Mobile carriers can get your GPS location
489 by cbeuw | 320 comments on Hacker News.
Saturday, January 31, 2026
Friday, January 30, 2026
Thursday, January 29, 2026
Somebody used spoofed ADSB signals to raster the meme of JD Vance
Somebody used spoofed ADSB signals to raster the meme of JD Vance
468 by wubin | 115 comments on Hacker News.
https://ift.tt/1egMRzV https://ift.tt/W2Xgtlj...
468 by wubin | 115 comments on Hacker News.
https://ift.tt/1egMRzV https://ift.tt/W2Xgtlj...
Wednesday, January 28, 2026
A few random notes from Claude coding quite a bit last few weeks
A few random notes from Claude coding quite a bit last few weeks
528 by bigwheels | 438 comments on Hacker News.
https://ift.tt/b2dY0mN
528 by bigwheels | 438 comments on Hacker News.
https://ift.tt/b2dY0mN
Tuesday, January 27, 2026
Monday, January 26, 2026
Sunday, January 25, 2026
Claude Code's new hidden feature: Swarms
Claude Code's new hidden feature: Swarms
424 by AffableSpatula | 287 comments on Hacker News.
https://ift.tt/IR8H1rE https://ift.tt/KJ6pqVX
424 by AffableSpatula | 287 comments on Hacker News.
https://ift.tt/IR8H1rE https://ift.tt/KJ6pqVX
Saturday, January 24, 2026
I built a light that reacts to radio waves [video]
I built a light that reacts to radio waves [video]
462 by codetheweb | 102 comments on Hacker News.
https://ift.tt/acLmEBA
462 by codetheweb | 102 comments on Hacker News.
https://ift.tt/acLmEBA
Friday, January 23, 2026
Thursday, January 22, 2026
Claude's new constitution
Claude's new constitution
439 by meetpateltech | 424 comments on Hacker News.
https://ift.tt/LF7Uoei
439 by meetpateltech | 424 comments on Hacker News.
https://ift.tt/LF7Uoei
Wednesday, January 21, 2026
EU–INC – A new pan-European legal entity
EU–INC – A new pan-European legal entity
475 by tilt | 459 comments on Hacker News.
Speech: https://ift.tt/fOWCXY0...
475 by tilt | 459 comments on Hacker News.
Speech: https://ift.tt/fOWCXY0...
Tuesday, January 20, 2026
Level S4 solar radiation event
Level S4 solar radiation event
439 by WorldPeas | 149 comments on Hacker News.
https://ift.tt/gi40Q8u
439 by WorldPeas | 149 comments on Hacker News.
https://ift.tt/gi40Q8u
Monday, January 19, 2026
Sunday, January 18, 2026
Saturday, January 17, 2026
Cursor's latest “browser experiment” implied success without evidence
Cursor's latest “browser experiment” implied success without evidence
490 by embedding-shape | 203 comments on Hacker News.
Related: Scaling long-running autonomous coding - https://ift.tt/In91SjZ - Jan 2026 (174 comments)
490 by embedding-shape | 203 comments on Hacker News.
Related: Scaling long-running autonomous coding - https://ift.tt/In91SjZ - Jan 2026 (174 comments)
Friday, January 16, 2026
Ask HN: How can we solve the loneliness epidemic?
Ask HN: How can we solve the loneliness epidemic?
485 by publicdebates | 796 comments on Hacker News.
Countless voiceless people sit alone every day and have no one to talk to, people of all ages, who don't feel that they can join any local groups. So they sit on social media all day when they're not at work or school. How can we solve this?
485 by publicdebates | 796 comments on Hacker News.
Countless voiceless people sit alone every day and have no one to talk to, people of all ages, who don't feel that they can join any local groups. So they sit on social media all day when they're not at work or school. How can we solve this?
Thursday, January 15, 2026
Wednesday, January 14, 2026
Tuesday, January 13, 2026
Monday, January 12, 2026
Sunday, January 11, 2026
Show HN: I used Claude Code to discover connections between 100 books
Show HN: I used Claude Code to discover connections between 100 books
423 by pmaze | 130 comments on Hacker News.
I think LLMs are overused to summarise and underused to help us read deeper. I built a system for Claude Code to browse 100 non-fiction books and find interesting connections between them. I started out with a pipeline in stages, chaining together LLM calls to build up a context of the library. I was mainly getting back the insight that I was baking into the prompts, and the results weren't particularly surprising. On a whim, I gave CC access to my debug CLI tools and found that it wiped the floor with that approach. It gave actually interesting results and required very little orchestration in comparison. One of my favourite trail of excerpts goes from Jobs’ reality distortion field to Theranos’ fake demos, to Thiel on startup cults, to Hoffer on mass movement charlatans ( https://ift.tt/LHkpX2D ). A fun tendency is that Claude kept getting distracted by topics of secrecy, conspiracy, and hidden systems - as if the task itself summoned a Foucault’s Pendulum mindset. Details: * The books are picked from HN’s favourites (which I collected before: https://ift.tt/NBwxpU6 ). * Chunks are indexed by topic using Gemini Flash Lite. The whole library cost about £10. * Topics are organised into a tree structure using recursive Leiden partitioning and LLM labels. This gives a high-level sense of the themes. * There are several ways to browse. The most useful are embedding similarity, topic tree siblings, and topics cooccurring within a chunk window. * Everything is stored in SQLite and manipulated using a set of CLI tools. I wrote more about the process here: https://ift.tt/G8j9FHR I’m curious if this way of reading resonates for anyone else - LLM-mediated or not.
