Honey's Dieselgate: Detecting and tricking testers
364 by AkshatJ27 | 159 comments on Hacker News.
Wednesday, 31 December 2025
Tuesday, 30 December 2025
New best story on Hacker News: Show HN: 22 GB of Hacker News in SQLite
Show HN: 22 GB of Hacker News in SQLite
391 by keepamovin | 136 comments on Hacker News.
Community, All the HN belong to you. This is an archive of hacker news that fits in your browser. When I made HN Made of Primes I realized I could probably do this offline sqlite/wasm thing with the whole GBs of archive. The whole dataset. So I tried it, and this is it. Have Hacker News on your device. Go to this repo ( https://ift.tt/X6yDnIf ): you can download it. Big Query -> ETL -> npx serve docs - that's it. 20 years of HN arguments and beauty, can be yours forever. So they'll never die. Ever. It's the unkillable static archive of HN and it's your hands. That's my Year End gift to you all. Thank you for a wonderful year, have happy and wonderful 2026. make something of it.
391 by keepamovin | 136 comments on Hacker News.
Community, All the HN belong to you. This is an archive of hacker news that fits in your browser. When I made HN Made of Primes I realized I could probably do this offline sqlite/wasm thing with the whole GBs of archive. The whole dataset. So I tried it, and this is it. Have Hacker News on your device. Go to this repo ( https://ift.tt/X6yDnIf ): you can download it. Big Query -> ETL -> npx serve docs - that's it. 20 years of HN arguments and beauty, can be yours forever. So they'll never die. Ever. It's the unkillable static archive of HN and it's your hands. That's my Year End gift to you all. Thank you for a wonderful year, have happy and wonderful 2026. make something of it.
Monday, 29 December 2025
New best story on Hacker News: Show HN: Z80-μLM, a 'Conversational AI' That Fits in 40KB
Show HN: Z80-μLM, a 'Conversational AI' That Fits in 40KB
400 by quesomaster9000 | 90 comments on Hacker News.
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations with a distinct personality. -- The extreme constraints nerd-sniped me and forced interesting trade-offs: trigram hashing (typo-tolerant, loses word order), 16-bit integer math, and some careful massaging of the training data meant I could keep the examples 'interesting'. The key was quantization-aware training that accurately models the inference code limitations. The training loop runs both float and integer-quantized forward passes in parallel, scoring the model on how well its knowledge survives quantization. The weights are progressively pushed toward the 2-bit grid using straight-through estimators, with overflow penalties matching the Z80's 16-bit accumulator limits. By the end of training, the model has already adapted to its constraints, so no post-hoc quantization collapse. Eventually I ended up spending a few dollars on Claude API to generate 20 questions data (see examples/guess/GUESS.COM), I hope Anthropic won't send me a C&D for distilling their model against the ToS ;P But anyway, happy code-golf season everybody :)
400 by quesomaster9000 | 90 comments on Hacker News.
How small can a language model be while still doing something useful? I wanted to find out, and had some spare time over the holidays. Z80-μLM is a character-level language model with 2-bit quantized weights ({-2,-1,0,+1}) that runs on a Z80 with 64KB RAM. The entire thing: inference, weights, chat UI, it all fits in a 40KB .COM file that you can run in a CP/M emulator and hopefully even real hardware! It won't write your emails, but it can be trained to play a stripped down version of 20 Questions, and is sometimes able to maintain the illusion of having simple but terse conversations with a distinct personality. -- The extreme constraints nerd-sniped me and forced interesting trade-offs: trigram hashing (typo-tolerant, loses word order), 16-bit integer math, and some careful massaging of the training data meant I could keep the examples 'interesting'. The key was quantization-aware training that accurately models the inference code limitations. The training loop runs both float and integer-quantized forward passes in parallel, scoring the model on how well its knowledge survives quantization. The weights are progressively pushed toward the 2-bit grid using straight-through estimators, with overflow penalties matching the Z80's 16-bit accumulator limits. By the end of training, the model has already adapted to its constraints, so no post-hoc quantization collapse. Eventually I ended up spending a few dollars on Claude API to generate 20 questions data (see examples/guess/GUESS.COM), I hope Anthropic won't send me a C&D for distilling their model against the ToS ;P But anyway, happy code-golf season everybody :)
Sunday, 28 December 2025
Saturday, 27 December 2025
New best story on Hacker News: Exe.dev
Exe.dev
426 by achairapart | 279 comments on Hacker News.
https://ift.tt/eMOwPIh https://ift.tt/S4aylij https://ift.tt/zVEqRZL
426 by achairapart | 279 comments on Hacker News.
