DeepSeek Coder: Let the Code Write Itself

Re:DeepSeek Coder: Let the Code Write Itself by chrisweekly on Wednesday January 31, 2024 @08:16PM (#39211794)

tangent: I often have a hard time disambiguating the ">" in comparisons like yours: (A) greater than (ie, Mixtral superior to DeepSeek, w/ Codellama in between) vs (B) arrow/sequence (ie, start w/ Mixtral, progress to Codellama, finally land on DeepSeek as the culmination).

I'd love to hear of a less ambiguous way to represent these.

[ Parent | on HN ]

Re:DeepSeek Coder: Let the Code Write Itself by mooreds on Wednesday January 31, 2024 @08:23PM (#39211839)

How does

Mixtral >= Codellama >= DeepSeek

Work for you?

[ Parent | on HN ]

Re:DeepSeek Coder: Let the Code Write Itself by illusive4080 on Wednesday January 31, 2024 @08:32PM (#39211878)

Sadly that implies that all 3 could be equal or very close to equal.

[ Parent | on HN ]

Re:DeepSeek Coder: Let the Code Write Itself by addandsubtract on Thursday February 01, 2024 @07:48AM (#39215387)

Which they can be, when you ask them for a console.log. It does, however, get rid of the ambiguity of case (B) that GP mentioned.

[ Parent | on HN ]

Re:DeepSeek Coder: Let the Code Write Itself by mcny on Wednesday January 31, 2024 @09:09PM (#39212069)

I personally use a -> b -> c for sequence, a > b >> c for nested hierarchy.

In this context, I read it as a is better than b which is better than c.

[ Parent | on HN ]