Work in progress: 181,232 of 181,233 sites checked so far, more every week · updated 2 Nov 2026Missing a blog? Tell us

Top all-time · #17183

P

Pawel Jozefiak

Personal blog · thoughts.jock.plaicareer

Pawel Jozefiak writes Digital Thoughts, a personal blog at thoughts.jock.pl about ai and career. Since 2026, 4 different Hacker News readers have linked it 42 times, most often “Kicked from AI Memory”. It is still writing: the last post was on 2026-10-30, and you can follow it by feed.

Visit the blog
42mentions?
4HN people?
2026–2026first – last linked?

Too few sampled comments (1) to say how often HN recommends it.?

Why HN links it

HN readers link Pawel Jozefiak's posts on personal experience with AI tools, such as cancelling Claude over token issues, declining quality and poor support, and ADHD and AI agents.

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.

Practical AI insights from an AI marketing lead who builds agents at night.

Most-linked posts?

  1. Kicked from AI Memory
    2 people · 2 mentions · first linked 2026-01-21
  2. My $600 Mac Mini Runs a 35B AI Model
    2 people · 2 mentions · first linked 2026-04-03
  3. Notes on running an AI agent with ADHD
    2 people · 2 mentions · first linked 2026-04-24

What Hacker News says?

  1. y42 · 2026-04-24Recommends
    I like your blog and I can totally relate to this article - it's like something I wanted to write about for a couple of weeks now. :D https://thoughts.jock.pl/p/adhd-ai-agent-personal-experience...

    Comment linking /p/adhd-ai-agent-personal-experience-2026

    on “I Cancelled Claude: Token Issues, Declining Quality, and Poor Support”
  2. Submitted Claude Code vs. Codex CLI vs. Aider vs. OpenCode vs. Pi vs. Cursor as a story · 4 points

    HN discussion
  3. Funny. I thought I was the only one. Then I found more people and now you wrote about that. Just this week I also wrote about Claude Opus 4.7 and how I came back to Codex after that: https://thoughts.jock.pl/p/opus-4-7-codex-comeback-2026

    Comment linking /p/opus-4-7-codex-comeback-2026

    on “I Cancelled Claude: Token Issues, Declining Quality, and Poor Support”
  4. Submitted I Maxed Out Fable 5 and Regretted It as a story · 3 points

    HN discussion
  5. Submitted My AI Agent Got Its Own Screen on My Desk. It Decides What I See as a story · 3 points

    HN discussion
  6. Submitted I Am an Anthropic Guy. GPT-6 Astra Made Me Resubscribe to Codex as a story · 3 points

    HN discussion
  7. Submitted I Cancelled Codex Two Months Ago. Opus 4.7 Brought Me Back as a story · 3 points

    HN discussion
  8. Submitted I built my first AI agent (and what I got wrong) as a story · 3 points

    HN discussion
  9. Submitted Claude Code's Source Got Leaked. Here's What's Worth Learning as a story · 2 points

    HN discussion
  10. Submitted Opus 5.5 Took Fable's Job. Haiku 5.5 Proved Me Wrong as a story · 2 points

    HN discussion
  11. Submitted I Ran 255 AI Agents to Make Three Comics. The Line Between Slop and Good Is as a story · 2 points

    HN discussion
  12. Submitted I Tried to Leave the Terminal Eight Times. The Ninth Stuck as a story · 2 points

    HN discussion
  13. Submitted Notes on running an AI agent with ADHD as a story · 2 points

    HN discussion
  14. Submitted My $600 Mac Mini Runs a 35B AI Model as a story · 2 points

    HN discussion
  15. Submitted Built my AI agent a custom dashboard. Then replaced it with Fizzy as a story · 2 points

    HN discussion
  16. Submitted Running Qwen 35B on 16GB Mac Mini via MMAP (17 tok/s) then swapping to Gemma 4 as a story · 2 points

    HN discussion
  17. Submitted Claude Code ranks 39th on terminal bench. The leaked source shows why as a story · 2 points

    HN discussion
  18. Submitted 88% of companies use AI. Only 13% trained anyone how as a story · 2 points

    HN discussion
  19. Submitted I ran 4 Claude Opus 4.6 agents in parallel – 1,400 lines of game code in 45 min as a story · 2 points

    HN discussion
  20. Submitted Running 50 AI agent threads at once made me the bottleneck as a story · 1 points

    HN discussion
  21. Submitted The Compounding Agent as a story · 1 points

    HN discussion
  22. Submitted I Cancelled Codex Two Months Ago. Opus 4.7 Brought Me Back as a story · 1 points

    HN discussion
  23. Submitted How to Almost Fry Your AI Agent (and Your Mac Mini) as a story · 1 points

    HN discussion
  24. Submitted AI Opinions: June 2026. Fable 5 Hands-On, Billing Split Countdown, OpenAI Banks as a story · 1 points

    HN discussion
  25. Submitted Five diverse AI agents vs. five clones for 14 nights: a constant tied both as a story · 1 points

    HN discussion
  26. Submitted How to break your AI agent as a story · 1 points

    HN discussion
  27. Submitted I trust my car more than my AI agent as a story · 1 points

    HN discussion
  28. Submitted AI coding agents read Git log as their first debugging step as a story · 1 points

    HN discussion
  29. Submitted Token Waste Management: I audited 9,667 Claude Code sessions for $19 as a story · 1 points

    HN discussion
  30. Submitted The AI Productivity Paradox: More Done and (Still) Zero Free Time as a story · 1 points

    HN discussion

Search all of HN for thoughts.jock.pl