https://ift.tt/eMOwPIh https://ift.tt/S4aylij https://ift.tt/zVEqRZL
Friday, 26 December 2025
Thursday, 25 December 2025
New best story on Hacker News: Show HN: Vibium – Browser automation for AI and humans, by Selenium's creator
Show HN: Vibium – Browser automation for AI and humans, by Selenium's creator
388 by hugs | 110 comments on Hacker News.
i started the selenium project 21 years ago. vibium is what i'd build if i started over today with ai agents in mind. go binary under the hood (handles browser, bidi, mcp) but devs never see it. just npm install vibium. python/java coming. for claude code: claude mcp add vibium -- npx -y vibium v1 ships today. ama.
388 by hugs | 110 comments on Hacker News.
i started the selenium project 21 years ago. vibium is what i'd build if i started over today with ai agents in mind. go binary under the hood (handles browser, bidi, mcp) but devs never see it. just npm install vibium. python/java coming. for claude code: claude mcp add vibium -- npx -y vibium v1 ships today. ama.
Wednesday, 24 December 2025
New best story on Hacker News: Show HN: CineCLI – Browse and torrent movies directly from your terminal
Show HN: CineCLI – Browse and torrent movies directly from your terminal
325 by samsep10l | 111 comments on Hacker News.
Hi HN I built CineCLI — a cross-platform terminal app to browse movies, view details, and open torrents directly in your system torrent client. Features: - Search movies from the terminal - Rich UI with ratings, runtime, genres - Interactive & non-interactive modes - Magnet handling via system default client - Linux/macOS/Windows support - No ads, no tracking GitHub: https://ift.tt/EibVuXO PyPI: https://ift.tt/cwDJCnm Would love feedback from terminal + Python folks
325 by samsep10l | 111 comments on Hacker News.
Hi HN I built CineCLI — a cross-platform terminal app to browse movies, view details, and open torrents directly in your system torrent client. Features: - Search movies from the terminal - Rich UI with ratings, runtime, genres - Interactive & non-interactive modes - Magnet handling via system default client - Linux/macOS/Windows support - No ads, no tracking GitHub: https://ift.tt/EibVuXO PyPI: https://ift.tt/cwDJCnm Would love feedback from terminal + Python folks
Tuesday, 23 December 2025
Monday, 22 December 2025
Sunday, 21 December 2025
Saturday, 20 December 2025
Friday, 19 December 2025
Thursday, 18 December 2025
New best story on Hacker News: I got hacked: My Hetzner server started mining Monero
I got hacked: My Hetzner server started mining Monero
551 by jakelsaunders94 | 335 comments on Hacker News.
551 by jakelsaunders94 | 335 comments on Hacker News.
New best story on Hacker News: Tell HN: HN was down
Tell HN: HN was down
579 by uyzstvqs | 312 comments on Hacker News.
- HN errored on all authenticated requests with 502 Bad Gateway. It did still respond to a limited amount of unauthenticated requests with presumably cached pages, which did not get updated. The last post on /newest claimed "0 minutes ago", but was actually much older (1:32:57 PM GMT) and not the newest post. - This status page actually identified the outage: https://ift.tt/URt3M9Z - Pages by Hund and Statuspal did not show the outage. - The last post before the outage was https://ift.tt/Jepl5jh (1:39:59 PM GMT). The last comment was https://ift.tt/7JSGh35 (1:41:54 PM GMT). - There was an average of ~4 seconds per comment just prior to the outage. Based on this, HN likely went down at 1:41:58 PM GMT.
579 by uyzstvqs | 312 comments on Hacker News.
- HN errored on all authenticated requests with 502 Bad Gateway. It did still respond to a limited amount of unauthenticated requests with presumably cached pages, which did not get updated. The last post on /newest claimed "0 minutes ago", but was actually much older (1:32:57 PM GMT) and not the newest post. - This status page actually identified the outage: https://ift.tt/URt3M9Z - Pages by Hund and Statuspal did not show the outage. - The last post before the outage was https://ift.tt/Jepl5jh (1:39:59 PM GMT). The last comment was https://ift.tt/7JSGh35 (1:41:54 PM GMT). - There was an average of ~4 seconds per comment just prior to the outage. Based on this, HN likely went down at 1:41:58 PM GMT.
Wednesday, 17 December 2025
New best story on Hacker News: Gemini 3 Flash: Frontier intelligence built for speed
Gemini 3 Flash: Frontier intelligence built for speed
644 by meetpateltech | 296 comments on Hacker News.
