Hacker News: emehex

New comment by emehex in "Lisette a little language inspired by Rust that compiles to Go"

emehex — Sun, 05 Apr 2026 11:16:26 +0000

Looks a lot like Swift! Awesome!

New comment by emehex in "Local LLM App by Ente"

emehex — Wed, 25 Mar 2026 14:48:24 +0000

There are literally 1000s of these types of apps. Why is this on the Front Page?

New comment by emehex in "Kagi Small Web"

emehex — Tue, 17 Mar 2026 10:00:51 +0000

StumbleUpon?

New comment by emehex in "Kagi Translate now supports LinkedIn Speak as an output language"

emehex — Tue, 17 Mar 2026 10:00:04 +0000

Can anyone get LinkedIn>English working? Nothing I've found and pasted in has seemed to work... just spits back out the original

New comment by emehex in "Show HN: Rudel – Claude Code Session Analytics"

emehex — Thu, 12 Mar 2026 14:23:31 +0000

For those unaware, Claude Code comes with a built in /insights command...

New comment by emehex in "Ask HN: What did you read in 2025?"

emehex — Sat, 27 Dec 2025 00:21:05 +0000

Favourite books of the year:

"When the Moon Hits Your Eye" - John Scalzi

"Making History" - K.J. Parker

"Let Dogs be Dogs" - Monks of New Skete

"The First Gentleman" - Bill Clinton (it's actually fun!)

"The Thinking Machine" - Stephen Witt

New comment by emehex in "Volvo Centum is Dalton Maag's new typeface for Volvo"

emehex — Tue, 23 Dec 2025 20:48:02 +0000

I thought Volvo was publicly traded. Had to look it up.

Volvo Group - sells trucks - publicly traded - Swedish

Volvo Cars - sells cars - not publicly traded - 100% owned by Geely (Chinese)

Volvo Cars ≠ Volvo Group

New comment by emehex in "My Workflow Is 70% AI, 20% Copy-Paste, 10% Panic. What's Yours?"

emehex — Wed, 10 Sep 2025 11:47:57 +0000

My flow (with legacy software) is: manual strip > LLM > manual clean up > repeat

New comment by emehex in "We're Joining OpenAI"

emehex — Wed, 03 Sep 2025 20:14:24 +0000

If your iOS project has more than 700 files... you might be doing it wrong?

New comment by emehex in "Open models by OpenAI"

emehex — Tue, 05 Aug 2025 17:18:00 +0000

So 120B was Horizon Alpha and 20B was Horizon Beta?

New comment by emehex in "Perplexity is using stealth, undeclared crawlers to evade no-crawl directives"

emehex — Mon, 04 Aug 2025 15:46:45 +0000

Would highly recommend listening to the latest Hard Fork podcast with Matthew Prince (CEO, Cloudflare): https://www.nytimes.com/2025/08/01/podcasts/hardfork-age-res...

I was skeptical about their gatekeeping efforts at first, but came away with a better appreciation for the problem and their first pass at a solution.

New comment by emehex in "Vibe code is legacy code"

emehex — Wed, 30 Jul 2025 22:39:45 +0000

I think the question to ask about your two scenarios: in which is it faster and cheaper to get from v1 to v2? From v2 to v3? I think, for right now, it's cheaper under scenario B. But in the future? Who knows!

New comment by emehex in "Stop Building AI Tools Backwards"

emehex — Wed, 23 Jul 2025 19:32:21 +0000

Counter-counter-point: handwriting > typing for remembering things (https://www.glamour.com/story/typing-memory)

Ask HN: How does my usage of LLMs train the underlying models?

emehex — Wed, 25 Jun 2025 11:55:02 +0000

I understand that using tools like Chat, Cursor, and Claude Code for software development is likely providing training data to help these LLMs get better at coding (the irony isn't lost on me that I might be contributing to making myself obsolete...)

But I'm curious about the actual mechanics: How exactly does this feedback loop work? When I accept, reject, or modify the code that these models spit out, is that signal fed directly back into training?

Not necessarily against this, just genuinely curious about how the sausage is made.

Comments URL: https://news.ycombinator.com/item?id=44376231

Points: 1

# Comments: 1

New comment by emehex in "Why Pandas feels clunky when coming from R (2024)"

emehex — Sat, 07 Jun 2025 19:48:15 +0000

I haven't seriously used R in nearly a decade but I still miss (and think about) dpylr and the hadleyverse...

A few years ago I made a package called "redframes" that tried to "solve" all of my frustrations with pandas, make data wrangling feel more like R, while retaining all the best bits of Python...

Alas, it never really took off. For those curious: https://github.com/maxhumber/redframes

New comment by emehex in "Gemini-2.5-pro-preview-06-05"

emehex — Thu, 05 Jun 2025 17:03:49 +0000

Is this "kingfall"?

New comment by emehex in "MCP explained without hype or fluff"

emehex — Thu, 22 May 2025 17:43:28 +0000

As in: "JSON was a huge deal, and this could also be a huge deal" or "Just use JSON"?

New comment by emehex in "Ask HN: What are you working on? (March 2025)"

emehex — Sun, 30 Mar 2025 22:51:57 +0000

Dusting off the game I made during the pandemic and trying to actually grow the player base in earnest.

It's turn-based two-player game sorta like chess, but the pieces take up multiple spaces.

App Store: https://apps.apple.com/ca/app/kingbit/id1565583669

New comment by emehex in "I'm Peter Roberts, immigration attorney who does work for YC and startups. AMA"

emehex — Fri, 14 Mar 2025 15:18:39 +0000

Scenario: A Canadian tech worker (software engineer) has been working in tech for 10-ish years, however, their University degree (general BA, BSc, etc) does not match the work that they've been doing. Would this person be SOL for a TN/H1B? To improve their chances would it be advisable to get a 1-year accelerated Master's in the field (CompSci, AI)?

New comment by emehex in "Ask HN: What are you working on? (February 2025)"

emehex — Mon, 24 Feb 2025 14:44:23 +0000

I'm working on my online multiplayer game: kingbit (iOS). I released it back in 2023 and haven't touched the code since. It's still by far my most successful app (7.3M impressions, 500 MAU) so I'm excavating the code and going to try and seriously monetize this project into a real business.