Hacker News: pajtai

New comment by pajtai in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

pajtai — Sat, 04 Apr 2026 14:49:52 +0000

Where is the official announcement on https://www.anthropic.com/ or https://claude.com/? I haven't gotten an email.

Claude Auto Memory

pajtai — Mon, 02 Mar 2026 19:25:41 +0000

Article URL: https://code.claude.com/docs/en/memory

Comments URL: https://news.ycombinator.com/item?id=47222840

Points: 1

# Comments: 0

New comment by pajtai in "Cognitive Debt: When Velocity Exceeds Comprehension"

pajtai — Sat, 28 Feb 2026 16:14:51 +0000

The whole premise of the post, that coders remember what and why they wrote things from 6 months ago, is flawed.

We've always had the problem that understanding while writing code is easier than understanding code you've written. This is why, in the pre-AI era, Joel Spolsky wrote: "It's harder to read code than to write it."

Claude.md isn't always read and followed

pajtai — Thu, 19 Feb 2026 02:44:36 +0000

I thought Claude was more reliable. Guess you can't count on CLAUDE.md files always being read and followed.

Context was only at 13% used.

The transcript:

---

pajtai> Why didn't you rename the completed plan per ~/.claude/CLAUDE.md?

You're right, I missed that. Let me find and rename the plan file now.

Read 1 file (ctrl+o to expand)

I need to identify which plan file corresponds to the [PROJECT] fix. Let me check the likely candidates.

Searched for 1 pattern, read 1 file (ctrl+o to expand)

Bash(mv ~/.claude/plans/elegant-leaping-spring.md ~/.claude/plans/2026-02-18-[PROJECT].md) ⎿ Done

Done. Renamed elegant-leaping-spring.md → 2026-02-18-[PROJECT].md.

  I'll make a note to remember this step going forward.

 Wrote 1 memory (ctrl+o to expand)

pajtai> Where did you put the note?

I put it in the project-specific memory file at /Users/pajtai/.claude/projects/-Users-pajtai-[PROJECT]/memory/MEMORY.md.

  But that's the wrong place — the reminder applies to all projects, not just this one.
  It should go in the global MEMORY.md at /Users/pajtai/.claude/projects/-Users-pajtai-[PROJECT]/memory/MEMORY.md...
  wait, let me check where the global one actually is.

 Searched for 1 pattern (ctrl+o to expand)

 The only MEMORY.md that exists is the project-specific one at
  /Users/pajtai/.claude/projects/-Users-pajtai-[PROJECT]/memory/MEMORY.md.
  That's where I put it.

  However, since the plan-renaming rule is already in your global CLAUDE.md, the note is redundant. Would you like me to remove it?

Comments URL: https://news.ycombinator.com/item?id=47069255

Points: 3

# Comments: 1

New comment by pajtai in "Evaluating AGENTS.md: are they helpful for coding agents?"

pajtai — Mon, 16 Feb 2026 18:26:37 +0000

I'd be interested to see results with Opus 4.6 or 4.5

Also, I bet the quality of these docs vary widely across both human and AI generated ones. Good Agents.md files should have progressive disclosure so only the items required by the task are pulled in (e.g. for DB schema related topics, see such and such a file).

Then there's the choice of pulling things into Agents.md vs skills which the article doesn't explore.

I do feel for the authors, since the article already feels old. The models and tooling around them are changing very quickly.

Explaining how a touchscreen works with a sausage (2025) [video]

pajtai — Fri, 06 Feb 2026 07:02:11 +0000

Article URL: https://www.bbc.com/reel/video/p0lv0hqk/explaining-how-a-touchscreen-works-with-a-sausage

Comments URL: https://news.ycombinator.com/item?id=46909963

Points: 1

# Comments: 0

New comment by pajtai in "Carnegie Mellon Unversity Computer Club FTP Server"

pajtai — Tue, 03 Feb 2026 04:23:51 +0000

Some of the http://128.237.157.9/pub/core-mp3s/ files are an interesting record of the past.

