Top all-time · #23468
Roman Leventov
Personal blog · engineeringideas.substack.comaidataphilosophy
Roman Leventov writes Engineering Ideas, a personal blog at engineeringideas.substack.com about ai, data and philosophy. Since 2020, 3 different Hacker News readers have linked it 11 times. It is still writing: the last post was on 2026-10-28, and you can follow it by feed.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
The linked posts are book reviews. One is a review of a book co-authored by a research manager at OpenAI, which a commenter says covers how bottom-up innovation works there.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
Ethics, AI Safety, physics of intelligence and agency, organisation and community engineering, methodology.
What Hacker News says?
If you'd like some "objective" insights into how bottoms-up innovation at OpenAI works.. a research manager there coauthored this under-hyped book: https://engineeringideas.substack.com/p/review-of-why-greatn...
Comment linking /p/review-of-why-greatness-cannot-be
on “Reflections on OpenAI”Submitted The future of OLAP table storage is not Iceberg as a story · 2 points
HN discussionI'm working on Pocketdata - a personal, private AI data plane. The idea is to take boring components: PostgreSQL, Bifrost (LLM gateway), Open WebUI, LanceDB, Agentgateway (MCP and OpenAPI gateway) and deploy them in Fly.io. One Fly.io "org" per user. The closest equivalent is blaxel.ai, but it caters for AI SaaS startups, not individual customers. The combination of the fact that Fly secrets are visible only from wi…
Comment linking /p/tasklet-is-the-o1-moment-for-long
on “Ask HN: What Are You Working On? (Nov 2025)”Submitted Trace LLM workflows at your app's semantic level, not at the OpenAI API boundary as a story · 1 points
HN discussionBigQuery Storage Read API claims to support filters and simple projections pushed down to the storage: https://cloud.google.com/bigquery/docs/reference/storage . See also this recent paper: https://research.google/pubs/biglake-bigquerys-evolution-tow... I've also recently proposed a Table Read protocol that should be a "non-vendor-controlled" equivalent of BigQuery Storage APIs: https://engineeringideas.substack.com…
Comment linking /p/table-transfer-protocols-for-universal
on “Predicting the Future of Distributed Systems”Submitted Trace LLM workflows at your app's semantic level, not at the OpenAI API boundary as a story · 1 points
HN discussion> It seems like a web version of claude code + skills + marketplace, but with an encrypted database, and permissions that let you feel safe using yolo mode. I’m going to try it. I'm building infra for exactly this thing :) Here I posted about it today: https://engineeringideas.substack.com/p/tasklet-is-the-o1-mo... Architecture TLDR: In Fly.io, org-per user, manage keys in Fly secrets. A Postgres db with transparent…
Comment linking /p/tasklet-is-the-o1-moment-for-long
on “Let the little guys in: A context sharing runtime for the personalised web”Submitted Table transfer protocols: improved Arrow Flight and alternative to Iceberg as a story · 1 points
HN discussionI don't buy this "object storage + Iceberg is all you need for OLAP" hype. If the application has sustained query load, it makes sense to provision servers rather than go pure serverless. If there are already provisioned servers, it makes sense to cache data on them (either in their memory or SSDs) to avoid round-trips to object storage. This is the architecture of the latest breed of OLAP databases such as Databend…
Comment linking /p/the-future-of-olap-table-storage
on “Predicting the future of distributed systems”Submitted Table transfer protocols for universal access to OLAP databases as a story · 1 points
HN discussionSubmitted Should you become a full-stack programmer? as a story · 1 points
HN discussion