Hacker News: haneul

New comment by haneul in "GitHub is investigating unauthorized access to their internal repositories"

haneul — Wed, 20 May 2026 07:01:10 +0000

NX again??

This isn't the first time their plugin has led to RCE...

New comment by haneul in "I believe there are entire companies right now under AI psychosis"

haneul — Sat, 16 May 2026 09:26:02 +0000

How are you able to get to $300/hr productively? (I’m assuming this isn’t fast mode tax).

New comment by haneul in "Ask HN: Who is using OpenClaw?"

haneul — Wed, 15 Apr 2026 22:25:57 +0000

Works perfectly installed as part of a server and at mentioning you there. Direct DMs are finicky in my experience.

New comment by haneul in "ChatGPT for Excel"

haneul — Wed, 15 Apr 2026 22:23:30 +0000

Except for pro and plus users in the EU eh…

New comment by haneul in "Ask HN: Who is using OpenClaw?"

haneul — Wed, 15 Apr 2026 22:16:42 +0000

I still use it.

We have it as a data analyst that’s been trained via exemplar queries and MD about the underlying databases.

It also does ad creatives analysis and overall paid marketing spend analysis, including delivering briefs and conversing with stakeholders about things such as cross-ad-platform deduplicated cost of customer acquisition.

In general it is used to lower the technical bar required for cross-domain collab.

New comment by haneul in "Mount Mayhem at Netflix: Scaling Containers on Modern CPUs"

haneul — Wed, 04 Mar 2026 03:48:44 +0000

Interesting, another case of removing HT improving performance. Reminds me of doing that on Intel CPUs of a few gens ago.

New comment by haneul in "Toyota’s hydrogen-powered Mirai has experienced rapid depreciation"

haneul — Sun, 22 Feb 2026 05:59:32 +0000

There were also really good financing deals during Covid. Net for me after all costs after resale was $1k for the years I owned the car (the 2nd gen).

But I got in near the bottom and got out before the market for it dumped.

New comment by haneul in "Masked namespace vulnerability in Temporal"

haneul — Fri, 06 Feb 2026 21:46:02 +0000

Even in a product as technically wonderful as Temporal, we can have relatively simple oversights like this that lead to cross tenant leakage.

If anyone is more familiar with Temporal, is there a way clients could have had internal defense in depth that guards against tenant leakage at the provider (Temporal) level?

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

haneul — Thu, 05 Feb 2026 19:09:12 +0000

My codex CLI didn’t notice version bump available, but I manually did pnpm add -g @openai/codex and 5.3 was there after.

New comment by haneul in "GPT-5-reasoning alpha found in the wild"

haneul — Sat, 19 Jul 2025 12:52:56 +0000

As someone who doesn't keep track of the influencer scene at the moment because I am way addicted to building...

You should totally give Claude Code a try. The biggest problem is that it is glaze-optimized, so have to work at getting it to not treat you like the biggest genius of all time. But when you manage to get in a good flow with it, and your project is very predictably searchable, results start to be quite helpful, even if just to unstuck yourself when you're in a rut.

New comment by haneul in "Ask HN: What Are You Working On? (June 2025)"

haneul — Mon, 30 Jun 2025 04:30:56 +0000

Hah that's pretty fun. I got tossed about by the animated hands for a few, but grabbed a 194 after that.

Dunno about the trigrams though, mostly it's on the "token group" level for me - either the upcoming lookahead feels familiar or it doesn't, and I don't much get bothered by the specific letters as much as "oh I don't have muscle memory on that word, and it's sadly nestled between two easy words, so it's going to be a patchy bit of alternating speed".

New comment by haneul in "Better Auth, by a self-taught Ethiopian dev, raises $5M from Peak XV, YC"

haneul — Wed, 25 Jun 2025 22:27:15 +0000

Love this news! Amazing by Bereket!

New comment by haneul in "ChatGPT's enterprise success against Copilot fuels OpenAI/Microsoft rivalry"

haneul — Tue, 24 Jun 2025 23:08:20 +0000

I wonder if a Lexus/Toyota Acura/Honda Lamborghini/Audi OpenAI/Microsoft marketing split isn't in the best interests of tech giants going forward since LLMs are nondeterministic, unlike the deterministic nation-states they've built up till now...

New comment by haneul in "I Solved a 7-Day Calculation Problem in a Weekend"

haneul — Tue, 24 Jun 2025 06:41:19 +0000

Don’t dangle the man - enrich him with your advice!

New comment by haneul in "Discord Is Threatening to Shutdown BotGhost"

haneul — Mon, 23 Jun 2025 21:05:43 +0000

Yea the data market from discord bots is quite a thing. Really concerning, imo.

New comment by haneul in "NASA's Voyager Found a 30k-50k Kelvin "Wall" at the Edge of Solar System"

haneul — Mon, 23 Jun 2025 20:24:56 +0000

> tin foil can disrupt mind control

You're not weaponizing Gell-Mann amnesia against us are you?

New comment by haneul in "AGI is Mathematically Impossible 2: When Entropy Returns"

haneul — Mon, 23 Jun 2025 07:34:50 +0000

I suppose it disproves embodied, fully meat-space god if sound?

New comment by haneul in "AGI is Mathematically Impossible 2: When Entropy Returns"

haneul — Mon, 23 Jun 2025 06:56:52 +0000

> In plain language:

> No matter how sophisticated, the system MUST fail on some inputs.

Well, no person is immune to propaganda and stupididty, so I don't see it as a huge issue.

New comment by haneul in "Why agents are bad pair programmers"

haneul — Tue, 10 Jun 2025 06:56:55 +0000

Hmm you can tweak fine these days without messing up context. But, I run in “ask mode” only, with opus in claude code and o3 max in cursor. I specifically avoid agent mode because, like in the post, I feel like I gain less over time.

I infrequently tab complete. I type out 80-90% of what is suggested, with some modifications. It does help I can maintain 170 wpm indefinitely on the low-medium end.

Keeping up with the output isn’t much an issue at the moment given the limited typing speed of opus and o3 max. Having gained more familiarity with the workflow, the reading feels easier. Felt too fast at first for sure.

My hot take is that if GitHub copilot is your window into llms, you’re getting the motel experience.

New comment by haneul in "Typing 118 WPM broke my brain in the right ways"

haneul — Mon, 02 Jun 2025 20:39:15 +0000

Monkeytype is better than keybr imo. More options (eg coding modes), actual zen mode, and doesn’t break above 149.5 wpm like keybr does (or did, haven’t been there in 2 years).