Hacker News: FrankRay78

New comment by FrankRay78 in "Fast Software, the Best Software (2019)"

FrankRay78 — Sun, 05 Jul 2026 10:28:59 +0000

Slop or not, I enjoyed reading it. And could relate.

New comment by FrankRay78 in "Time to talk about my writerdeck"

FrankRay78 — Sat, 23 May 2026 20:42:21 +0000

Anybody else wonder how the screenshots were taken?

New comment by FrankRay78 in "AI is making me dumb"

FrankRay78 — Thu, 14 May 2026 21:42:43 +0000

I’m still the same smart person when using AI. What the author probably means is their memory of syntax is fading. Bothered?

Ask HN: How to separate agent harness from code repo?

FrankRay78 — Tue, 12 May 2026 19:52:53 +0000

I’m interested in any approaches or ideas for how to keep agent harness and code separate, like ideally separate repos.

Spec driven development is going really well for me, along with a swarm of agents and skills etc.

However, I’m seeing .Claude/memory/, docs/, .specify/*, hooks and extensions, context management tools etc becoming as much an overhead to manage as the codebase itself sometimes.

Also, it’s all mixed in together, in the same repo. Surely this is an anti-pattern.

Are there better ways to do this (yet)? Or is this the next AI frontier to evolve?

Comments URL: https://news.ycombinator.com/item?id=48113536

Points: 2

# Comments: 1

New comment by FrankRay78 in "Software engineering may no longer be a lifetime career"

FrankRay78 — Mon, 11 May 2026 21:40:02 +0000

Write a damn good automated review agent that runs against their PRs before even looking at them… works well for me!

New comment by FrankRay78 in "CC-Canary: Detect early signs of regressions in Claude Code"

FrankRay78 — Sat, 25 Apr 2026 16:48:57 +0000

I haven't tracked it recently, but when I've pulled up the metrics I've generally seen about 25% token saving (sometimes higher circa 40%, depending on type of use). I've bought a max Claude plan recently, as I couldn't make enough savings to stay on the Pro plan. Perhaps most importantly, I've not seen any conflict or degradation after installing the plugins, which I've done on both Windows and Linux. Recommended, so far.

New comment by FrankRay78 in "CC-Canary: Detect early signs of regressions in Claude Code"

FrankRay78 — Fri, 24 Apr 2026 21:02:00 +0000

See the very last section in this doc for how I minimise token usage and track savings, all three plugins co-exist fine: https://github.com/FrankRay78/NetPace/blob/main/docs/agentic...

New comment by FrankRay78 in "The Beauty of Bonsai Styles"

FrankRay78 — Tue, 21 Apr 2026 07:30:35 +0000

Most of these are outdoor trees, regardless of size. Something more tropical might fare better inside.

New comment by FrankRay78 in "The Beauty of Bonsai Styles"

FrankRay78 — Tue, 21 Apr 2026 07:29:28 +0000

Not that different to our two year old tortoise, who still has another 100+ years to go.

New comment by FrankRay78 in "Spending 3 months coding by hand"

FrankRay78 — Sat, 18 Apr 2026 11:29:42 +0000

I’m writing production quality code with agents, it was the development ‘harness’ that took time up get right.

New comment by FrankRay78 in "I’m spending months coding the old way"

FrankRay78 — Sat, 18 Apr 2026 11:25:08 +0000

I find something similar happening as I transition to spec driven development - whilst the agents do the work I used to do, I spend a hell of a lot more time thinking about what I want the outcome to be, rather than hacking around the limitations of frameworks I know, avoiding tech I don’t. It’s freeing actually.

New comment by FrankRay78 in "Claude Design"

FrankRay78 — Sat, 18 Apr 2026 11:18:48 +0000

I wonder if this is the death of true design.

New comment by FrankRay78 in "Ask HN: How do you handle clients who don't pay on time?"

FrankRay78 — Sun, 05 Apr 2026 02:26:27 +0000

Include clear payment terms and penalty interest. For me, this looks like 30 payment window, reminders fortnightly there after, and a money claim lodged in the small claims court at 90 days. You’ll almost certainly get your money ahead of court appearance (assuming they haven’t gone bankrupt).

New comment by FrankRay78 in "Show HN: Baton – A desktop app for developing with AI agents"

FrankRay78 — Wed, 01 Apr 2026 13:43:59 +0000

If nothing else, I see that Conductor is currently Mac only.

New comment by FrankRay78 in "Some things just take time"

FrankRay78 — Sat, 21 Mar 2026 22:07:10 +0000

A perfectly good methodology with the right guardrails in place imho.

New comment by FrankRay78 in "Some things just take time"

FrankRay78 — Sat, 21 Mar 2026 22:05:25 +0000

Shrewd context management is the go here.

New comment by FrankRay78 in "Kotlin creator's new language: a formal way to talk to LLMs instead of English"

FrankRay78 — Thu, 12 Mar 2026 16:55:32 +0000

Sure, but where are the formal acceptance tests to validate against?

New comment by FrankRay78 in "Verified Spec-Driven Development (VSDD)"

FrankRay78 — Sat, 28 Feb 2026 22:12:47 +0000

No much different from what I did manually when employer outsourced development to India.

New comment by FrankRay78 in "ai;dr"

FrankRay78 — Fri, 13 Feb 2026 18:53:36 +0000

I would be happy to, but let me think about writing it up properly and posting it as a more serious piece for consideration.

New comment by FrankRay78 in "ai;dr"

FrankRay78 — Thu, 12 Feb 2026 20:29:54 +0000

I’m seriously not astroturfing, point is serious. Most people here would not be able to tell the difference between good human and good AI generated writing anymore in a blind test, especially a blend of both. So if the reader often can’t tell, why is the source of a well written, interesting piece of writing more important, than the effect of the content itself? I don’t feel the OP made a good argument imho.