NewsWorld
PredictionsDigestsScorecardTimelinesArticles
NewsWorld
HomePredictionsDigestsScorecardTimelinesArticlesWorldTechnologyPoliticsBusiness
AI-powered predictive news aggregation© 2026 NewsWorld. All rights reserved.
Trending
MilitaryTrumpStrikesMajorFebruaryIranAnnouncesMarketTariffsAdditionalIranianNewsDigestSundayTimelineUkraineNuclearTargetingGamePrivateEnergyTradeYearsHumanoid
MilitaryTrumpStrikesMajorFebruaryIranAnnouncesMarketTariffsAdditionalIranianNewsDigestSundayTimelineUkraineNuclearTargetingGamePrivateEnergyTradeYearsHumanoid
All Articles
Hacker News
Clustered Story
Published 7 days ago

Show HN: Microgpt is a GPT you can visualize in the browser

Hacker News · Feb 15, 2026 · Collected from RSS

Summary

very much inspired by karpathy's microgpt of the same name. it's (by default) a 4000 param GPT/LLM/NN that learns to generate names. this is sorta an educational tool in that you can visualize the activations as they pass through the network, and click on things to get an explanation of them. Comments URL: https://news.ycombinator.com/item?id=47026186 Points: 44 # Comments: 2

Share this story
Read Original at Hacker News

Related Articles

Hacker News6 days ago
Show HN: Andrej Karpathy's microgpt.py to C99 microgpt.c – 4,600x faster

Andrej Karpathy showed us the GPT algorithm. I wanted to see the hardware limit. The Punchline: I made it go 4,600x faster in pure C code, no dependencies and using a compiler with SIMD auto-vectorisation!!! Andrej recently released microgpt.py - a brilliant, atomic look at the core of a GPT. As a low-latency developer, I couldn't resist seeing how fast it could go when you get closer to the metal. So just for funzies, I spent a few hours building microgpt-c, a zero-dependency and pure C99 implementation featuring: - 4,600x Faster training vs the Python reference (Tested on MacBook Pro M2 Max). On Windows, it is 2,300x faster. - SIMD Auto-vectorisation for high-speed matrix operations. - INT8 Quantisation (reducing weight storage by ~8x). Training is slightly slower, but the storage reduction is significant. - Zero Dependencies - just pure logic. The amalgamation image below is just for fun (and to show off the density!), but the GitHub repo contains the fully commented, structured code for anyone who wants to play with on-device AI. I have started to build something useful, like a simple C code static analyser - I will do a follow-up post. Everything else is just efficiency... but efficiency is where the magic happens Comments URL: https://news.ycombinator.com/item?id=47042014 Points: 31 # Comments: 1

Hacker Newsabout 8 hours ago
We hid backdoors in ~40MB binaries and asked AI + Ghidra to find them

Article URL: https://quesma.com/blog/introducing-binaryaudit/ Comments URL: https://news.ycombinator.com/item?id=47111440 Points: 14 # Comments: 2

Hacker Newsabout 8 hours ago
Man accidentally gains control of 7k robot vacuums

Article URL: https://www.popsci.com/technology/robot-vacuum-army/ Comments URL: https://news.ycombinator.com/item?id=47111400 Points: 16 # Comments: 1

Hacker Newsabout 9 hours ago
Iran students stage first large anti-government protests since deadly crackdown

Article URL: https://www.bbc.com/news/articles/c5yj2kzkrj0o Comments URL: https://news.ycombinator.com/item?id=47111067 Points: 25 # Comments: 4

Hacker Newsabout 9 hours ago
I put New Zealand behind a $1 paywall

Article URL: https://rename.world/ Comments URL: https://news.ycombinator.com/item?id=47111042 Points: 22 # Comments: 4

Hacker Newsabout 9 hours ago
Volatility: The volatile memory forensic extraction framework

Article URL: https://github.com/volatilityfoundation/volatility3 Comments URL: https://news.ycombinator.com/item?id=47110781 Points: 3 # Comments: 0