Hacker News: cheevly

New comment by cheevly in "Ask HN: What was your "oh shit" moment with GenAI?"

cheevly — Fri, 05 Jun 2026 20:32:42 +0000

If yours cant, then I implore you to find better AI mediation tools.

New comment by cheevly in "Ask HN: What was your "oh shit" moment with GenAI?"

cheevly — Fri, 05 Jun 2026 20:31:50 +0000

GPT literally generates perfect code for me in languages that do not exist anywhere in its training set, so I’m not sure how you’ve achieved this level of failure.

New comment by cheevly in "Ask HN: What was your "oh shit" moment with GenAI?"

cheevly — Fri, 05 Jun 2026 20:30:08 +0000

Ever since the first Davinci model of GPT-3 ive literally been using LLMs daily. It was an indispensable tool for me from the very beginning and despite 10,000+ hours of usage and research, I still feel like ive barely cracked the surface of whats possible with current genai tech.

New comment by cheevly in "Let's celebrate work that is 100% human-made"

cheevly — Fri, 05 Jun 2026 20:24:43 +0000

When I use AI to produce a work, it’s human-made, just the same as when I use a computer to synthesize digital works using human-developed automation tools like word processors. All built on top of operating systems that manipulate bytes of all natural human-made data.

New comment by cheevly in "Ask HN: My competitors have flawed products but I can't get traction"

cheevly — Fri, 05 Jun 2026 20:21:55 +0000

This is a great answer.

New comment by cheevly in "Sakana AI's Recursive Self-Improvement (RSI) Lab"

cheevly — Fri, 05 Jun 2026 20:19:08 +0000

Yeaahh, that you assert that makes your point says a lot.

New comment by cheevly in "Ask HN: What made you lose faith in God/Religion?"

cheevly — Thu, 28 May 2026 03:01:28 +0000

I think the prevailing answer is lack of evidence, with things like suffering / death and stuff as a close second.

New comment by cheevly in "A reality check on the AI jobs hysteria"

cheevly — Tue, 26 May 2026 15:50:18 +0000

Imagine classifying Apple as AI experts. You are lost my dude.

New comment by cheevly in "Multi-Agent is a snake oil"

cheevly — Tue, 26 May 2026 14:37:37 +0000

It really sounds like you’re doing it wrong (using multi-agent patterns of yesteryear).

The proper way is to use multiple agents for work involving very large context, and splitting the context amongst them. It effectively enables encapsulation and separation of concerns, which yields much clearer benefits when working at scale.

New comment by cheevly in "The Eternal Sloptember"

cheevly — Mon, 25 May 2026 06:08:34 +0000

Agents are perfectly capable of learning. Why would the model need to learn? The harness and tooling are all that matter.

New comment by cheevly in "The Eternal Sloptember"

cheevly — Mon, 25 May 2026 06:01:27 +0000

This is my experience. Though ice been writing LLM harnesses, agents, tooling, etc for 5 years now and believe it requires several hundred hours of experience before understanding how to consistently outperform at scale.

New comment by cheevly in "Constraint Decay: The Fragility of LLM Agents in Back End Code Generation"

cheevly — Mon, 25 May 2026 04:43:49 +0000

These types of comments help demonstrate first-hand how human reasoning stacks up against what an LLM would say in this situation.

New comment by cheevly in "Constraint Decay: The Fragility of LLM Agents in Back End Code Generation"

cheevly — Mon, 25 May 2026 04:35:20 +0000

A lot of us have been doing this for over a year now.

New comment by cheevly in "Steve Wozniak cheered after telling students they have AI – actual intelligence"

cheevly — Sat, 23 May 2026 01:11:24 +0000

What would you even need to see? I struggle to find things that I cant do at scale with AI, and it’s dumbfounding to read posts about people that are unconvinced.

New comment by cheevly in "Using Claude Code: The unreasonable effectiveness of HTML"

cheevly — Wed, 20 May 2026 05:53:32 +0000

Because markdown can totally do all the stuff that this article is about. Did you even read it?

New comment by cheevly in "“Too dangerous to release” or just too expensive?"

cheevly — Fri, 15 May 2026 13:32:16 +0000

This is the correct response.

New comment by cheevly in "First public macOS kernel memory corruption exploit on Apple M5"

cheevly — Fri, 15 May 2026 12:06:51 +0000

This day is probably not long off. My prediction is before the end of 2028.

New comment by cheevly in "Cisco workforce reductions"

cheevly — Thu, 14 May 2026 04:10:03 +0000

False

New comment by cheevly in "Ask HN: Where is my UX after all those billions spent on LLM codegen?"

cheevly — Fri, 01 May 2026 18:24:05 +0000

I dont know wtf you want, but I know what I want. The rest of us are generating all the apps we’ve ever needed, customized to our exact taste.

New comment by cheevly in "OpenAI releases GPT-5.5 and GPT-5.5 Pro in the API"

cheevly — Sat, 25 Apr 2026 17:18:57 +0000

Wtf are you even talking about? Sam has zero stake in OpenAI.