{"channel":"cities","content":"The second \"LLM coding app\" tried was Windsurf.\r\n\r\nAnd, while it is not a *knockout* decision, ZenCoder has clearly won on points.\r\n\r\n----\r\n\r\nThe biggest advantage of Windsurf over ZenCoder is the usage dashboard. It is much clearer how many queries I have run, and what they have cost.\r\n\r\n <<< Just because I'm not *paying* during a two-week trial doesn't mean that the queries didn't *cost* something to someone else. >>>\r\n\r\n----\r\n\r\nThe coding skill of Windsurf was substantially worse.\r\n\r\nWas this because it defaulted to their own (free) << SWE-1-Lite >> model, rather than a more effective one? Maybe.\r\n\r\n <<< Right now, *not* giving your users a choice of 7 different models, is a feature. >>>\r\n\r\n----\r\n\r\nBoth have a version of the \"accept changes\" diff-review tool. Windsurf lets you accept part of the change. But, in practice, this is more of an *inconvenience* than a convenience. When the change is something like \"update the imports\", there are 8 separate things to accept.\r\n\r\n----\r\n\r\n*Vibecoding* is still slow enough that I can operate two sessions simultaneously. So, perhaps, having Windsurf and Zencoder both running can double my productivity.\r\n\r\n----\r\n\r\nZencoder's \"advanced workflows\" do seem to have solved some of the basic problems. Like << figure out which file the user is referring to >>. The solution is not \"read everything\", but \"use a subcommand to << grep >> the file titles\".\r\n\r\n----\r\n\r\nUltimately, for an experienced coder, the key feature of these tools is to fail in a way that is easy to << detect and correct >>.","created_at":"2025-05-24T14:58:55.666729","id":503,"llm_annotations":{},"parent_id":501,"processed_content":"

The second \"LLM coding app\" tried was Windsurf.\r

\n

And, while it is not a knockout decision, ZenCoder has clearly won on points.\r

\n
\n

The biggest advantage of Windsurf over ZenCoder is the usage dashboard. It is much clearer how many queries I have run, and what they have cost.\r

\n

Just because I'm not paying during a two-week trial doesn't mean that the queries didn't cost something to someone else.

\n
\n

The coding skill of Windsurf was substantially worse.\r

\n

Was this because it defaulted to their own (free) SWE-1-Lite model, rather than a more effective one? Maybe.\r

\n

Right now, not giving your users a choice of 7 different models, is a feature.

\n
\n

Both have a version of the \"accept changes\" diff-review tool. Windsurf lets you accept part of the change. But, in practice, this is more of an inconvenience than a convenience. When the change is something like \"update the imports\", there are 8 separate things to accept.\r

\n
\n

Vibecoding is still slow enough that I can operate two sessions simultaneously. So, perhaps, having Windsurf and Zencoder both running can double my productivity.\r

\n
\n

Zencoder's \"advanced workflows\" do seem to have solved some of the basic problems. Like figure out which file the user is referring to. The solution is not \"read everything\", but \"use a subcommand to grep the file titles\".\r

\n
\n

Ultimately, for an experienced coder, the key feature of these tools is to fail in a way that is easy to detect and correct.

","quotes":[],"subject":"watertown (part 2)"}