Community post
Clean up Claude 5's token vomit with a separate LLM. Save your tokens, Claude 5 is hopeless - zachahn/vomit
Clean up Claude 5's token vomit with a separate LLM. Save your tokens, Claude 5 is hopeless - zachahn/vomit Source: github.com/zachahn (197 points, 215 comments) Hacker News discussion
Community post
Intelligence is a very general mental capability that, among other things, involves the ability to reason, plan, solve problems, think abstractly, comprehend complex ideas, learn quickly and learn from experience. It is not merely book learning, a narrow academic skill, or test-taking smarts. Rather, it reflects a broader and deeper capability for comprehending our surroundings-“catching on,” “making sense” of things, or “figuring out” what to do […] Intelligence, so defined, can be measured, and intelligence tests measure it well.
Intelligence is a very general mental capability that, among other things, involves the ability to reason, plan, solve problems, think abstractly, comprehend complex ideas, learn quickly and learn from experience. It is not merely book learning, a narrow...
Community post
TL;DR: I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The biggest improvements came from finding the right MIDI representation, cleaning the training data aggressively, and adding DPO post-training.
TL;DR: I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The biggest improvements came from finding the right MIDI representation, cleaning the training data aggressively, and adding DPO...
Community post
Discussion from Hacker News with 359 points and 217 comments.
Discussion from Hacker News with 359 points and 217 comments. Source: wsj.com (359 points, 217 comments) Hacker News discussion
Community post
Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. This model is free to use. 1,048,576 token context window, maximum output of 131,072 tokens.
Ox Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. This model is free to use. 1,048,576 token context window, maximum output of 131,072 tokens. Source: openrouter.ai (51 points, 38 comments) Hacker News...
Community post
Discussion from Hacker News with 16 points and discuss.
Discussion from Hacker News with 16 points and discuss. Source: aps.org (16 points, discuss) Hacker News discussion
Community post
In biology class, biology wasn't presented as a quest for the secrets of life. The textbooks wrung out the questing.
In biology class, biology wasn't presented as a quest for the secrets of life. The textbooks wrung out the questing. Source: jsomers.net (204 points, 78 comments) Hacker News discussion
Community post
A compromised release of the popular Rust crate arrayref pulled in a typosquatted proc-macro1 whose build script downloads and runs a remote binary at compile…
A compromised release of the popular Rust crate arrayref pulled in a typosquatted proc-macro1 whose build script downloads and runs a remote binary at compile… Source: safedep.io (413 points, 373 comments) Hacker News discussion
Everyone, deep in their hearts, is waiting for the end of the world to come.
WebNovare is where clarity meets curiosity — a space for stories that matter without chasing hype. Inspired by voices like NCCapital, we aim to elevate conversation through discipline, insight, and everyday wisdom.
New posts in your reader.
