Hacker News: aryehof

New comment by aryehof in "Sites in ChatGPT"

aryehof — Sat, 03 Oct 2026 07:06:20 +0000

Most software that isn't trivial is a big ball of mud. AI is trained on that and produces the same (or worse) - faster.

New comment by aryehof in "Plan mode is dead"

aryehof — Tue, 29 Sep 2026 03:58:39 +0000

Are you following more of an “aider” type approach, or something different?

New comment by aryehof in "The new CC, an AI agent built for families"

aryehof — Wed, 23 Sep 2026 06:14:45 +0000

When I was a child, schools didn’t need to communicate on a daily, weekly (or even monthly) basis with parents. How times change. Heck, we went for a whole school day without having to talk to Mummy or Daddy. So this agent is technology to help the mess enabled by technology?

New comment by aryehof in "Introducing System One Models and Jev"

aryehof — Wed, 16 Sep 2026 05:05:50 +0000

As a zero-shot classifier, I expect that effectiveness is dependent on the data trained upon.

Jev input … > Unstructured data (e.g. text) with an emphasis on structured program state.

What pre-training data/model is Jev based on? Surely result effectiveness is dependent (outside of one’s own input as “state”) on that?

New comment by aryehof in "We must pace the frontier"

aryehof — Mon, 14 Sep 2026 08:22:09 +0000

> Without alignment, further improvements in capability turn LLMs into wanton felony generators

Isn’t “full” alignment and guardrails a task that can never be generally achieved? One will always discover and realize the need for new guidelines and guardrails? What about vague, incomplete, inconsistent nuances and generalizations - that make this a losing battle?

I suggest ultimate safeguards need to be outside the models?

New comment by aryehof in "iPhone Duo"

aryehof — Thu, 10 Sep 2026 06:07:49 +0000

Are the Silo shots too dark to see, like when attempting to watch it via an Apple sub?

New comment by aryehof in "Muse – Meta’s personal AI agent"

aryehof — Wed, 09 Sep 2026 04:53:31 +0000

Perhaps a better overview is from Reuters …

https://www.reuters.com/business/meta-launches-ai-agent-that...

From the article:

- … rolled out … despite internal concerns that the technology mismanages its access to sensitive personal data

- The product will be available only in the U.S.initially

- A basic version of the agent will be available for free, while Meta will offer subscriptions priced at $20 a month and $100 a month for heavier usage

- People can opt out of their interactions being used to train Meta's AI models.

- Others flagged serious security flaws, like an agent routing around guardrails …

New comment by aryehof in "The Real Luxuries In Life"

aryehof — Sun, 06 Sep 2026 05:52:01 +0000

On reading the title, the first thing that came to mind was “a good book”.

Albeit, that I view many of the things in the list as “ideals” or “values”, rather than “luxuries”. The greatest thing one can aspire to in terms of an ideal, is to have “peace of mind” in my opinion.

New comment by aryehof in "The Real Luxuries In Life"

aryehof — Sun, 06 Sep 2026 05:46:30 +0000

So true.

New comment by aryehof in "I were 17, I'd learn how to build LLMs from scratch"

aryehof — Wed, 26 Aug 2026 03:47:05 +0000

> I am kind of amazed how negative the comments are here, especially on HN.

Sadly, I attribute this to a decline in having “good will” towards others, and an increase in cynicism, prejudice, and meanness.

New comment by aryehof in "There's no such thing as a small software team anymore"

aryehof — Fri, 21 Aug 2026 04:19:57 +0000

> Build a well architected monolith and be super strict on single purpose and keeping modules separated from each other

Isn’t the question how to keep likely dependent modules separated from each other in a monolith? You say “single purpose”, but how does that admonition work in the reality of a complex problem domain?

New comment by aryehof in "Ask HN: Does anyone else feel like nothing matters anymore?"

aryehof — Tue, 18 Aug 2026 06:34:03 +0000

> Democracy is "everyone gets a vote"

It is that we are governed by those chosen by us to represent us. In a perfect democracy the government is (the majority of) us. Hence the saying … “in a democracy the people get the government they deserve”.

New comment by aryehof in "Ask HN: Does anyone else feel like nothing matters anymore?"

aryehof — Tue, 18 Aug 2026 05:49:17 +0000

> We will be building architectural blueprints for software "buildings" same as Civic Engineers and Architects do for bridges and towers.

If only we knew how. All we seem to know formally given popular discourse is languages, frameworks, tools, protocols and algorithms.

Thinking about how to move beyond functional decomposition and structured design to enable those “blueprints” isn’t even on the agenda?

New comment by aryehof in "Software Engineering fundamentals matter more"

aryehof — Sun, 16 Aug 2026 08:08:39 +0000

> But what really gets me is the model often tries to make assumptions for me that I didn't specify in the prompt.

This is a problem with your instructions, your specification. An LLM isn't a mind reader. It will attempt to succeed regardless of missing requirements and ambiguity.

New comment by aryehof in "I turned my RSS feeds into an e-ink newspaper to stop reading on my phone"

aryehof — Sat, 15 Aug 2026 07:49:25 +0000

I really like the UI. That I prefer to keep my Kindle “books only” is the only reason I might not use inkfeed.

New comment by aryehof in "Ask HN: How do you keep up with HN these days?"

aryehof — Sat, 15 Aug 2026 06:52:47 +0000

I typically use hckr news (https://hckrnews.com/) set to show only the top 10 or top 20. It also has the advantage of showing those i missed overnight or earlier.

New comment by aryehof in "Ask HN: How do you keep up with HN these days?"

aryehof — Sat, 15 Aug 2026 06:48:28 +0000

> hit hide on the domains that I never want to see anything from

I thought hide just hid that particular entry. Have I been wrong all this time?

New comment by aryehof in "Go is an ideal language for AI-assisted software engineering"

aryehof — Wed, 12 Aug 2026 05:19:57 +0000

One of the authors is a Google “Evangelist”. A “Chief” one to boot. Why would you expect different?

New comment by aryehof in "What's the best programming language for coding agents?"

aryehof — Wed, 12 Aug 2026 04:41:04 +0000

> I wonder though if we are asking the right question

I also wonder. Is there no further design thought, research or discussion on how to better modularize a program to address complexity - in an LLM world?

Instead, we still can’t move beyond arguing about languages …

New comment by aryehof in "Improving GPT‑5.6 Sol in ChatGPT, expanding GPT‑5.6 Luna access for free users"

aryehof — Fri, 07 Aug 2026 04:34:41 +0000

For me on a paid plan, the effort indicator was hidden and the model was 5.5 instant. I had to press the + button to select “think harder” before the dial that allowed Sol medium or high to be selected to show.

It made me wonder how many paid subscribers realize they are using the same 5.5 instant model as free users by default. A dark pattern or oversight?