Article URL: https://github.com/Higangssh/pvm Comments URL: https://news.ycombinator.com/item?id=47815391 Points: 3 # Comments: 0
今天用 ccs 配置了geminicli，但是运行的时候发现一个问题，一旦根目录有.env这种环境变量的文件，他就跟卡死了一样，半天不回答。但是把.env文件删掉就可以正常使用，这个要怎么弄呢，捣鼓了半天，一直以为是我的配置问题，geminicli来回卸载安装，搞了半天 2 个帖子 - 2 位参与者 阅读完整话题
{ “env”: { “ANTHROPIC_AUTH_TOKEN”: “sk-”, “ANTHROPIC_BASE_URL”: “ https://a-ocnfniawgw.cn-shanghai.fcapp.run ”, “CLAUDE_CODE_ATTRIBUTION_HEADER”: “0”, “CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC”: “1”, “CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS”: “1” }, “includeCoAuthoredBy”: false, “model”: “opus[1m]” } 这个配置一直在出现重试的问题 4 个帖子 - 4 位参与者 阅读完整话题
Article URL: https://www.alien.dev/docs/quickstart Comments URL: https://news.ycombinator.com/item?id=47793166 Points: 1 # Comments: 0
Article URL: https://github.com/Chrilleweb/vscode-dotenv-diff Comments URL: https://news.ycombinator.com/item?id=47778220 Points: 1 # Comments: 1
I want to share a new dataset of 331 reward-hackable environments. These are real environments used in Terminal Bench and adjacent benchmarks. I first got interested in this because, as a reviewer of Terminal Bench, I noticed a lot of our tasks were hackable. I also noticed that many contributors to the benchmark do so because it provides credibility when selling environments to labs. Hence, TBench tasks are, in my opinion, held to a higher quality standard than those being used today for RL. No one is spending hours manually reviewing the $1B in tasks being purchased by major labs. As far as I understand, while everyone knows environments are hackable, nobody has released hundreds of "realistic" environments. Comments URL: https://news.ycombinator.com/item?id=47773298 Points: 6 # Comments: 1
RT，配置文件里括号带上思考等级 "env": { "ANTHROPIC_AUTH_TOKEN": "sk-iVBCgVi6KlDV3aQeX", "ANTHROPIC_BASE_URL": "http://localhost:8085", "ANTHROPIC_REASONING_MODEL": "gpt-5.4(high)", "ANTHROPIC_DEFAULT_OPUS_MODEL": "gpt-5.3-codex(high)", "ANTHROPIC_DEFAULT_SONNET_MODEL": "gpt-5.3-codex(medium)", "ANTHROPIC_DEFAULT_HAIKU_MODEL": "gpt-5.4(auto)", "ENABLE_TOOL_SEARCH": "true" }, 但是claude可以调整effort level，这样不会冲突吗，是会覆盖还是怎样？ 1 个帖子 - 1 位参与者 阅读完整话题
根据发表在《Environmental Research Letters》期刊上的一项研究，1990-2023 年间热带和极地之间的中纬度地区的夏季平均每十年延长约 6 天。城市的变化更为惊人，澳大利亚悉尼的夏季如今持续 130 天，而在 1990 年只有 80 天，相当于每十年增加 15 天。加拿大多伦多的夏季每十年延长 8 天。研究还发现季节的转换变得更突然，春季不是慢慢升温转换到夏季，而是春季突然就暴热切换到夏季。这种骤然变化可能会扰乱依赖季节变化的系统，比如花朵可能在授粉昆虫活跃前就盛开了，农作物可能需要更早播种，春季气温的快速升高可能促使积雪更快融化洪涝风险加大。
Denver registered a 2-1 victory over Wisconsin to win the Frozen Four and claim the program's third national championship in five years.
I built a tool to run multiple AI coding agents in parallel across projects. NeZha is a character from Chinese mythology, famous for having three heads and six arms — which feels like the perfect metaphor for running AI coding agents across multiple projects at once. Claude Code + Codex + Git + Editor, all in one place. Managing sessions in the terminal was getting painful — especially across projects. Comments URL: https://news.ycombinator.com/item?id=47739860 Points: 2 # Comments: 0