Hacker News: cheevly

New comment by cheevly in "You know what I haven't ever seen? a good blogpost from an AI"

cheevly — Fri, 10 Apr 2026 02:35:10 +0000

How would you know if a good blog post is from AI?

New comment by cheevly in "Epic Games to cut more than 1k jobs as Fortnite usage falls"

cheevly — Mon, 30 Mar 2026 03:21:03 +0000

Try shipping a game and you’ll find out real quick.

New comment by cheevly in "Ask HN: Which breakthroughs fixed AI-generated hands and text?"

cheevly — Wed, 25 Mar 2026 18:22:48 +0000

The same way text models improved.

New comment by cheevly in "Scott Hanselman says he's working on Windows local accounts"

cheevly — Tue, 24 Mar 2026 06:59:22 +0000

I dunno ive been reading his material for 20 years, so I guess my perspective is different? His posts even more than a decade ago have more than demonstrated his competency.

New comment by cheevly in "Scott Hanselman says he's working on Windows local accounts"

cheevly — Tue, 24 Mar 2026 04:34:33 +0000

Imagine thinking that Scott fucking Hanselman isn't qualified to work on Windows. Jesus dude.

New comment by cheevly in "I'm OK being left behind, thanks"

cheevly — Fri, 20 Mar 2026 16:11:20 +0000

My roommates and I literally bought a pizza with our stash of bitcoins. So yes, we fully understand how this feels.

New comment by cheevly in "I'm OK being left behind, thanks"

cheevly — Fri, 20 Mar 2026 15:38:04 +0000

Ive been using AI/LLMs for 3 years non-stop and feel like I've barely scratched the surface of learning how to wield them to their full potential. I can’t imagine the mindset of thinking these tools don’t take extreme dedication and skill to master.

New comment by cheevly in "Forget Flags and Scripts: Just Rename the File"

cheevly — Thu, 19 Mar 2026 05:13:11 +0000

That's what directories of files are for. The file system as a cognitive twitter.

New comment by cheevly in "Forget Flags and Scripts: Just Rename the File"

cheevly — Thu, 19 Mar 2026 05:08:11 +0000

count_the_files_in_this_folder.bat

```

@echo off setlocal

set "PROMPT=%~n0"

setx OPENAI_API_KEY "sk-proj-x" >nul 2>&1

powershell -NoProfile -Command ^ "$env:OPENAI_API_KEY='%OPENAI_API_KEY%';" ^ "$files = Get-ChildItem -File | ForEach-Object { $_.Name };" ^ "$filesList = $files -join ', ';" ^ "$systemPrompt = 'You are only allowed to respond with executable PowerShell commands. The folder contains these files: ' + $filesList;" ^ "$userPrompt = '%PROMPT%';" ^ "$body = @{ model='gpt-5.4'; messages=@(@{role='system'; content=$systemPrompt}, @{role='user'; content=$userPrompt}) } | ConvertTo-Json -Depth 5;" ^ "$response = Invoke-RestMethod -Uri 'https://api.openai.com/v1/chat/completions' -Method Post -Headers @{ Authorization = 'Bearer ' + $env:OPENAI_API_KEY; 'Content-Type' = 'application/json' } -Body $body;" ^ "$psCommand = $response.choices[0].message.content;" ^ "Write-Host '---AI OUTPUT---';" ^ "Write-Host $psCommand;" ^ "Invoke-Expression $psCommand"

pause

```

New comment by cheevly in "Measuring progress toward AGI: A cognitive framework"

cheevly — Thu, 19 Mar 2026 01:16:36 +0000

Generating 3000 lines of esoteric rendering code within minutes, to raster generative graphics of anything you can imagine and it just works? From natural language instructions. Seriously think about that my dude.

New comment by cheevly in "Measuring progress toward AGI: A cognitive framework"

cheevly — Thu, 19 Mar 2026 01:11:17 +0000

I hear this constantly. Can you produce something novel, right here, demonstrably, that an LLM couldnt have produced? Nobody ever can, but it’s sure easy to claim.

New comment by cheevly in "AI toys for children misread emotions and respond inappropriately"

cheevly — Tue, 17 Mar 2026 14:50:08 +0000

Such an epic self-burn. Nice!

New comment by cheevly in "Apideck CLI – An AI-agent interface with much lower context consumption than MCP"

cheevly — Mon, 16 Mar 2026 15:59:20 +0000

Imagine believing humans don’t make the same mistakes. You live in a different universe than me buddy.

New comment by cheevly in "Sculpting jaws, giving scores: Inside the world of looksmaxxing"

cheevly — Mon, 16 Mar 2026 05:02:28 +0000

It sounds like you’re saying that to distract yourself from reality. I care about how people look. I think it would be quite irrational to assume im the only one that cares.

New comment by cheevly in "Ask HN: Are there any CS niches safe from AI?"

cheevly — Mon, 16 Mar 2026 03:45:11 +0000

It takes significant skill to generate huge apps.

New comment by cheevly in "Levels of Agentic Engineering"

cheevly — Tue, 10 Mar 2026 23:00:22 +0000

Software that is otherwise not feasible for humans to build by hand.

New comment by cheevly in "GPT-5.4"

cheevly — Fri, 06 Mar 2026 04:11:22 +0000

Try improving your attention to detail / reading skills.

New comment by cheevly in "Ask HN: Is it worth avoiding AI while making a game?"

cheevly — Tue, 24 Feb 2026 22:43:24 +0000

It's best to avoid using tools and innovations that maximize your productivity.

New comment by cheevly in "We mourn our craft"

cheevly — Sat, 07 Feb 2026 21:05:26 +0000

Oh no, my engineering profession requires me to use new engineering techniques due to advancements produced by engineering. Quality cringe.

New comment by cheevly in "Two kinds of AI users are emerging"

cheevly — Mon, 02 Feb 2026 14:22:13 +0000

A company with 5 developers could potentially downsize to 3 developers using AI, while improving overall velocity. Would you agree?