Top all-time · #17183
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.
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?
- Kicked from AI Memory2 people · 2 mentions · first linked 2026-01-21
- My $600 Mac Mini Runs a 35B AI Model2 people · 2 mentions · first linked 2026-04-03
- Notes on running an AI agent with ADHD2 people · 2 mentions · first linked 2026-04-24
What Hacker News says?
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”Submitted Claude Code vs. Codex CLI vs. Aider vs. OpenCode vs. Pi vs. Cursor as a story · 4 points
HN discussionFunny. 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”Submitted I Maxed Out Fable 5 and Regretted It as a story · 3 points
HN discussionSubmitted My AI Agent Got Its Own Screen on My Desk. It Decides What I See as a story · 3 points
HN discussionSubmitted I Am an Anthropic Guy. GPT-6 Astra Made Me Resubscribe to Codex as a story · 3 points
HN discussionSubmitted I Cancelled Codex Two Months Ago. Opus 4.7 Brought Me Back as a story · 3 points
HN discussionSubmitted I built my first AI agent (and what I got wrong) as a story · 3 points
HN discussionSubmitted Claude Code's Source Got Leaked. Here's What's Worth Learning as a story · 2 points
HN discussionSubmitted Opus 5.5 Took Fable's Job. Haiku 5.5 Proved Me Wrong as a story · 2 points
HN discussionSubmitted I Ran 255 AI Agents to Make Three Comics. The Line Between Slop and Good Is as a story · 2 points
HN discussionSubmitted I Tried to Leave the Terminal Eight Times. The Ninth Stuck as a story · 2 points
HN discussionSubmitted Notes on running an AI agent with ADHD as a story · 2 points
HN discussionSubmitted My $600 Mac Mini Runs a 35B AI Model as a story · 2 points
HN discussionSubmitted Built my AI agent a custom dashboard. Then replaced it with Fizzy as a story · 2 points
HN discussionSubmitted Running Qwen 35B on 16GB Mac Mini via MMAP (17 tok/s) then swapping to Gemma 4 as a story · 2 points
HN discussionSubmitted Claude Code ranks 39th on terminal bench. The leaked source shows why as a story · 2 points
HN discussionSubmitted 88% of companies use AI. Only 13% trained anyone how as a story · 2 points
HN discussionSubmitted 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 discussionSubmitted Running 50 AI agent threads at once made me the bottleneck as a story · 1 points
HN discussionSubmitted The Compounding Agent as a story · 1 points
HN discussionSubmitted I Cancelled Codex Two Months Ago. Opus 4.7 Brought Me Back as a story · 1 points
HN discussionSubmitted How to Almost Fry Your AI Agent (and Your Mac Mini) as a story · 1 points
HN discussionSubmitted AI Opinions: June 2026. Fable 5 Hands-On, Billing Split Countdown, OpenAI Banks as a story · 1 points
HN discussionSubmitted Five diverse AI agents vs. five clones for 14 nights: a constant tied both as a story · 1 points
HN discussionSubmitted How to break your AI agent as a story · 1 points
HN discussionSubmitted I trust my car more than my AI agent as a story · 1 points
HN discussionSubmitted AI coding agents read Git log as their first debugging step as a story · 1 points
HN discussionSubmitted Token Waste Management: I audited 9,667 Claude Code sessions for $19 as a story · 1 points
HN discussionSubmitted The AI Productivity Paradox: More Done and (Still) Zero Free Time as a story · 1 points
HN discussion