Hacker News: gervwyk

New comment by gervwyk in "Instant 1.0, a backend for AI-coded apps"

gervwyk — Fri, 10 Apr 2026 16:57:41 +0000

simple. you reduce the surface that you need to manage and shift that responsibility to the framework.

choose a good one and your can save you and your llms 1000s of decisions and future maintenance overheads.

frameworks exists because they scale.

New comment by gervwyk in "We've raised $17M to build what comes after Git"

gervwyk — Fri, 10 Apr 2026 16:54:45 +0000

please also build it for easy multimedia management

New comment by gervwyk in "S3 Files and the changing face of S3"

gervwyk — Tue, 07 Apr 2026 20:53:47 +0000

any recommendations for a lambda based sftp sever setup?

New comment by gervwyk in "TurboQuant KV Compression and SSD Expert Streaming for M5 Pro and IOS"

gervwyk — Wed, 01 Apr 2026 20:13:15 +0000

Anyone else looking at these developments and thinking that local llms are the future. So many advantages above remote, and the hardware is just not there jet, but another leap like apple silicon and the tech is there..

Ofcourse large corps will have fancy proprietary models, but for every day queries and tasks, local feels like a huge, and just slightly out of reach.

Am i missing something fundamental?

New comment by gervwyk in "The Claude Code Source Leak: fake tools, frustration regexes, undercover mode"

gervwyk — Tue, 31 Mar 2026 23:33:11 +0000

how sure are we this entire “accident” is not an aprils fools joke??

Genius level AI marketing

New comment by gervwyk in "Meta and YouTube found negligent in landmark social media addiction case"

gervwyk — Thu, 26 Mar 2026 13:37:23 +0000

now do Candy Crush..

New comment by gervwyk in "iPhone 17 Pro Demonstrated Running a 400B LLM"

gervwyk — Tue, 24 Mar 2026 20:22:07 +0000

there was a time when mainframes was the main thing.. we’ll look back and say data centers was a thing.. (hopefully if we lucky)

New comment by gervwyk in "We should revisit literate programming in the agent era"

gervwyk — Sun, 08 Mar 2026 21:31:22 +0000

For me this is where a config layer shines. Develop a decent framework and then let the agents spin out the configuration.

This allows a trusted and tested abstraction layer that does not shift and makes maintenance easier, while making the code that the agents generate easier to review and it also uses much less tokens.

So as always, just build better abstractions.

New comment by gervwyk in "Nanobot: Ultra-Lightweight Alternative to OpenClaw"

gervwyk — Thu, 05 Feb 2026 21:32:15 +0000

This is a very cool idea. I’ve been dragging CC around very large code bases with a lot of docs and stuff. it does great but can be a swing and a miss.. have been wondering if there is a more efficient / effective way. This got me thinking. Thanks for sharing!

New comment by gervwyk in "GPT-5.3-Codex"

gervwyk — Thu, 05 Feb 2026 21:03:20 +0000

also my experience in using these two models. they are trying to recover from oversteer perhaps.

Hemingway bench AI writing leaderboard

gervwyk — Wed, 04 Feb 2026 20:47:04 +0000

Article URL: https://surgehq.ai/blog/hemingway-bench-ai-writing-leaderboard

Comments URL: https://news.ycombinator.com/item?id=46891512

Points: 1

# Comments: 0

New comment by gervwyk in "Anthropic's original take home assignment open sourced"

gervwyk — Wed, 21 Jan 2026 21:06:34 +0000

Don’t stress, its very likely that this problem was vibe coded :) It’s insane how much better Claude Code is compared to alternatives lately.

New comment by gervwyk in "Creators of Tailwind laid off 75% of their engineering team"

gervwyk — Wed, 07 Jan 2026 21:44:46 +0000

Great point here, the only thing that feels greedy to me is that these larger companies do not contribute back to the foundational libraries that they are building on, even to a minor extent for ecosystem improvements. Perhaps greedy is a strong word.

i’ve always felt that oss licenses needs to include responsible use terms or something. some orgs dont mind paying for value contributed but you need to provide a structure to do so, even if that is on a voluntary basis.

If anyone from Lovable etc sees these comments, great opportunity for sponsorship where it can make a difference upstream.

Some companies have done this well, at a stage Retool use to sponsor a number of open source libs which greatly helped them with exposure to devs. Surely a better way to spend ad revenue imo.

New comment by gervwyk in "Creators of Tailwind laid off 75% of their engineering team"

gervwyk — Wed, 07 Jan 2026 21:26:33 +0000

Please let us know if you launch this open source project, we’d all be excited to use it!

New comment by gervwyk in "Ask HN: Resources to get better at outbound sales?"

gervwyk — Sat, 27 Dec 2025 21:35:01 +0000

Same here, would love to share experiences. From South Africa.

New comment by gervwyk in "Toys with the highest play-time and lowest clean-up-time"

gervwyk — Thu, 25 Dec 2025 20:22:19 +0000

I’m surprised no one mentions Knex. By far my childhood favorite, and for me, far more creative opportunity when comparing to something like lego.

New comment by gervwyk in "AI is wiping out entry-level tech jobs, leaving graduates stranded"

gervwyk — Tue, 16 Dec 2025 21:12:23 +0000

It all depends on how you prompt. and the prompt system you’ve setup.. when done well, you just “steer” the code /system. Quite amazing to see it come together. But there are multiple layers to this.

New comment by gervwyk in "Children with cancer scammed out of millions fundraised for their treatment"

gervwyk — Tue, 16 Dec 2025 12:08:08 +0000

As per other comments, if it’s making them money, why bother banning it

New comment by gervwyk in "Compiler Engineering in Practice"

gervwyk — Sun, 14 Dec 2025 19:12:01 +0000

have to disagree. maybe read a paragraph, its dense with context imo. i find slop to be light on context and wordy, this is not.

Meme: The Complete Version of Modern Digital Infrastructure

gervwyk — Fri, 21 Nov 2025 21:12:31 +0000

Article URL: https://programmerhumor.io/microsoft-memes

Comments URL: https://news.ycombinator.com/item?id=46009048

Points: 2

# Comments: 0