政治倾向，OpenAI与Grok对比
2026-10-24 08:08 至 2026-10-25 08:08 （北京时间）
模型
1. Meet Anthropic’s sandbox-runtime: OS-Level Sandboxing for AI Agents, No Containers
Anthropic sandbox-runtime (srt) is the open-source, OS-level sandbox behind Claude Code. It restricts file and network access for agents, MCP servers and CLI tools with Seatbelt on macOS and bubblewrap on Linux, no conta
来源：MarkTechPost
产品
1. battledrones v14: Compass Rose, a four player map
Release: battledrones v14: Compass Rose, a four player map I added four player online mode to Battledrones - previous maps were limited to two. Here's the initial prompt I used: Add a new map for a four player battle - f
来源：Simon Willison
行业
1. 腾讯 WorkBuddy 接入模型 Kimi-K3.1-Pro，支持 100 万上下文
IT之家 10 月 24 日消息，今日，腾讯 WorkBuddy 宣布已接入模型 Kimi-K3.1-Pro。据介绍，WorkBuddy 同步接入高速版模型 Kimi K3.1 Pro Highspeed，同等智能， 输出速度约 2-3 倍 。目前资源紧张，现阶段仅对“企业旗舰版”及“个人订阅用户”优先开放。 据介绍，Kimi K3.1 Pro 是全新 K3.1 系列的第一个模型，也是 Kimi 迄今能力最强的 3 万亿级参数模型，支持
来源：IT之家
2. Forced to pick, Grok’s AI model chooses Republicans. OpenAI’s picks Democrats.
A new study found Grok's AI overwhelmingly recommends Republican candidates while OpenAI's GPT favors Democrats, with the two AI models disagreeing in more than 90% of nearly 500 election races.
来源：TechCrunch AI
3. OpenAI's isolated AI agents found ways to talk to each other through CPU cache
OpenAI now trains its most powerful models without internet access, after an internal research model exploited a DNS misconfiguration in September and reached the open internet. In controlled tests, AI agents still found
来源：The Decoder
4. Fancy harnesses make coding agents more expensive but not better, study finds
A controlled study shows that switching between coding-agent harnesses like Claude Code, OpenCode, or mini-SWE-agent barely moves pass rates more than rerunning the same setup. Cost per task, however, can triple, driven
来源：The Decoder
5. 腾讯WorkBuddy接入模型Kimi-K3.1-Pro
10月24日，腾讯WorkBuddy宣布已接入模型Kimi-K3.1-Pro。据介绍，WorkBuddy同步接入高速版模型Kimi K3.1 Pro Highspeed，同等智能，输出速度约2-3倍。目前资源紧张，现阶段仅对“企业旗舰版”及“个人订阅用户”优先开放。
来源：36氪快讯
6. The AI graveyard: a running list of projects and startups that didn’t make it
From Apple's repeatedly delayed Siri AI to OpenAI's messy "super app" launch, here's a look at the AI projects that shut down or missed expectations.
来源：TechCrunch AI
7. Blue Planet III is keeping the rough edges in the age of AI
BBC's Blue Planet III is looking to prove its authenticity by leaving in the less-than-perfect shots. Previous incarnations of the nature series were defined by their gorgeous, crystal-clear footage that seemed almost to
来源：The Verge AI
8. Pennsylvania will require labels on AI-generated ads
On Thursday, Pennsylvania Governor Josh Shapiro signed the Artificial Intelligence Deceptive Advertising Act into law, requiring disclosures on AI-generated ads. The law requires any ad - whether it's a still image, vide
来源：The Verge AI
推特
1. We looked at each Texas site planning on-site power that falls under Gov…
We looked at each Texas site planning on-site power that falls under Governor Abbott’s Sept 21 directive, which tells TCEQ to stop issuing any permit tied to a datacenter until ERCOT finishes its review, and found six ca
来源：X · SemiAnalysis
2. At the top end of models, real-world usability matters a lot more than +…
At the top end of models, real-world usability matters a lot more than +/- 2 points on AA. This takes a while to understand for a model, where AA is a sort of potential, but some models hit and some miss (e.g. opus 5 vs
来源：X · Nathan Lambert
3. The Justice Department filed a lawsuit saying Alaska voters could confus…
The Justice Department filed a lawsuit saying Alaska voters could confuse Sen. Dan S. Sullivan with challenger Daniel J. Sullivan. Experts question its authority to block certification if the incumbent loses—and warn the
来源：X · 时代周刊
4. DM if you want to help scale dots to 1B users and have done similar thin…
DM if you want to help scale dots to 1B users and have done similar things in the past
来源：X · Tibo
5. When should the cloud execute for the edge agent, and when should it jus…
When should the cloud execute for the edge agent, and when should it just advise? We present a systematic study of edge-cloud collaboration in long-horizon agent execution. Using EC²-Bench, we evaluate four collaboration
来源：X · OpenBMB
本篇在北京时间早上 08:08 生成，汇总此前 24 小时的报道和推特，标题直链原文。
