Introducing SWE-1.5: Our Fast Agent Model
simonwillison.netยท17h
๐Ÿ”’WASM Capabilities
Flag this post
Bots, Bread and the Battle for the Web
unit42.paloaltonetworks.comยท1d
๐Ÿ“ŠFeed Optimization
Flag this post
Wikipedia says AI answers are starting to take a bite. There are reasons to be worried.
businessinsider.comยท29m
๐Ÿค–AI Curation
Flag this post
Kilo for Cursor Refugees Program
blog.kilocode.aiยท18hยท
Discuss: Hacker News
๐Ÿ“กRSS Automation
Flag this post
Why 80% of Brands Disappear by Prompt Three โ€“ and How to Measure If You're One
aivojournal.orgยท3dยท
Discuss: Hacker News
๐ŸŽฏRecommendation Metrics
Flag this post
Migrating Whop from PostgreSQL to PlanetScale MySQL with 0 downtime
evilmartians.comยท2dยท
Discuss: Hacker News
๐Ÿ—„๏ธPostgreSQL WAL
Flag this post
Freephdlabor: Customizable multiagent research automation system
freephdlabor.github.ioยท13hยท
Discuss: Hacker News
๐Ÿ“„Document Digitization
Flag this post
The influence of the random numbers quality on the results in stochastic simulations and machine learning
arxiv.orgยท13h
๐ŸŒธBloom Variants
Flag this post
GRAPHIA: Harnessing Social Graph Data to Enhance LLM-Based Social Simulation
arxiv.orgยท1d
๐Ÿ•ธ๏ธKnowledge Graphs
Flag this post
Can LLMs Write Faithfully? An Agent-Based Evaluation of LLM-generated Islamic Content
arxiv.orgยท1d
โšกProof Automation
Flag this post
VOGUE: A Multimodal Dataset for Conversational Recommendation in Fashion
arxiv.orgยท3d
๐Ÿ›Digital humanities
Flag this post
Gaperon: A Peppered English-French Generative Language Model Suite
arxiv.orgยท13h
โš™๏ธCompression Benchmarking
Flag this post
Retrieval-augmented generation can manage expectations of AI
techradar.comยท7h
๐ŸŒCultural Algorithms
Flag this post
Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders
arxiv.orgยท13h
๐Ÿง Machine Learning
Flag this post
Unlocking Developer Revenue: AI Monetization with Dual Earnings for LLM Apps
dev.toยท3hยท
Discuss: DEV
๐Ÿค–AI Curation
Flag this post