Hacker News: mceachen

New comment by mceachen in "Don't let anyone take away your big box of cables"

mceachen — Fri, 11 Sep 2026 23:43:16 +0000

I should have clarified: I use a 1" piece of maybe 5mm wide good quality 3M tape that wraps over itself.

This follows (at least my local) electrical code--it's quite robust. I have 40 year old electrical conduit that has tape applied like this and there's no movement, no fraying, no stickiness.

New comment by mceachen in "Don't let anyone take away your big box of cables"

mceachen — Fri, 11 Sep 2026 02:17:37 +0000

I bought a cheap pack of 5 colors of 3m electrical tape. Each cable gets one or two pieces of tape:

Data:

White if usb2

Blue if it supports USB 3 data (because 5Gbps USB 3 ports are mostly blue)

Green if TB/USB4/40Gbps

Power:

None if low/no Power Delivery

Yellow for 45W PD

Red for 65W+ PD

New comment by mceachen in "Ask HN: How do you manage skills files?"

mceachen — Mon, 07 Sep 2026 13:54:07 +0000

Have your agent make a plugin marketplace -- mine is here (feel free to crib): https://github.com/photostructure/coding-skills

Be sure to increment unofficial plugin versions when you make edits: codex's auto-update works reasonably well, claude not so much, but when asked, both can fix their own config.

And like others have said, imho the skills that are incanted as macros are much more reliably useful. I use my technical project plan skill suite in 90% of my sessions via direct reference, and the stage -> cross-model second-opinion review is how I land all my commits.

New comment by mceachen in "De-Brainrot Vacations"

mceachen — Mon, 07 Sep 2026 13:43:36 +0000

The neurologists and neurotherapists for a family member who is a stroke survivor have been pretty consistent in saying that cardiovascular exercise and regular social engagement seem to be the most promising activities to stem cognitive decline.

New comment by mceachen in "Portal by Spotify cut my Claude Code token usage by 90%"

mceachen — Sat, 05 Sep 2026 15:21:38 +0000

"Use subagents as applicable. Use sonnet/luna for finding relevant code references"

This should have been the entirety of TFA.

New comment by mceachen in "GPT-6 Astra on OpenRouter"

mceachen — Sat, 05 Sep 2026 02:53:00 +0000

Aldus Freehand 1.0 was released in 1988. Adobe Illustrator was first released in 1987.

New comment by mceachen in "Claude Fable 5.1 and Claude Mythos 5.1"

mceachen — Fri, 04 Sep 2026 20:36:46 +0000

Sol doesn't support larger contexts, and the prior fable context was ~300k, way under where you see substantive regression

New comment by mceachen in "Claude Fable 5.1 and Claude Mythos 5.1"

mceachen — Tue, 01 Sep 2026 19:42:26 +0000

I had two sessions this morning that prior fable and sol sessions were stuck on, where iterations just resulted in _different_ bugs. (One kind of tricky fe layout problem, the other was a backend refactoring that was complicated by trying to aggregate a couple prior sessions that crashed).

I summarized each into new fable 5.1 sessions, and both seem to have arrived at reasonable solutions that only need a few nits revised before they are commit worthy.

New comment by mceachen in "Judge rules Trump administration’s blacklisting of Anthropic was illegal"

mceachen — Fri, 28 Aug 2026 03:45:03 +0000

age of xitter won't make you feel better.

New comment by mceachen in "Xiaomi: New CPU matches Apple cores single threaded, much faster multithreaded"

mceachen — Mon, 24 Aug 2026 16:10:49 +0000

The general workload performance (browsing, text editing) is comparable for neo and m* MacBooks afaict.

Ghastly was macOS on an Intel MacBook Air.

New comment by mceachen in "Small, native web tricks worth remembering"

mceachen — Fri, 21 Aug 2026 14:00:32 +0000

"... that matters" is the new emdash

New comment by mceachen in "Degraded performance for multiple models"

mceachen — Tue, 18 Aug 2026 16:47:14 +0000

Model competence is an interaction of weights, system prompt, and harness.

New comment by mceachen in "Stripe 2.9% vs. Adyen 0.6% vs. Braintree 2.59%: 2026 Fees"

mceachen — Sun, 16 Aug 2026 13:26:19 +0000

I suspect most CFOs/CTOs fear the risk of undertaking a rewrite of your payment processor or merchant of record layers (which can be tricky to fully test even with sandbox/test environments) more than the percentage discount and opportunity cost of not shipping more features.

New comment by mceachen in "Hyperspace"

mceachen — Tue, 11 Aug 2026 14:11:31 +0000

If you're referencing Fetch for mac (pre macos) or Transit by Panic (later renamed to Transmit), I was a fan (and I've been a terminal fanboy since the early 80s). Both of them started as FTP wrappers, and both provided convenience the cli lacked.

New comment by mceachen in "Message your other Claude Code sessions"

mceachen — Sun, 09 Aug 2026 13:35:38 +0000

Claude is quite good at searching both its own and codex session transcripts, and if asked, can spawn tmux/konsole/whatever to resume those sessions to be interactive if needed.

My system prompt adds TPPs and TLDRs for task/feature planning, and shared memories/documentation management. I find them invaluable.

https://photostructure.com/coding/claude-code-tpp/

New comment by mceachen in "The new rules of context engineering for Claude 5 generation models"

mceachen — Sun, 26 Jul 2026 03:46:36 +0000

"Wdyt" is a prompt I've used for ages (originally to get around Claude "ultrathink"-related parsing bugs), and it's helpful alongside replan

https://photostructure.com/coding/claude-code-replan/

New comment by mceachen in "Qwen 3.8"

mceachen — Sun, 19 Jul 2026 16:09:51 +0000

Please don't conflate a volunteer effort with no expected economic gain with a very well funded company (or fleet of companies).

With the CCP's highly successful track record with subsuming other markets, Occam's razor applies to why they're doing this.

New comment by mceachen in "How to stop Claude from saying load-bearing"

mceachen — Tue, 14 Jul 2026 15:57:20 +0000

All of those phrases I've heard actively used even a decade (or two) ago. (I actually had to read your comment twice because I thought you were saying always, not never!)

"Critical path" and "long pole in tent" didn't make it into the model training data, but those were certainly also in play incessantly.

But they're all reasonably useful descriptions for common things, so I'm not surprised.

New comment by mceachen in "Proof of care in the age of AI"

mceachen — Tue, 14 Jul 2026 15:50:51 +0000

I don't know if it's universal, but your non-dominant hand may form reflected letters delightfully easily if you air-write simultaneously with your dominant hand.

New comment by mceachen in "Help I accidentally a wigglegram"

mceachen — Mon, 22 Jun 2026 14:23:14 +0000

If you're really wanting to do perceptual hash based deduplication, use multiple, heterogeneous hash algorithms (phash, dct hash, mean hash, ...) as it is likely that a given hash algo will happily lossily match with very very different images--but if all hashes match, you're much less likely to have false positives.

I wrote up what I do here: https://photostructure.com/guide/what-do-you-mean-by-dedupli...