Skip to content
channel · books & ideas

Book Cube

Books, ideas and engineering culture — every week

A Telegram channel with original notes and reviews on books about technology, architecture, management, economics and personal growth. Long-form posts with practical takeaways, no fluff, no ads.

Open channel on TelegramRelated materials
Public archive

Book Cube posts

Bilingual versions of channel posts, with sources and a link to the original Telegram publication.

  1. #Personal

    UK Visa Approval and Plans for London

    My UK visa, my wife’s, and our youngest son’s have been approved; our middle son needs additional documents. The plan is to be in London in the second half of November.

  2. #AI4SDLC

    Agents Write Code. How Do We Know Development Has Become More Effective? | Code of Leadership (#AI4SDLC)

    An announcement of Code of Leadership with Vladimir Dolgov on developer productivity, the impact of AI agents, the cost of verification, and DevOptify metrics.

  3. #AI4SDLC

    Agent Skills and Open Knowledge Format (OKF): Skills, Knowledge, and Trust (#AI4SDLC)

    An announcement of a Research Insights Made Simple livestream with Maxim Smirnov about Agent Skills, Open Knowledge Format, skill evaluation, and trust in knowledge.

  4. #AI

    [1/2] Stanford CME295: How LLMs Are Trained (#AI)

    Part one of a breakdown of Stanford CME295’s third lecture: how pretraining, SFT, preference tuning, RL, and on-policy distillation provide different training signals.

  5. #AI

    3 AImigo S1E10 Materials: Agents with Payment Authority (#AI)

    Materials for the tenth 3 AImigo episode on shopping with AI agents: preferences, permissions, order approval, merchant incentives, and responsibility for mistakes.

  6. #AI4SDLC

    Demystifying evals for AI agents: Evaluation Structure and Margin Notes (#AI4SDLC)

    The structure of evals in Anthropic’s article, with my notes on TDD, expectations, the DOM, independent trials, and trajectory evaluation.

  7. #Leadership

    Code of Leadership #85 Materials: FDE with Pavel Golubev (#Leadership)

    Pavel Golubev on delivering AI for customers: feasibility checks, business commitments, access permissions, and FDE teamwork.

  8. #AI4SDLC

    Agent evals: how to tell whether an agent succeeded / Research Insights Made Simple #42 (#AI4SDLC)

    Research Insights Made Simple No. 42: checking agent outcomes, choosing graders, and distinguishing a better system from a higher score.

  9. #Humor

    The How to be British Collection Two (#Humor)

    Martyn Ford and Peter Legon’s second collection: British humor about food, railways, compliments, and self-deprecation.

  10. #Personal

    Research Insights #41 live: the anatomy of an agent

    Research Insights Made Simple No. 41 is starting, covering the seven responsibilities of a harness and the Harness Engineering preprint.

  11. #AI4SDLC

    Jediah Katz on the harness: what remains after a new model (#AI4SDLC)

    Jediah Katz’s talk on the co-evolution of models and harnesses: tracking temporary shims, testing their removal, and preserving authorization boundaries.

  12. #AI4SDLC

    Research Insights #39 materials: Scion and development with agents (#AI4SDLC)

    Materials for Research Insights Made Simple No. 39, October 15, 2026: Scion, server-side source control, the engineers’ role, and the limits of validation.

  13. #AI4SDLC

    Harness Engineering: the anatomy of coding agents (#AI4SDLC)

    A source-code study of 11 coding agents: seven harness subsystems, engineering trade-offs, and questions about the authors’ conclusions.

  14. #Personal

    Live: how AI is changing work at Anthropic

    An invitation to a live discussion of an Anthropic article on how using AI changes work inside the company.

  15. #DevEx

    Anthropic: What Remains for Humans in a Company of Agents? Research Insights Made Simple #40 (#DevEx)

    An announcement of a discussion of Anthropic’s research: outcomes, human attention, learning, and incentives.

  16. #AI4SDLC

    Research Insights №38: What a Harness Contributes — Materials (#AI4SDLC)

    Episode materials on experimentally evaluating agent planning, tools, and context management.

  17. #AI

    How Work Is Changing Inside Anthropic (#AI)

    Research on hiring, productivity, meta-work, and employee incentives, with the author’s PDF annotations.

