Ask HN: Are LLMs Solving Math?
Are LLM agents solving all known math problems from low to high complexity consistently now or are LLMs "only" synthesizing solutions for ripe problems given humanities current math knowledge?
sean_pedersen
Re:I know why Mathematicians weep
on Thursday October 15, 2026 @12:45PM (#50106380)
Ok what about memory systems though (basically LLM modifies its own RAG context) - that should allow commits and changing dispositions over time?
Re:JevBench, a reproducible benchmark for typed decision models
on Tuesday September 22, 2026 @05:37PM (#49808495)
Good project but this one also exists https://huggingface.co/spaces/multimodalart/jev-decision-ind... and the results do not seem to add up and also model sets are different... still needs time to mature likely
Re:Bonsai 2 27B: Near-Lossless Compression in a 9x Smaller Footprint
on Friday September 18, 2026 @12:23AM (#49750164)
Try a MoE model like Qwen3.6 35B-A3B for better tok/s
Re:Google Is Making Private AI Practical with Homomorphic Encryption
on Friday August 14, 2026 @03:25PM (#49303465)
There are LLM models which compute only using addition no?
Show HN: VS Code Extension – Semantic Code Search (Semble)
Re:What happens if you put work into the second dimension?
on Wednesday August 05, 2026 @07:03PM (#49190257)
Just gave it a spin and feels very rough / unpolished.
- Why is the default scroll wheel action panning vertically and not zooming in and out (the main interaction)?
- Why is the app size 1GB?
- Everything feels clunky / not native - these are not my real apps.
This would need a lot of work to feel frictionless but I like the concept.
Re:What happens if you put work into the second dimension?
on Wednesday August 05, 2026 @06:54PM (#49190165)
Looks very interesting - is it open-source yet?
Re:How we measured AI writing across arXiv, and where the measurement ...
on Monday July 20, 2026 @07:59PM (#48986451)
"Any attempt to build AI generated content (deep fake) detection systems is flawed, since the outputs of such a system may be used to train an even better fake data generator. This leads to an equilibrium state of digital uncertainty: nothing in the digital realm can be deemed as real anymore - only as digital. I do not care if a digital artifact is human or AI made - I only care if it is useful to me. Useful content is on point, factual and at best surprising (teaches something new)." - https://seanpedersen.github.io/posts/digital-uncertainty/
Re:Ask HN: Add flag for AI-generated articles
on Monday July 13, 2026 @07:44AM (#48891176)
It is not about AI generated or not, it is and always has been about quality of the content. So just let the people up- / downvote.
Re:Ask HN: What Are You Working On? (July 2026)
on Sunday July 12, 2026 @06:24PM (#48885481)
Digger Solo - a smart file explorer with semantic search and maps for your files (images, videos, text, audio). All running locally on your machine.
Re:Show HN: Write SaaS apps where users control where their data is st...
on Thursday June 25, 2026 @01:01AM (#48669125)
Please explain in simple words what it is and does. Is user data stored unencrypted on your servers?
Show HN: Digger Solo – Local AI File Explorer
After a lot of work I present Digger Solo 0.5.0 - the AI file explorer that respects your privacy (everything runs locally).Demo video: https://vimeo.com/1198414414New features: - LLM Chat with RAG (bring your own OpenAI compatible API key - ideally host a local model) - fresh redesign with light theme available in settings - multi-tabbed GUI: open multiple semantic maps at once - smart music...
Re:The bootstrapper's EU stack for under €10 per month
on Monday May 25, 2026 @05:29PM (#48271878)
as long as the text is not slop (no hallucinations / factual) and useful to me, I do not care about the author of it
AI Safety Farce
Re:Show HN: Now I Get It – Translate scientific papers into interactiv...
on Saturday February 28, 2026 @11:38AM (#47197364)
very cool! would be useful if headings where linkable using anchor
Re:Pi – a minimal terminal coding harness
on Tuesday February 24, 2026 @08:23PM (#47146089)
There is a Rust port: https://github.com/Dicklesworthstone/pi_agent_rust
Re:Show HN: Lightwave – Real-time notes app, 3.5 years of hand-rolled ...
on Sunday February 15, 2026 @05:17PM (#47028229)
The test acc. UX flow is shit IMHO: I do not want to see the first user tips (just annoying flashes) and I can not directly edit the first doc I see.
Re:Ask HN: Could you share your personal website here?
on Wednesday January 14, 2026 @05:36PM (#46624843)
Re:Show HN: Ferrite – Markdown editor in Rust with native Mermaid diag...
on Sunday January 11, 2026 @12:39AM (#46572985)
Like the idea but it spawns a terminal on startup on Mac and is not WYSIWYG (like Obsidian). Hope this project develops into usable state soon.
Re:Finding and Fixing Ghostty's Largest Memory Leak
on Saturday January 10, 2026 @10:44PM (#46572526)
Would this kind of bug have been catched by the Rust compiler?
Re:Some people can't see mental images
on Thursday October 30, 2025 @05:58PM (#45765895)
By this reasoning aphantasiacs should be incapable of drawing anything from their mind.
Digital Security for Everyone
YouTube Transcription MCP Server
Popping the AGI Bubble
Re:Irrelevant facts about cats added to math problems increase LLM err...
on Wednesday July 30, 2025 @09:44AM (#44734110)
Link to the OG paper: https://arxiv.org/abs/2503.01781
Show HN: Digger Solo – Semantic Search and Maps for Local Files
Hey, I am Sean and I built Digger Solo - a privacy respecting file explorer from the "future". The core features are semantic file search and interactive data maps allowing to explore your files with ease. All processing happens locally - your files never leave your machine.The file search works by combining full text search with semantic search allowing to search for content of text and image...
Show HN: Digger Solo – Semantic File Search and Maps
I built Digger Solo a privacy respecting file explorer from the future. The core features are semantic file search and interactive data maps allowing to explore your files with ease. All processing happens locally - your files never leave your machine.The file search works by combining full text search with semantic search allowing to search for content of text and image files by their meaning...
Zipf's Law
Re:Curl takes action against time-wasting AI bug reports
on Thursday May 08, 2025 @08:59PM (#43932861)
Maybe fight fire with fire and respond as default with a non-sensical question and see if the bug reporter responds genuinely confused or happily tries to engage in a non-sense convo…