LLMs Outperform Data Scientists (2025)

pajtai — Tue, 20 Jan 2026 02:49:29 +0000

Article URL: https://presentofcoding.substack.com/p/llms-already-outperform-data-scientists

Comments URL: https://news.ycombinator.com/item?id=46687337

Points: 1

# Comments: 0

New comment by pajtai in "FLUX.2 [Klein]: Towards Interactive Visual Intelligence"

pajtai — Sat, 17 Jan 2026 04:55:35 +0000

It cannot create an image of a pogo stick.

I was trying to get it to create an image of a tiger jumping on a pogo stick, which is way beyond its capabilities, but it cannot create an image of a pogo stick in isolation.

New comment by pajtai in "Patterns.dev"

pajtai — Thu, 11 Dec 2025 07:38:48 +0000

Looks great. Wish it had a table of contents. Am I missing it?

Turning Gemini CLI into a Multi-Agent System with Just Prompts

pajtai — Sat, 04 Oct 2025 02:55:11 +0000

Article URL: https://aipositive.substack.com/p/how-i-turned-gemini-cli-into-a-multi

Comments URL: https://news.ycombinator.com/item?id=45470134

Points: 3

# Comments: 0

An Automated Lego Car Factory [video]

pajtai — Thu, 28 Aug 2025 04:35:32 +0000

Article URL: https://www.youtube.com/watch?v=XTyzfUEb9_s

Comments URL: https://news.ycombinator.com/item?id=45048408

Points: 5

# Comments: 0

AI and programming: the beginning of a new era

pajtai — Sun, 11 May 2025 05:11:51 +0000

Article URL: https://www.oreilly.com/radar/ai-and-programming-the-beginning-of-a-new-era/

Comments URL: https://news.ycombinator.com/item?id=43951589

Points: 3

# Comments: 0

Trachtenberg System of Mental Calculation

pajtai — Sat, 21 Sep 2024 15:32:06 +0000

Article URL: https://en.wikipedia.org/wiki/Trachtenberg_system

Comments URL: https://news.ycombinator.com/item?id=41610622

Points: 20

# Comments: 2

A search engine by and for the federal government

pajtai — Fri, 19 Jul 2024 17:43:44 +0000

Article URL: https://search.gov/

Comments URL: https://news.ycombinator.com/item?id=41009021

Points: 235

# Comments: 62

Real Tennis

pajtai — Tue, 11 Jun 2024 20:32:35 +0000

Article URL: https://en.wikipedia.org/wiki/Real_tennis

Comments URL: https://news.ycombinator.com/item?id=40651142

Points: 3

# Comments: 0

New comment by pajtai in "Rebuilding memchess.com from its archive"

pajtai — Mon, 11 Mar 2024 00:50:33 +0000

This is awesome. If you want help from other contributors, you'll probably find it easier to collaborate if you move memchess into its own repo (vs storing it in the grondilu.github.io repo). Each repo can have a dedicated GH Pages.

Really cool!

48 Blindfold boards – The tale behind the record (2017)

pajtai — Mon, 08 Jan 2024 04:03:14 +0000

Article URL: https://en.chessbase.com/post/48-blindfold-boards-the-tale-behind-the-record

Hacker News: pajtai

New comment by pajtai in "Tell HN: Anthropic no longer allowing Claude Code subscriptions to use OpenClaw"

Claude Auto Memory

New comment by pajtai in "Cognitive Debt: When Velocity Exceeds Comprehension"

Claude.md isn't always read and followed

New comment by pajtai in "Evaluating AGENTS.md: are they helpful for coding agents?"

Explaining how a touchscreen works with a sausage (2025) [video]

New comment by pajtai in "Carnegie Mellon Unversity Computer Club FTP Server"

LLMs Outperform Data Scientists (2025)

New comment by pajtai in "FLUX.2 [Klein]: Towards Interactive Visual Intelligence"

New comment by pajtai in "Patterns.dev"

Turning Gemini CLI into a Multi-Agent System with Just Prompts

An Automated Lego Car Factory [video]

AI and programming: the beginning of a new era

Trachtenberg System of Mental Calculation

A search engine by and for the federal government

Real Tennis

New comment by pajtai in "Rebuilding memchess.com from its archive"

48 Blindfold boards – The tale behind the record (2017)

Famous Trials

Random JSXGraph Example