{"url":"https:\/\/x.com\/andonlabs\/status\/1937613090130174261","author_name":"Andon Labs","author_url":"https:\/\/x.com\/andonlabs","html":"\u003Cblockquote class=\"twitter-tweet\"\u003E\u003Cp lang=\"en\" dir=\"ltr\"\u003EOverall, it&#39;s encouraging to see frontier models getting more reliable over long-term tasks. Excited to keep benchmarking future releases, there is still plenty of room for improvement! \u003Ca href=\"https:\/\/t.co\/YXfQ6YpEF1\"\u003Epic.twitter.com\/YXfQ6YpEF1\u003C\/a\u003E\u003C\/p\u003E&mdash; Andon Labs (@andonlabs) \u003Ca href=\"https:\/\/x.com\/andonlabs\/status\/1937613090130174261?ref_src=twsrc%5Etfw\"\u003EJune 24, 2025\u003C\/a\u003E\u003C\/blockquote\u003E\n\u003Cscript async src=\"https:\/\/platform.x.com\/widgets.js\" charset=\"utf-8\"\u003E\u003C\/script\u003E\n\n","width":550,"height":null,"type":"rich","cache_age":"3153600000","provider_name":"X","provider_url":"https:\/\/x.com","version":"1.0"}