  18. #AI4SDLC

    Gautam Korlam: CI for a Stream of Agent Changes (#AI4SDLC)

    CI capacity, repeated checks, independent review, and retaining the evidence behind merge decisions.

  19. #SelfDevelopment

    Understand Before Deciding: How I Learn New Topics with AI (#SelfDevelopment)

    A pmclub upskill week talk announcement about using AI to work with sources and decision criteria.

  20. #AI4SDLC

    Giga Conf: What Should Happen to a Harness After a New Model? (#AI4SDLC)

    A talk announcement about agent harness evolution and reassessing accumulated instructions.

  21. #AI4SDLC

    Stack Overflow 2026 (#AI4SDLC)

    An author’s reading of the Stack Overflow survey: trust in AI, tool popularity, and work context.

  22. #DevTools

    Scion: Anthropic’s Git Replacement for Agent Development (#DevTools)

    Research Insights №39 announcement on Scion’s architecture and guarantees between merge and deployment.

  23. #AI

    3 AImigo S1E10: Agents with Payment Rights — Would We Trust AI with Our Money? (#AI)

    A discussion announcement about shopping, payment protocols, budgets, and the limits of agent autonomy.

  24. #Engineering

    The Pavel Golubev Livestream Is Starting

    A short invitation to join the livestream as it starts.

  25. #AI4SDLC

    Scion: When Agents Hit Development Infrastructure Limits (#AI4SDLC)

    Scion’s architecture, migration from Git, server-side operations, and changing CI guarantees in Anthropic’s report.

  26. #AI

    Stanford CME295, Lecture 2: What Changed Inside the Transformer (#AI)

    MoE, RoPE, GQA, inference reproducibility, and guided decoding in Stanford’s second course lecture.

  27. #Engineering

    Pavel Golubev FDE Livestream Rescheduled

    A date correction for the conversation with Pavel Golubev about forward deployed engineers.

  28. #Data

    AI and Data Platforms: Research Insights Made Simple №37 Materials (#Data)

    A conversation with Nikolay Golov about data platform approaches, zero-ETL, and engineering trade-offs.

  29. #AI4SDLC

    3 AImigo S1E9: Boundaries of Autonomy — Episode Materials (#AI4SDLC)

    Materials from a discussion of agent delegation, approvals, and the full cost of an accepted task.

  30. #AI4SDLC

    Live: What Does an Agent Harness Contribute?

    An invitation to discuss a study of planning, tools, and context management for coding agents.

  31. #AI4SDLC

    Factory: Engineers Become Managers — Who Can Still Check Their Agents’ Work? (#AI4SDLC)

    Davis Palmie’s talk on software factories, environment readiness, and engineering judgment when managing agents.

  32. #Books

    Harness Engineering: Familiar Ideas in One Book (#Books)

    Nicole Koenigstein’s first two chapters: familiar ideas, task state, and questions about when harness components help.

  33. #AI4SDLC

    Research Insights #36: Harnesses for Long-running Development (#AI4SDLC)

    Episode materials on planners, generators, evaluators, and the limits of autonomous application development.

  34. #Data

    AI and Data Platforms: Live with Nikolay Golov

    An invitation to a conversation with Nikolay Golov about adding AI to data platforms.

  35. #AI4SDLC

    Meet Pi: The Minimalist, Self-Modifying Coding Agent (#AI4SDLC)

    Mario Zechner and Armin Ronacher on a small agent core, extensions, and control over the workflow.

  36. #AI4SDLC

    Research Insights #35 materials: an environment for agents (#AI4SDLC)

    Episode materials on OpenAI harness engineering: project knowledge, tools, architectural checks, and technical debt.

  37. #ForKids

    Pasha and Dad (#ForKids)

    A book about Pasha and his dad: family sketches, reading with Kirill, and a personal postscript.

  38. #Management

    FDE: who is responsible for making AI work for the customer? (#Management)

    The October 14 Code of Leadership livestream with Pavel Golubev: AI implementation, project boundaries, and FDE management.

