Hacker News: elpakal

New comment by elpakal in "Why Does Everyone Hate AI?"

elpakal — Thu, 25 Jun 2026 13:46:59 +0000

I work in AI, both building at a large company and consulting on the side. My manager (of two months) uses claude to reply to everyone in Teams and emails, usually filled with nonsensical slop. I believe in its potential when applied correctly but also am realizing that it's unlocking an entirely new kind of fraudster.

New comment by elpakal in "Open Code Review – An AI-powered code review CLI tool"

elpakal — Fri, 05 Jun 2026 01:58:11 +0000

At a kill s@@s hackathon at work, I was able to build something that

uses a node image installs claude code runs a /review-like command puts inline comments to PR deletes old comments when rerunning

OCR seems cool, but overkill, and I'm definitely not using Code Rabbit after their CEO was on here acting snobbish a while back.

Point being AI code review in Git** itself isn't hard to do and can add a lot of value quickly.

New comment by elpakal in "MAI-Code-1-Flash"

elpakal — Tue, 02 Jun 2026 23:25:06 +0000

even worse on mobile

New comment by elpakal in "YouTube to automatically label AI-generated videos"

elpakal — Thu, 28 May 2026 12:24:37 +0000

Now can LinkedIn please label posts

New comment by elpakal in "Microsoft and OpenAI end their exclusive and revenue-sharing deal"

elpakal — Mon, 27 Apr 2026 17:51:25 +0000

Confirmed by Andy Jassy just now https://www.linkedin.com/posts/andy-jassy-8b1615_very-intere...

New comment by elpakal in "The Prompt API"

elpakal — Mon, 27 Apr 2026 13:53:45 +0000

Apple's Foundation models seem great on paper until you see the 4k context window. (though I know we are still early in this chapter).

Google to invest up to $40B in Anthropic in cash and compute

elpakal — Fri, 24 Apr 2026 20:00:30 +0000

Article URL: https://techcrunch.com/2026/04/24/google-to-invest-up-to-40b-in-anthropic-in-cash-and-compute/

Comments URL: https://news.ycombinator.com/item?id=47895080

Points: 209

# Comments: 7

New comment by elpakal in "Ask HN: What Are You Working On? (April 2026)"

elpakal — Mon, 13 Apr 2026 13:42:36 +0000

dotIPA, an iOS app build size inspector that runs locally on your macOS [$4.99]

Track app size growth over time, inspect contents, spot duplication and size bloat and more.

https://apps.apple.com/us/app/dotipa/id6742254881

New comment by elpakal in "Show HN: March Madness Bracket Challenge for AI Agents Only"

elpakal — Tue, 17 Mar 2026 17:07:24 +0000

I thought about using claw but felt like overkill and wonder if an AI browser (atlas etc) would do the trick.

New comment by elpakal in "Show HN: March Madness Bracket Challenge for AI Agents Only"

elpakal — Tue, 17 Mar 2026 17:06:27 +0000

Really cool idea. My son is using different LLMs to fill out brackets for his 4th grade science experiment, and then we are going to compare them to the experts. I like your idea of Strategy/Inspiration prompting, we had to tell them that "upsets happen" because all the favorites were picked on first pass.

Tangentially, I wonder if we are going to see AI predictions impact point spreads.

New comment by elpakal in "Levels of Agentic Engineering"

elpakal — Wed, 11 Mar 2026 15:44:36 +0000

thanks

New comment by elpakal in "Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon"

elpakal — Wed, 11 Mar 2026 15:43:25 +0000

Sorry, I scrolled through some of the rest of the comments on this thread and can’t stay tuned.

New comment by elpakal in "Launch HN: RunAnywhere (YC W26) – Faster AI Inference on Apple Silicon"

elpakal — Wed, 11 Mar 2026 14:56:41 +0000

> This is a known limitation with small LLMs (0.6B-1.2B) doing tool calling.

To me this is this nut to crack, wrt tool calling and locally running inference. This seems like a really cool project and I'm going to dive around a little later but if it's hallucinating for something as basic as this makes me think it's more of POC stage right now (to echo other sentiment here).

New comment by elpakal in "Levels of Agentic Engineering"

elpakal — Wed, 11 Mar 2026 14:49:00 +0000

> file-based state that persists between agent invocations

Can you expand on this with a practical example?

Ask HN: What Happened to Llama Models?

elpakal — Tue, 10 Mar 2026 14:58:06 +0000

Has meta conceded in the race to have the best llm? They've been awfully quiet over there.

Comments URL: https://news.ycombinator.com/item?id=47324159

Points: 2

# Comments: 1

New comment by elpakal in "Ask HN: What Are You Working On? (March 2026)"

elpakal — Mon, 09 Mar 2026 20:17:22 +0000

An iOS app size analysis tool you can run on your Mac and track build size changes over time https://apps.apple.com/us/app/dotipa/id6742254881

Ask HN: Git branching strategy when using multiple CLIs running multiple agents?

elpakal — Mon, 02 Mar 2026 19:38:13 +0000

How do you manage git branching and asynchronous changes happening when running multiple terminal windows and multiple agents on the same code?

Comments URL: https://news.ycombinator.com/item?id=47223001

Points: 1

# Comments: 0

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

elpakal — Mon, 09 Feb 2026 16:00:37 +0000

An iOS build size analysis app that runs locally on your Mac: https://apps.apple.com/us/app/dotipa/id6742254881

New comment by elpakal in "Xcode 26.3 – Developers can leverage coding agents directly in Xcode"

elpakal — Thu, 05 Feb 2026 21:13:59 +0000

Does fastlane still hang for a little before every command? I used to optimize build pipelines for a large company's iOS teams and it always seemed to stall for a little before doing the work. We eventually moved to Xcode Cloud (mainly to avoid code signing) and ran xcodebuild directly.

New comment by elpakal in "The Codex App"

elpakal — Mon, 02 Feb 2026 23:59:10 +0000

why would it need local network access though, I wonder?