Hacker News: jaredsohn

New comment by jaredsohn in "Ask HN: Show your AI coded games [June 2026]"

jaredsohn — Sat, 13 Jun 2026 01:55:36 +0000

Reminds me of ZeptoLab (company that made Cut The Rope)'s Pudding Monsters but it adds a lot more variety. (And it combines them together within one square instead of multiple squares and they don't fall off the edge of the screen.)

New comment by jaredsohn in "Anthropic's model naming, extrapolated"

jaredsohn — Wed, 10 Jun 2026 22:44:29 +0000

Models like Haiku are great if you just want to apply JSON structure to some free text.

New comment by jaredsohn in "Ask HN: How to get my contact info off US political party's list"

jaredsohn — Sun, 07 Jun 2026 04:22:20 +0000

For SMS, you can block text messages that match keywords via apps like VeroSMS on the iPhone. There may be similar apps on Android.

I personally don't think it is possible to get yourself off all of the lists so I do that and mark as spam in gmail.

New comment by jaredsohn in "Ask HN: How did you discover Hacker News?"

jaredsohn — Sat, 06 Jun 2026 04:06:34 +0000

Strangely I think it was TechCrunch. But I was reading pg's essays years earlier (maybe through Joel On Software) and already had known about yc.

Think it was related to the initial request for startups post: https://techcrunch.com/2009/08/16/y-combinator-starts-seedin...

New comment by jaredsohn in "Ask HN: Why Ask HN has only 14 questions now?"

jaredsohn — Wed, 03 Jun 2026 21:07:46 +0000

This posting made it 15 :)

Might be date-related; all are from past 3 days

New comment by jaredsohn in "Don't just paste the AI at me"

jaredsohn — Sat, 23 May 2026 02:18:24 +0000

The site has been updated now to use the current domain.

New comment by jaredsohn in "Don't just paste the AI at me"

jaredsohn — Sat, 23 May 2026 00:56:05 +0000

Weird thing is that domain is even available to buy.

New comment by jaredsohn in "Ask HN: How much AI is in your writing?"

jaredsohn — Fri, 22 May 2026 19:00:19 +0000

If you do have AI write for you, I think it is useful to indicate what is going on by having a rule set up for it. That can at least prepare the reader for reading AI text.

I personally find it okay / convenient to have AI respond to PR review comments with respect to something being addressed or why it was not. That text is often pretty mechanical.

New comment by jaredsohn in "Why does it look like LLMs consistently overestimate implementation time?"

jaredsohn — Fri, 22 May 2026 06:40:32 +0000

>day or 2 max

I've frequently seen tasks that it thinks will take weeks being done in under an hour. And it will often recommend doing X instead of Y because X requires so much extra work. Basically I just remind it that it is an LLM.

If it worries something is error prone, I ask it to write tools to verify it.

New comment by jaredsohn in "Building my own Vi text editor in BASIC"

jaredsohn — Thu, 07 May 2026 01:54:54 +0000

The line numbers were also used for GOTO and GOSUB (although later on languages supported strings instead of numbers).

New comment by jaredsohn in "GitHub Stacked PRs"

jaredsohn — Mon, 13 Apr 2026 20:53:09 +0000

There are tools that use LLMs to do this.

I've done this manually by building a big feature branch and asking an LLM to extract out functionality for a portion of it.

For the former, it would seem to split based on frontend/backend, etc. rather than what semantically makes the most sense and for the latter it would include changes I don't want and forget some I do want. But I haven't tried this a lot.

New comment by jaredsohn in "AI may be making us think and write more alike"

jaredsohn — Tue, 07 Apr 2026 14:51:04 +0000

The GP said more with LLMs than people - not no interactions at all with people and not preferring machines to people. I don't think it is that hard to spend more time talking with LLMs than people if you work in tech and I don't think that takes away from one's life meaningfulness.

New comment by jaredsohn in "I won't download your app. The web version is a-ok"

jaredsohn — Mon, 06 Apr 2026 17:18:10 +0000

One thing that is useful to remember is that if you ask AI for help on using some app, it will likely refer to the mobile UI instead of the web UI. I find it annoying that sometimes there are features that are only available in the mobile UI.

New comment by jaredsohn in "Delve removed from Y Combinator"

jaredsohn — Sat, 04 Apr 2026 03:19:11 +0000

Interestingly, they show up in the company list. When you click the link it returns 404.

https://www.ycombinator.com/companies/?query=delve

New comment by jaredsohn in "Claude Code's source code has been leaked via a map file in their NPM registry"

jaredsohn — Tue, 31 Mar 2026 18:51:45 +0000

>that conversation is lost forever.

You should be able to find it in ~/.claude

You can also ask Claude to search your history to answer questions about it.

New comment by jaredsohn in "Ask HN: Why isn't using AI in production considered stupid?"

jaredsohn — Sun, 29 Mar 2026 08:15:09 +0000

Your original post (and even after this comment I think) was vague in that AI can be used in a lot of different ways in 'production' - to generate code, to manage deployment / scripts, or as part of a feature that uses inference.

For example, if you're writing code with AI, you can still review it just like you would if a colleague wrote it. You can write tests (or have the AI do so) to prevent some hallucinations, too.

New comment by jaredsohn in "Ask HN: Why isn't using AI in production considered stupid?"

jaredsohn — Sun, 29 Mar 2026 08:02:05 +0000

This question is too vague to answer.

New comment by jaredsohn in "Our commitment to Windows quality"

jaredsohn — Fri, 20 Mar 2026 21:43:29 +0000

This xkcd is again relevant: https://xkcd.com/2501/

New comment by jaredsohn in "Ask HN: How do you use Coding Agents/CLIs out of coding?"

jaredsohn — Sat, 14 Mar 2026 18:59:29 +0000

I find it great for nutrition and cooking. I used AI to build a food tracker that works at the micronutrient level (LLMs built the code but are mostly not used in the app itself) but many of my prompts are helping me to learn nutrition in general.

I also use it to help me learn to cook more/better so I ask it questions about the how / why and have made a database of recipes that I tweak based on interests / abilities.

A neat thing is you can always ask AI - what can I do to eat or cook better? Then you do it and keep repeating.

New comment by jaredsohn in "MCP server that reduces Claude Code context consumption by 98%"

jaredsohn — Sun, 01 Mar 2026 00:39:15 +0000

Treat context like git shas. Yes, there is a specific order within a 'branch' but you should be able to do the equivalent of cherry-picking and rebasing it