Hacker News: kordikp

New comment by kordikp in "Show HN: P-book – an interactive book for kids about recommendation algorithms"

kordikp — Thu, 26 Mar 2026 10:11:57 +0000

I'm Pavel, co-founder of Recombee and an associate professor at CTU Prague. I built p-book because I kept running into a problem: most explainability work on recommender systems is aimed at researchers or regulators, not at the people actually affected by these systems every day — including kids.

The technical experiment here is whether personalizing how you explore a topic actually improves comprehension. Recombee drives the recommendations inside the book itself, so the book is eating its own dog food.

The thing I'm most unsure about: the four navigation modes (Missions, Browse, Read, Map) feel genuinely different to me as the builder, but I don't know if they feel different to a kid or a parent sitting with a kid. That's the feedback I most need.

Happy to talk about the technical architecture if anyone's curious — the spaced repetition layer on top of a live recommendation API is an unusual combination.

New comment by kordikp in "Show HN: P-book – an interactive book for kids about recommendation algorithms"

kordikp — Sun, 22 Mar 2026 22:45:40 +0000

let me know if you like it ... or if you can even imagine turning your edu content into p-book format ...

Show HN: P-book – an interactive book for kids about recommendation algorithms

kordikp — Sun, 22 Mar 2026 22:44:22 +0000

Hi HN — I’ve been building p-book, an open-source interactive book format that personalizes how a reader explores one topic.

The first p-book is for kids and teaches how recommendation systems work — including suggestions, privacy, filter bubbles, and fairness.

What I’m trying here is not only to personalize what comes next, but also how the same topic can be explored: through Missions, Browse, Read, or Map.

It’s still early, and I’d especially love feedback on three things:

- whether the navigation modes feel genuinely different, - whether the topic is understandable for kids, - where the experience feels confusing or too complex.

Comments URL: https://news.ycombinator.com/item?id=47483064

Points: 2

# Comments: 2

New comment by kordikp in "[dead]"

kordikp — Tue, 16 Jan 2024 16:39:17 +0000

1) Despite ongoing optimizations, the operation of proficient Language Model (LLM) models remains financially demanding. However, users are increasingly willing to invest in access to high-quality language models and the services built upon them. In 2024, we anticipate the rise of numerous Business-to-Consumer (B2C) companies offering subscription-based time-saving services that leverage LLMs, catering to a niche group of users and delivering substantial value. 2) While LLMs are beginning to function as reasoning engines, their principal weakness lies in their limited analytical reasoning capabilities. Recent research breakthroughs are poised to bridge this gap, aligning them more closely with human problem-solving processes. Expect LLMs to evolve, enabling them to plan, generalize acquired knowledge, and tackle novel, unfamiliar tasks across diverse domains. 3) These advancements will usher in a multitude of digital personas and assistants. No longer passive, these entities will proactively advocate for your interests in the digital realm. 4) Recognizing the current reluctance of humans to engage with machines using natural language, significant efforts will be invested in enhancing human-machine interfaces. The integration of conversational intelligence systems with recommender systems and personalized search systems will become more prevalent. This fusion aims to better incorporate human feedback into AI models, facilitating continuous improvement and personalization.

New comment by kordikp in "Introduction to Personalized Search"

kordikp — Tue, 24 Mar 2020 20:08:28 +0000

https://link.medium.com/opPIObpJ74

Introduction to Personalized Search

kordikp — Tue, 24 Mar 2020 20:07:44 +0000

Do you know learning to rank algorithms? You will learn it is better to combine search engines and recommender systems.

Comments URL: https://news.ycombinator.com/item?id=22678428

Points: 2

# Comments: 2

Business impact of personalized recommendation provided as a service

kordikp — Tue, 23 Aug 2016 08:49:24 +0000

Article URL: https://medium.com/recombee-blog/the-value-of-personalized-recommendations-for-your-business-6b2e81ce0a4d#.jzr14kyad

Comments URL: https://news.ycombinator.com/item?id=12342266

Points: 1

# Comments: 0