martianlantern
Re:I poisoned a Hugging Face dataset and it stayed up for 6 months
on Saturday May 23, 2026 @10:59AM (#48248276)
This is not something to taunt about
Re:Website streamed live directly from a model
on Wednesday April 22, 2026 @03:24PM (#47868101)
Cool project, but just a side thought I was having about how do people have resources and the money to make things like this and make it avl for public, I mean it's fair to say they have their own GPUs or if they are using api keys for gpt or Gemini with enterprise subsidized inference
But still coming from a frugal background I still cannot wrap my head around this
Re:Show HN: Tsplat – Render Gaussian Splats directly in your terminal
on Tuesday April 14, 2026 @03:04AM (#47762222)
Very nice! I found the tutorial on gaussian splatting to be very neatly written and educational
Re:Copilot Edited an Ad into My PR
on Monday March 30, 2026 @01:35AM (#47570736)
Why are they doing this?
Re:Show HN: I trained a 9M speech model to fix my Mandarin tones
on Saturday January 31, 2026 @01:30AM (#46834034)
Nice! I need something similar for english now
Re:Qwen3-ASR and Qwen3-ForcedAligner Is Now Open Sourced
on Friday January 30, 2026 @02:35AM (#46821541)
I am awaiting for a full duplex model from qwen team
Strassen's Matmul with AVX 512
Re:Show HN: Sweep, Open-weights 1.5B model for next-edit autocomplete
on Thursday January 22, 2026 @12:20AM (#46715619)
This is cool! I am more interested in how you guys generated next edit training data from repos, seems like there are lots of caveats here. Would love your insights
Again amazing work! waiting for what you guys cook next
Re:Ask HN: Could you share your personal website here?
on Wednesday January 14, 2026 @10:51PM (#46627805)
my site: https://martianlantern.github.io/
Re:Context7 Without Context Bloat
on Tuesday January 13, 2026 @02:22AM (#46598158)
I liked the new approach but I don't like the pseudo security framing. I don't see how an LLM rewritten query is secure than just sending my raw query, in both cases I don't feel secure at all
System Design Interview: An insider's guide (Alex Xu) [pdf]
Re:I built an interactive SHA-256 visualizer
on Monday January 12, 2026 @09:29AM (#46588993)
Cool! but it would be more educational if it explained each step and it's reasoning
Re:Ask HN: What Are You Working On? (January 2026)
on Sunday January 11, 2026 @12:01PM (#46577418)
If I am missing something, isn't this the whole purpose of hacker news to be a link aggregator for technical/developers?
Re:You probably don't need Oh My Zsh
on Saturday January 10, 2026 @01:23AM (#46563302)
I have given up on any external bash configurator a long time ago, instead I write my own bash prompts these days, they lack a lot of functionalities but I am much happy with them for now, also a shameless plug:
https://martianlantern.github.io/2025/11/updating-my-bash-pr...
3 Months of Using Neovim
Fail Faster on Your Idea
Fail Faster on Your Ideas
Re:Show HN: ssh tiny.christmas
on Thursday December 25, 2025 @08:16AM (#46384234)
would be great if there was a chat room where we can also chat with all the other people in the lobby :)
Distilling persona vectors into LLM weights
Re:Orchids – The Vibe Coding IDE
on Tuesday December 09, 2025 @11:54PM (#46214225)
damn
Fast Median Filter over arbitrary datatypes
Updating My Bash Prompt
How to Establish SSH over Tor
Median Filter over Arbitrary Datatypes
Re:1D Conway's Life glider found, 3.7B cells long
on Wednesday December 03, 2025 @12:30PM (#46137332)
Wow this seems very interesting! Can we get a TLDR of how this was achieved?
Re:Thoughtbubbles: An Unsupervised Method for Parallel Thinking in Lat...
on Friday October 03, 2025 @02:08PM (#45465912)
This is awesome! It reminds me of this
https://github.com/lucidrains/self-reasoning-tokens-pytorch
Show HN: Python Asyncio Puzzles
Re:Large Language Muddle
on Friday October 03, 2025 @04:10AM (#45460339)
The article itself seems to be AI slop, too many em dashes ...