Hacker News Reader

HNHacker News

Top New Best Ask Show Jobs

Comment by larrysalibra | Hacker News Reader

Parent Full thread

larrysalibra·

I tried Deepseek R1 via Kagi assistant and it was much better than claude or gpt.

I asked for suggestions for rust libraries for a certain task and the suggestions from Deepseek were better.

Results here: https://x.com/larrysalibra/status/1883016984021090796

View on HN

This is really poor test though, of course the most recently trained model knows the newest libraries or knows that a library was renamed.

Not disputing it's best at reasoning but you need a different test for that.

"recently trained" can't be an argument: those tools have to work with "current" data, otherwise they are useless.

That's a different part of the implementation details. If you were to break the system into mocroservices, the model is a binary blob with a mocroservices wrapper and accessing web search is another microservice entirely. You really don't want the entire web to be constantly compressed and re-released as a new model iteration, it's super inefficient.

Technically you’re correct, but from a product point of view one should be able to get answers beyond the cut-off date. The current product fails to realise that some queries like “who is the current president of the USA” are time based and may need a search rather than an excuse.

This only holds water if they are able to retrain frequently, which they haven't demonstrated yet. But if they are as efficient as they seem, then maybe.

That's interesting!

Reply on news.ycombinator.com