For example, you if you instruct a model to create decoder for some data type users will upload to your website. The intelligent model without notions will retrieve information about that data type and build a working decoder, but it might miss from context that users uploading to a website means untrusted input and thus won't even try to gather information about what it needs to be done to securely handle such uploaded data.

Or if you give it a task to translate text to a language it didn't encounter during training. You can provide it with grammar rules and a dictionary for information retrieval, but I guess it won't perform as well as inteligent model that already has some fundamental notions of that language and only needs a dictionary to expand its vocabulary.

Gpt-4.1 only knows a lot of patterns, but doesn't have reasoning intelligence that would help it properly use that knowledge. So, a small reasoning model can easily beat it in a lot of tasks. The question is how will, 14 months from now, new small reasoning models compare to current big reasoning models.

How much information needs to be embedded is not yet clear, but currently, bigger reasoning models are still better at complex tasks than small reasoning models. Either sweet spot of embedded notions is higher that what current small models have or information retrieval ability needs to improve.

Model doesn't know what it doesn't know.

"The react in react stands for reactivity, however it is not." [because] "Its entire state management is not reactive"

React is primarily an UI library, not full state management library. And its UI is reactive.

I think the mayor win for coding was reasoning. That's why such a small model can match GPT-4.1 in coding, but I suspect that GPT-4.1 still wins in general world knowledge due to bigger size.

This piqued my interest on how it does it and after briefly checking the project it seems it only has two features for automatic photo categorization. 1) it can group photos by date and 2) It has face detection and recognition that uses trained weights (so ML "intelligence").

Databasus seems to be taking somewhat similar approach to Barman, but (at this time) does not appear to use pg_receivewal, which makes it less efficient than Barman.

For PG v17+, Barman seems to be the most efficient backup solution based on PG native tools, that is able to do low-RPO or even zero-RPO (if configured as a synchronous receiver).

Did you encounter any issues or limitations?

  **Backup types**
  
  - **Logical** — Native dump of the database in its engine-specific binary format. Compressed and streamed directly to storage with no intermediate files
  - **Physical** — File-level copy of the entire database cluster. Faster backup and restore for large datasets compared to logical dumps
  - **Incremental** — Physical base backup combined with continuous WAL segment archiving. **Enables Point-in-time recovery (PITR)** — restore to any second between backups. Designed for disaster recovery and near-zero data loss requirements

https://github.com/databasus/databasus/issues/411

Better example might be statically typed languages. They were harder to use at first, but now with good type inference and features like generics, they are much more ergonomic than at first. The accessibility gap between static and dynamic languages has narrowed with time and maybe we can expect that user-friendliness of ownership will also improve like that.

AOT doesn't support generating new executable code at runtime (Reflection.Emit), like you can do in JIT mode.