  39. #AI4SDLC

    Harness design for coding agents: what does the harness contribute? (#AI4SDLC)

    An experimental comparison of planning, tools, and context management in coding agents.

  40. #Data

    AI and the data platform: connecting AI to all an organization’s data (#Data)

    The October 12 livestream with Nikolay Golov on operational data, analytics, Lakehouses, and agents.

  41. #Books

    The Forward Deployed Engineer — Paden Gayle (#Books)

    The first two chapters on FDE responsibility, stakeholder alignment, and the economics of implementation.

  42. #AI

    YC Paper Club: what comes after LLM + GPU? (#AI)

    Optical computing, neuromorphic chips, and living neurons: research bets and demonstration limits.

  43. #Books

    The Man from the Future: The Visionary Life of John von Neumann (#Books)

    Reflections on John von Neumann’s biography: computing, game theory, physics, and self-reproducing machines.

  44. #AI4SDLC

    Research Insights #34 materials: long-running agents and handoffs (#AI4SDLC)

    Episode materials on session handoffs, completion criteria, and evaluating a harness.

  45. #AI4SDLC

    Research Insights livestream: long-running application development

    An invitation to a livestream on Anthropic’s March article about harnesses for long-running application development.

  46. #Personal

    A charity auction: breakfast together

    A breakfast meeting auction on Tolk in support of the Nit Dobra charity.

  47. #Management

    Code of Leadership #84 materials: does a developer become a manager in the AI era? (#Management)

    A conversation with Andrey Dmitriev about useful tasks, responsibility, and the agent lifecycle.

  48. #AI4SDLC

    Harness design for long-running autonomous application development (#AI4SDLC)

    Anthropic’s Planner, Generator, and Evaluator: acceptance, cost, and simplification as models improve.

  49. #AI4SDLC

    Research Insights #33 materials: SWE-agent (#AI4SDLC)

    Episode materials on how tools, interfaces, and feedback change an agent’s results.

  50. #AI4SDLC

    Justin Reock: code is easier to change, harder to release confidently (#AI4SDLC)

    DX observations on maintainability, change confidence, and PR growth; what to verify after adopting AI.

Continue in the full archive
What's inside · manual May 2026 snapshot
4,500+
posts
30+
topic tags
5 years
of regular posting
1
author · no editorial

Why subscribe

  • 01Get notes on key books with practical takeaways and links to the originals
  • 02See how the same idea echoes across engineering, management and economics
  • 03Be the first to hear about new talks, articles and podcast episodes
  • 04Keep a ready-to-use list of recommendations: 'what should I read on X'

How the channel works

Deep reviews

Reviews of books, research, and talks: key ideas, context, practical conclusions, and a personal perspective.

Topic tags

Posts are tagged: #Engineering, #Management, #AI, #Economics, #Software, #Leadership and more — easy to find everything on a topic.

Announcements & threads

New talks, tellmeabout.tech articles and Code of Leadership episodes are announced here too. One feed for everything.

Channel sections

Real tags from recent months — frequency reflects the channel's focus: tech, AI and management at the center, but not only.

01#Engineering
02#AI
03#Management
04#Software
05#Processes
06#Agents
07#Leadership
08#SystemDesign
09#Productivity
10#Architecture
11#Whitepaper
12#DistributedSystems
13#Database
14#Future
15#Economics
16#PopScience
17#Strategy
18#Math

Post genres

What you'll actually see in the feed.

01book review

Engineering book review

From 'Designing Data-Intensive Applications' to fresh AI engineering whitepapers — with a take on what's useful and for whom.

02talk announcement

Talk announcement

When a new conference talk comes out — recording, slides, references and a short recap land here.

03engineering note

Practice note

Short observations and ideas: how we build architecture, how culture changes, what works in large orgs.

04research

Whitepapers & research

Reviews of DORA, DevEx, AI4SDLC and other studies — with focus on what's actually applicable.

Who it's for

  • Engineers who want depth, not summaries of summaries
  • Team leads and managers looking for books in their growth zone
  • CTOs and founders holding both the tech and the business context
  • Anyone who prefers long, thoughtful posts over a news feed

Subscribe

One post every few days, zero ads, thousands of readers as of May 2026 — join if you learn through books.

Open Book Cube