423 by pmaze | 130 comments on Hacker News.
I think LLMs are overused to summarise and underused to help us read deeper. I built a system for Claude Code to browse 100 non-fiction books and find interesting connections between them. I started out with a pipeline in stages, chaining together LLM calls to build up a context of the library. I was mainly getting back the insight that I was baking into the prompts, and the results weren't particularly surprising. On a whim, I gave CC access to my debug CLI tools and found that it wiped the floor with that approach. It gave actually interesting results and required very little orchestration in comparison. One of my favourite trail of excerpts goes from Jobs’ reality distortion field to Theranos’ fake demos, to Thiel on startup cults, to Hoffer on mass movement charlatans ( https://ift.tt/LHkpX2D ). A fun tendency is that Claude kept getting distracted by topics of secrecy, conspiracy, and hidden systems - as if the task itself summoned a Foucault’s Pendulum mindset. Details: * The books are picked from HN’s favourites (which I collected before: https://ift.tt/NBwxpU6 ). * Chunks are indexed by topic using Gemini Flash Lite. The whole library cost about £10. * Topics are organised into a tree structure using recursive Leiden partitioning and LLM labels. This gives a high-level sense of the themes. * There are several ways to browse. The most useful are embedding similarity, topic tree siblings, and topics cooccurring within a chunk window. * Everything is stored in SQLite and manipulated using a set of CLI tools. I wrote more about the process here: https://ift.tt/G8j9FHR I’m curious if this way of reading resonates for anyone else - LLM-mediated or not.
Saturday, January 10, 2026
Friday, January 9, 2026
Cloudflare CEO on the Italy fines
Cloudflare CEO on the Italy fines
443 by sidcool | 612 comments on Hacker News.
https://ift.tt/NWb6lua https://ift.tt/viaYQCm...
443 by sidcool | 612 comments on Hacker News.
https://ift.tt/NWb6lua https://ift.tt/viaYQCm...
Thursday, January 8, 2026
Wednesday, January 7, 2026
Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone
Stop Doom Scrolling, Start Doom Coding: Build via the terminal from your phone
474 by rbergamini27 | 344 comments on Hacker News.
I used Tailscale, an old laptop, Claude Code, and Termius to code from my phone anywhere I have Internet connection. Great for parties where you rather be home tinkering.
474 by rbergamini27 | 344 comments on Hacker News.
I used Tailscale, an old laptop, Claude Code, and Termius to code from my phone anywhere I have Internet connection. Great for parties where you rather be home tinkering.
Tuesday, January 6, 2026
Monday, January 5, 2026
Sunday, January 4, 2026
Saturday, January 3, 2026
Friday, January 2, 2026
Thursday, January 1, 2026
Show HN: Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc.
Show HN: Use Claude Code to Query 600 GB Indexes over Hacker News, ArXiv, etc.
361 by Xyra | 126 comments on Hacker News.
Paste in my prompt to Claude Code with an embedded API key for accessing my public readonly SQL+vector database, and you have a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens of other high-quality public commons sites. Claude whips up the monster SQL queries that safely run on my machine, to answer your most nuanced questions. There's also an Alerts functionality, where you can just ask Claude to submit a SQL query as an alert, and you'll be emailed when the ultra nuanced criteria is met (and the output changes). Like I want to know when somebody posts about "estrogen" in a psychoactive context, or enough biology metaphors when talking about building infrastructure. Currently have embedded: posts: 1.4M / 4.6M comments: 15.6M / 38M That's with Voyage-3.5-lite. And you can do amazing compositional vector search, like search @FTX_crisis - (@guilt_tone - @guilt_topic) to find writing that was about the FTX crisis and distinctly without guilty tones, but that can mention "guilt". I can embed everything and all the other sources for cheap, I just literally don't have the money.
361 by Xyra | 126 comments on Hacker News.
Paste in my prompt to Claude Code with an embedded API key for accessing my public readonly SQL+vector database, and you have a state-of-the-art research tool over Hacker News, arXiv, LessWrong, and dozens of other high-quality public commons sites. Claude whips up the monster SQL queries that safely run on my machine, to answer your most nuanced questions. There's also an Alerts functionality, where you can just ask Claude to submit a SQL query as an alert, and you'll be emailed when the ultra nuanced criteria is met (and the output changes). Like I want to know when somebody posts about "estrogen" in a psychoactive context, or enough biology metaphors when talking about building infrastructure. Currently have embedded: posts: 1.4M / 4.6M comments: 15.6M / 38M That's with Voyage-3.5-lite. And you can do amazing compositional vector search, like search @FTX_crisis - (@guilt_tone - @guilt_topic) to find writing that was about the FTX crisis and distinctly without guilty tones, but that can mention "guilt". I can embed everything and all the other sources for cheap, I just literally don't have the money.
Subscribe to:
Comments (Atom)