Docs: https://ift.tt/i2McQo6 Developer Blog: https://ift.tt/JivmnES... Model Card [pdf]: https://ift.tt/2K7kCO5 Gemini 3 Flash in Search AI mode: https://ift.tt/8W3rMlb... Deepmind Page: https://ift.tt/gTofIGJ
644 by meetpateltech | 296 comments on Hacker News.
Docs: https://ift.tt/i2McQo6 Developer Blog: https://ift.tt/JivmnES... Model Card [pdf]: https://ift.tt/2K7kCO5 Gemini 3 Flash in Search AI mode: https://ift.tt/8W3rMlb... Deepmind Page: https://ift.tt/gTofIGJ
Tuesday, 16 December 2025
Monday, 15 December 2025
Sunday, 14 December 2025
Saturday, 13 December 2025
Friday, 12 December 2025
Thursday, 11 December 2025
New best story on Hacker News: GPT-5.2
GPT-5.2
401 by atgctg | 295 comments on Hacker News.
https://ift.tt/X7zkFWh System card: https://ift.tt/K41XmgN...
401 by atgctg | 295 comments on Hacker News.
https://ift.tt/X7zkFWh System card: https://ift.tt/K41XmgN...
New best story on Hacker News: Rubio stages font coup: Times New Roman ousts Calibri
Rubio stages font coup: Times New Roman ousts Calibri
374 by italophil | 645 comments on Hacker News.
https://ift.tt/EQMbTvF
374 by italophil | 645 comments on Hacker News.
https://ift.tt/EQMbTvF
Wednesday, 10 December 2025
New best story on Hacker News: Valve: HDMI Forum Continues to Block HDMI 2.1 for Linux
Valve: HDMI Forum Continues to Block HDMI 2.1 for Linux
621 by OsrsNeedsf2P | 341 comments on Hacker News.
621 by OsrsNeedsf2P | 341 comments on Hacker News.
New best story on Hacker News: Australia begins enforcing world-first teen social media ban
Australia begins enforcing world-first teen social media ban
581 by chirau | 943 comments on Hacker News.
https://ift.tt/VXkzeun https://ift.tt/bGUyk3J https://ift.tt/roWhTOR... ( https://ift.tt/sQ7hrcn )
581 by chirau | 943 comments on Hacker News.
https://ift.tt/VXkzeun https://ift.tt/bGUyk3J https://ift.tt/roWhTOR... ( https://ift.tt/sQ7hrcn )
Tuesday, 9 December 2025
New best story on Hacker News: Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
Ask HN: Should "I asked $AI, and it said" replies be forbidden in HN guidelines?
495 by embedding-shape | 290 comments on Hacker News.
As various LLMs become more and more popular, so does comments with "I asked Gemini, and Gemini said ....". While the guidelines were written (and iterated on) during a different time, it seems like it might be time to have a discussion about if those sort of comments should be welcomed on HN or not. Some examples: - https://ift.tt/bRNcxBq - https://ift.tt/Zl5amEx - https://ift.tt/PNblUx9 Personally, I'm on HN for the human conversation, and large LLM-generated texts just get in the way of reading real text from real humans (assumed, at least). What do you think? Should responses that basically boil down to "I asked $LLM about $X, and here is what $LLM said:" be allowed on HN, and the guidelines updated to state that people shouldn't critique it (similar to other guidelines currently), or should a new guideline be added to ask people from refrain from copy-pasting large LLM responses into the comments, or something else completely?
495 by embedding-shape | 290 comments on Hacker News.
As various LLMs become more and more popular, so does comments with "I asked Gemini, and Gemini said ....". While the guidelines were written (and iterated on) during a different time, it seems like it might be time to have a discussion about if those sort of comments should be welcomed on HN or not. Some examples: - https://ift.tt/bRNcxBq - https://ift.tt/Zl5amEx - https://ift.tt/PNblUx9 Personally, I'm on HN for the human conversation, and large LLM-generated texts just get in the way of reading real text from real humans (assumed, at least). What do you think? Should responses that basically boil down to "I asked $LLM about $X, and here is what $LLM said:" be allowed on HN, and the guidelines updated to state that people shouldn't critique it (similar to other guidelines currently), or should a new guideline be added to ask people from refrain from copy-pasting large LLM responses into the comments, or something else completely?
Monday, 8 December 2025
Sunday, 7 December 2025
Saturday, 6 December 2025
New best story on Hacker News: We gave 5 LLMs $100K to trade stocks for 8 months
We gave 5 LLMs $100K to trade stocks for 8 months
383 by cheeseblubber | 301 comments on Hacker News.
383 by cheeseblubber | 301 comments on Hacker News.
