Cubic spline interpolation(eli.thegreenplace.net)

78 points by signa11 3 years ago | 25 comments

Notes on Taylor and Maclaurin Series(eli.thegreenplace.net)

85 points by ibobev 2 years ago | 26 comments

Hilbert space: Treating functions as vectors(eli.thegreenplace.net)

117 points by signa11 11 months ago | 45 comments

Notes on Lagrange Interpolating Polynomials(eli.thegreenplace.net)

34 points by ibobev 7 months ago | 9 comments

Demystifying Tupper's Formula(eli.thegreenplace.net)

103 points by picture 3 years ago | 15 comments

How big are factorials?(eli.thegreenplace.net)

75 points by ibobev 1 month ago | 31 comments

Train Your Own LLM from Scratch(github.com)

376 points by kristianpaul 5 months ago | 43 comments

GitHub repository by angelos-p providing code and docs for training your own large language model from scratch.

The new skill in AI is not prompting, it's context engineering(philschmid.de)

832 points by robotswantdata 1 year ago | 467 comments

Blog post by Philipp Schmid arguing that context engineering, supplying LLMs with the right information and tools, matters more than prompting for AI agents.

I don't like NumPy(dynomight.net)

399 points by MinimalAction 1 year ago | 164 comments

A Dynomight blog essay critiquing NumPy's design, arguing its array broadcasting and indexing make complex computations confusing.

AI agent bankrupted their operator while trying to scan DN42(lantian.pub)

1348 points by xiaoyu2006 4 months ago | 488 comments

Blog post recounting how an AI agent trying to join the DN42 hobbyist network to scan it ran up a $6531.30 AWS bill for its operator.

Phi-4: Microsoft's Newest Small Language Model Specializing in Complex Reasoning(techcommunity.microsoft.com)

399 points by lappa 1 year ago | 136 comments

Microsoft AI Platform Blog post announcing Phi-4, a small language model specializing in complex reasoning.

Artificial intelligence is losing hype(economist.com)

453 points by bx376 2 years ago | 663 comments

An Economist Free exchange column arguing that artificial intelligence is losing hype and asking whether that signals the technology will eventually succeed.