Why LLMs cannot reach GenAI, but why it looked like they could
haversine.substack.com·1h·
Discuss: Substack
🧠Intelligence Compression
Slip – A Lisp System in JavaScript
lisperator.net·10h·
Discuss: Hacker News
🔗Lisp
A Proof of the Riemann Hypothesis
dev.to·1d·
Discuss: DEV
⚔️Lean Theorem
A very short, very blunt, book note
logicmatters.net·4d
⚔️Lean Theorem
Let’s Make a Tic-Tac-Deal!
thefiddler.substack.com·11h·
Discuss: Substack
🎯Proof Tactics
Is ChatGPT-5 Able to Provide Proofs for Advanced Mathematics?
machinelearningmastery.com·3d
🎯Proof Tactics
Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention
huggingface.co·1d·
Discuss: Hacker News
📊Learned Metrics
BQN "Macros" with •Decompose (2023)
saltysylvi.github.io·1h·
Discuss: Hacker News
🦀Rust Macros
LINQ and Learning to Be Declarative
nickstambaugh.dev·1d·
Discuss: Hacker News
🔗Concatenative Programming
Show HN: Comparegpt.io – Trustworthy Mode to reduce LLM hallucinations
news.ycombinator.com·22h·
Discuss: Hacker News
🔍BitFunnel
Experimenting with ACL2 and Claude Code
mikedodds.org·11h·
Discuss: Hacker News
👑Isabelle
Atomic and Saturated Models
functor.network·6d·
Discuss: Hacker News
🔢Denotational Semantics
The Day I Hacked XCTrack
blog.syrac.org·9h·
Discuss: Hacker News
🔐PKI Archaeology
Vexing Exceptions
ericlippert.com·20h·
Discuss: Hacker News
🧪Binary Fuzzing
GHC Developer Blog: GHC 9.14.1-alpha3 is now available
haskell.org·1d
🔗Functional Compilers
Debugging Humidity: Lessons from deploying software in the physical world
physical-ai.ghost.io·3h·
Discuss: Hacker News
🛡️Error Boundaries
Evaluating Gemini 2.5 Deep Think's math capabilities
epoch.ai·10h·
Discuss: Hacker News
🎯Performance Proofs
Writing an LLM from scratch, part 21 – perplexed by perplexity
gilesthomas.com·3d·
Discuss: Hacker News
🧠Intelligence Compression
Erlang-Red Walkthrough – Visual FBP for Telecom: Diameter AAA on Erlang/OTP
blog.tadsummit.com·9h·
Discuss: Hacker News
🌐Protocol Synthesis