HN 提问：最近一次只有前沿模型才能完成的任务是什么？
14 分•作者: thedebuglife•3 个月前
我看到一种反复出现的说法，即落后前沿模型6个月的开放（权重）模型足以应对大多数“工作”。如果您在过去一个月内遇到一个具体的任务，其中GLM/DeepSeek/Kimi/Qwen失败而Opus/Fable/GPT成功（反之亦然！），请分享。
我将提供一个模板，因为我也经常看到发帖者抱怨缺乏上下文：
- 任务（简短且具体）
- 尝试的廉价模型及其失败原因
- 前沿模型及其是否成功
- 事后看来，前沿-1是否就足够了？
查看原文
ive been seeing a recurring claim that open (weight) models 6 months behind the frontier are good enough for the majority of ‘work’. if you've had a concrete task in the last month where GLM/DeepSeek/Kimi/Qwen failed and Opus/Fable/GPT succeeded (or vice versa!), please share<p>Ill provide a template as ive also frequently seen posters complain about a lack of context:
- task (short and specific)
- cheap model tried & how it failed
- frontier model & did it actually succeed
- would frontier-1 have been fine in hindsight?