Coding with LLMs in the summer of 2025 (an update)

Re:Coding with LLMs in the summer of 2025 (an update) by smallerize on Sunday July 20, 2025 @02:24PM (#44627852)

I don't have to actually run it locally to remove lock-in. Several cloud providers offer full DeepSeek R1 or Kimi K2 for $2-3/million output tokens.

[ Parent | on HN ]

Re:Coding with LLMs in the summer of 2025 (an update) by ketzo on Sunday July 20, 2025 @05:40PM (#44629572)

In what ways is that better for you than using eg Claude? Aren’t you then just “locked in” to having a cloud provider which offers those models cheaply?

[ Parent | on HN ]

Re:Coding with LLMs in the summer of 2025 (an update) by viraptor on Sunday July 20, 2025 @05:58PM (#44629709)

Any provider can run Kimi (including yourself if you would get enough use out of it), but only one can run Claude.

[ Parent | on HN ]

Re:Coding with LLMs in the summer of 2025 (an update) by hhh on Monday July 21, 2025 @06:55AM (#44633739)

Two can run Claude, AWS and Anthropic. Claude rollout on AWS is pretty good, but they do some weird stuff in estimating your quota usage thru your max_tokens parameter.

I trust AWS, but we also pay big bucks to them and have a reason to trust them.

[ Parent | on HN ]

Re:Coding with LLMs in the summer of 2025 (an update) by viraptor on Monday July 21, 2025 @07:32PM (#44641572)

In a way... But it's still just because Anthropic lets them. Things can change at any point.

[ Parent | on HN ]