
AI as a prompter
DeepResearch sucks or your promt sucks? (part 2)
DeepResearch sucks or your promt sucks? (part 2)
How I wrote a technical report in just 3 hours with no experience.
DeepResearch sucks or your promt sucks?
Do LLMs even care about comments in code or are they just skipping it?
My geniune thoughts about a research career and some stories for those views.
Exploring the difference between Representative and Generative LLMs.
In-depth analysis of transformer.
Some stories behind my first AI competition in my university.
Take a look how VLMs learn and the effectiveness of their learning process.
Is the prompting bias in LLM benchmarks actually a problem?