News for hackers. Stuff that matters.

20wenty

Re:AI poster wins Ohio State Fair contest on Sunday August 02, 2026 @07:40PM (#49149524)
It is very noticeable. Funny how it jumps right out when you've seen AI slop often enough. #5 is good and looks "real", whatever that means any more.
It was incredibly refreshing to read an honest story, warts and all, written by a human. And equally infuriating to read a comment about it written by AI.
Re:I Put a Datacenter GPU in My Gaming PC for £200 on Sunday May 31, 2026 @11:41AM (#48346616)
There are many tells aren't there? There was clearly hard human work and experimentation here, but it's a shame the OP let AI do chunks of the writing. Once you see it, it's much harder to take the post seriously.

Show HN: CoreMem – Portable context for AI agents

https://coremem.app

CoreMem lets you build collections of context, called a mem, and share it with any AI agent via URL, a Chrome extension, MCP, Cursor/VS Code plugins, a skill, and more. Instead of re-explaining your project or goal when you switch agents or start new sessions, CoreMem keeps your context centrally organized so that any AI tool can read it.This originally started as a CLI I built that kept pieces...

( Read More... | no comments | 4 points | on HN )
Re:Create Google API credentials in 50 easy steps (2023) on Tuesday March 10, 2026 @05:54PM (#47329251)
"Google has made it really easy to create api credentials for own use, just follow these few steps..." As someone who's been through that particular gauntlet a few times recently, I got a chuckle from the sarcasm.
Re:Ask HN: Books to learn 6502 ASM and the Apple II on Tuesday January 27, 2026 @09:15AM (#46780185)
I second this -- I just found the Ben Eater series a month or so ago and put together his computer clock over the holidays. It really helps you understand clock cycles, logic chips, etc, and is a good foundation for the 6502 kit you build later in the course. And learning Assembly before BASIC is the right learning path IMO, if only to understand how CPU registers work at the electron level.

Show HN: I wrote a Christmas-themed Space Invaders clone in 8086 Assembly

https://github.com/jbnunn/Invaders

I've had a goal for the past three years to learn Assembly language. This December, I finally put some real effort into learning the language. I followed the tutorials in Oscar Toledo G's "Programming Boot Sector Games" and used Gemini as a tutor to help explain the concepts I was stuck on. It was tempting at points to vibe code some of the trickiest pieces, but I found resisting the temptation...

( Read More... | no comments | on HN )
Re:The Ruliology of Lambdas on Friday September 19, 2025 @11:50AM (#45302989)
I have never made it to the end of a Wolfram post, or a David Foster Wallace book. I'm envious of people who can read AND understand these tomes.
Re:The MCP Registry on Tuesday September 09, 2025 @03:17PM (#45187284)
Yeah it's confusing. They mention https://registry.modelcontextprotocol.io but it is just a redirect to https://github.com/modelcontextprotocol/registry/tree/main/d.... Like MCP itself there's still work to be done, it seems.
Re:Claude Code for VSCode on Monday June 23, 2025 @08:40AM (#44355190)
Do you have details on what "optimise for token usage" looks like in Cursor? Or is your point more about how Cursor manages the context window?
Re:California has got good at building giant batteries on Thursday May 29, 2025 @06:23PM (#44130962)
Thank you, thought I was going crazy. Maybe this is the new thing, adding grammatical errors so people won't think the content was written by AI.
If it gives any unfair advantage at all, the Astros will figure out a way to use them ASAP.

([1,2] For those that don't get the snide reference to cheating.)

[1] https://www.nytimes.com/article/astros-cheating.html

[2] https://en.wikipedia.org/wiki/Houston_Astros_sign_stealing_s...

I like the idea but it will be hard to build a moat -- if that's something you care about. How about making it more general? "touch grass", "feel sand between your fingers", "hug a tree" ...
Re:Ask HN: Books about people who did hard things on Friday January 10, 2025 @08:27AM (#42655411)
Similar in nature is Farthest North: The Incredible Three-Year Voyage to the Frozen Latitudes of the North. Fridjtof Nansen (https://en.wikipedia.org/wiki/Fridtjof_Nansen) led the expedition.
Re:Warp terminal – no more login required on Tuesday November 26, 2024 @01:39PM (#42248532)
I had more about a drawbridge but it was really too much :)
Re:Warp terminal – no more login required on Tuesday November 26, 2024 @01:00PM (#42248113)
The damage is done. You can't overthrow the king (whether you pledge fealty to iTerm2, PowerShell/WSL, Putty, Hyper ... ) if you have to sign up to get past the castle gates. And in the two years it took to remove the signup, the townsfolk have realized their kings are good enough for what they want to do anyway.
Re:Apple is launching its own password manager app on Tuesday June 11, 2024 @10:39AM (#40646695)
Same opinion on 1Password's great service. I've found them to be responsive and accessible anytime I've needed them. I'm not seeing all the bugs and issues others are reporting, but I have noticed a couple of odd UI changes lately that feel a bit like a product manager is bored and looking for work to do.
Re:You can now train a 70B language model at home on Friday March 08, 2024 @09:02AM (#39641123)
For the most part this post was easy to read, and I could feel the collective excitement of the team. I came away feeling like I'd learned something and ready to try it myself. The only time the post gets a little fuzzy is "...store the quantized parameters in a selectable data type, where that storage data type is the same data type as the “computation type” of the mode". I assume "selectable datatype" is the float size of the quantization?
Re:IBM Rebus on Tuesday November 07, 2023 @05:21AM (#38175197)
This is like looking at a painting and thinking "what's the big deal, I could paint that." I'm guilty of the same, and yet, I've never painted.
Re:Every app that adds AI looks like this on Friday October 13, 2023 @01:17PM (#37873013)
You're not necessarily wrong, but you may also be throwing stones from a glass (Substack) house. Barely made it past the fold before I was nagged with a Substack popup.
Re:A Really Big Computer on Wednesday August 09, 2023 @04:29PM (#37067953)
Say what you want about him, but George is one of the few people I know that can actually go a mile wide and a mile deep into any field they choose. And he does most of his digging live on stream, so he makes an easy punching bag. Do I think he'll successfully raise a $400M round on a $2B valuation? No, something else will distract him before that - but I'm going to enjoy watching him (and pulling for him) regardless.
Re:I moved to Germany and regret it on Wednesday June 14, 2023 @08:38AM (#36324969)
That's Insider for you. They're often more concerned with doing exactly that than doing good journalism.
Finally, an interesting article on Insider that doesn't feel like a hit piece.
Re:User: Junnn11 on Thursday April 20, 2023 @06:47AM (#35638270)
Reminds me of the George Costanza line from Seinfeld,

Jerry (on Keith Hernandez): Yeah, he's a real smart guy too. He's a Civil War buff. George: I'd love to be a Civil War buff. What do you have to do to be a buff?

Re:Show HN: Generate commit messages using GPT-3 on Tuesday January 31, 2023 @06:26AM (#34593820)
I believe the original comment was to show some of the sample commit messages in the repo README itself, no?

Older »