Hacker News: vcryan

New comment by vcryan in "AI, activity, and outcomes in software engineering"

vcryan — Wed, 11 Nov 2026 17:05:41 +0000

We are shipping faster. Shipping speed depends on a variety of factors. That said, the ability to generate and validate designs, code, tests, data, performance and security evals, etc is increasing the speed of delivery for many organizations - I'm a consultant and I see it every day.

I also see companies that don't know what they want to build, suffer from toxic culture etc -- they are not faster because their core problems never had much to do with software development.

Sure, there are plenty of developers clinging to the "old way" or using AI in ways that add complexity and slow things down but I don't see this as the dominant group.

New comment by vcryan in "Claude Whiteboards, Claude Sheets, and Claude Data"

vcryan — Tue, 10 Nov 2026 19:37:50 +0000

Claude vendor lock-in - Claude: not thanks! I prefer you as an easily interchangeable commodity that plays an intermittent role in my broader AI strategy.

New comment by vcryan in "Ask HN: What are you working on? (November 2026)"

vcryan — Mon, 09 Nov 2026 02:39:04 +0000

12 words in, I was like - this must be Aaron :) then I at word 15 I saw OneBusAway and I was like yep. Then I checked your handle, and it is you. TransitOPS-Ryan here - great to see you!

New comment by vcryan in "Agent memory needs its OpenTelemetry moment"

vcryan — Sun, 08 Nov 2026 16:39:12 +0000

I'm not convinced that agent memory is more good than bad.

If there is something an agent needs to know across sessions shouldn't the operator also know and include that information intentionally?

I often catch Claude (and wardon) noting information that is only pertinent to a single season as if it were a forever rule and then I need to tell it to forget.

Maybe the moment we need is to remove this capability?

New comment by vcryan in "Claude Code's "Don't Ask Again" exposes passwords in 1,122 public GitHub files"

vcryan — Sun, 08 Nov 2026 04:10:50 +0000

This is also an example of how someone's personal settings don't belong in a source code repo at all.

I find it pretty annoying when someone commits their harness specific files into a repo - put that stuff under $HOME/.claude/

New comment by vcryan in "Tencent Hy4"

vcryan — Wed, 04 Nov 2026 18:49:52 +0000

It's arguable that there is a threshold of quality that matter and US and China are both there already. I guess we'll see. Many of us on here are software engineers and I think we've seen that while Opus 4.7 (I think) was some sort of outlier/miracle, today there are several options to choose from. Depending on the task, the harness, etc Astra/Fable are only better when the work demands their level of capability - which much of software engineering does not.

New comment by vcryan in "Ask HN: What's your current AI agentic setup?"

vcryan — Wed, 04 Nov 2026 16:14:18 +0000

I built a "software factory" on top of pi agents so I can automate most product dev work

New comment by vcryan in "We're Training a Figma-Fluent Editing Model"

vcryan — Tue, 03 Nov 2026 23:18:11 +0000

With the ability of models to generate design-system aligned interactive prototypes in HTML/Tailwind... there really isn't a purpose for Figma. I use to love it - now I don't touch it. It doesn't really help my process to have not-HTML to work with. Maybe for mobile apps?

New comment by vcryan in "Anthropic's internal AI use, at retail prices, now exceeds its employee pay"

vcryan — Mon, 02 Nov 2026 19:04:51 +0000

They should use Deepseek - much cheaper.

New comment by vcryan in "The new iPad mini"

vcryan — Mon, 26 Oct 2026 16:13:34 +0000

Everything old is new again - return of the phablet.

New comment by vcryan in "Anthropic S-1"

vcryan — Mon, 26 Oct 2026 16:12:11 +0000

I don't participate in stock markets for personal reasons but if I did, I would be betting against Anthropic in the long term. This is a highly commoditized field and while they are a leader it's not clear than any of their attempts at vendor lock-in are working. They are certainly not working on me as I cancel and enable my subscription depending on the availability of capable lower-cost models.

New comment by vcryan in "The State of Context Engineering"

vcryan — Mon, 26 Oct 2026 01:11:19 +0000

I thought the price reduction was because both companies implemented Deepseek's published research which demonstrate effective approaches to lowering the cost of inference while maintaining quality. Thanks to Deepseek, they did lower their costs and they passed that in to their customers.

New comment by vcryan in "Amazon’s “digital pacifier” for toddlers"

vcryan — Sun, 25 Oct 2026 19:35:13 +0000

My kids must be losers - they still like books.

New comment by vcryan in "Dutch government had hacked into Jared Kushner's phone"

vcryan — Fri, 23 Oct 2026 13:44:52 +0000

Yes, Jared Kushner is a human. A human criminal.

New comment by vcryan in "Israeli settlers attack European diplomatic cars in West Bank beat French mayor"

vcryan — Sat, 17 Oct 2026 18:42:02 +0000

The world turns a blind eye to Israeli terrorism.

New comment by vcryan in "Apple HomeView"

vcryan — Tue, 13 Oct 2026 18:00:06 +0000

I always wanted an immovable laptop that is closer to phone size. I'm just a worst of both worlds kids of guy.

New comment by vcryan in "Beam: Reflection's 501B open-weight model"

vcryan — Mon, 05 Oct 2026 21:29:22 +0000

This is like an ad for how great Deepseek V4.1 Flash is.

New comment by vcryan in "Kushner's financial stake in Israeli defence firms conflict of interest concerns"

vcryan — Sat, 03 Oct 2026 23:02:13 +0000

Kushner is like the human embodiment of conflict of interest. I can't see his face without immediately thinking the term: corruption.

He's like the fresh face of elite capture.

New comment by vcryan in "Agents don't need memory, they need documentation"

vcryan — Sat, 03 Oct 2026 22:51:25 +0000

Yes, this makes sense. Memory is an uncurated and often opaque system of arbitrary past discussions. It can help, it can harm. Accurate documentation in the other hand is only beneficial.

New comment by vcryan in "Kolibri: A Sovereign Open-Weight Model"

vcryan — Sat, 03 Oct 2026 22:46:40 +0000

For the benchmark... it seems a bit silly to compare only to outdated/underperforming models.