Anthropic builds RAG directly into Claude models with new Citations API New feature allows Claude to reference source documents and reduce hallucinations.

Anthropic builds RAG directly into Claude models with new Citations API buff.ly/3WuN4W3

"Anthropic announced Citations, a new API feature that helps Claude models avoid confabulations (also called hallucinations) by linking their responses directly to source documents."

#genAI #LLMs

Writing an LLM from scratch, part 1 Learning how to build a large language model from scratch, following Sebastian Raschka's book 'Build a Large Language Model (from Scratch)'. Part 1/??

www.gilesthomas.com/2024/12/llm-...

pluralistic.net/2024/11/02/u...

GitHub - microsoft/ai-agents-for-beginners: 10 Lessons to Get Started Building AI Agents 10 Lessons to Get Started Building AI Agents. Contribute to microsoft/ai-agents-for-beginners development by creating an account on GitHub.

github.com/microsoft/ai...

Ruby on Rails on WebAssembly, the full-stack in-browser journey  |  web.dev Ruby on Rails' famous blog in 15 minutes now runs right in your browser thanks to WebAssembly.

web.dev/blog/ruby-on...

dhruvvidyut.co.in - cool idea and hillerious low budget advertising

o1 isn’t a chat model (and that’s the point) How Ben Hylak turned from ol pro skeptic to fan by overcoming his skill issue.

www.latent.space/p/o1-skill-i... super interesting read on using o1 more as a report generator than as a chat bot

Practical Text-to-SQL for Data Analytics

www.linkedin.com/blog/enginee...

xeiaso.net/notes/2024/b...

www.inferable.ai/blog/posts/p...

Hitting OKRs vs Doing Your Job In Engineering, quarterly OKRs (Objectives & Key Results) can feel like a duplication of product planning. Basically, they say “Ship the Roadmap.” What new information are they comm…

jessitron.com/2025/01/05/h...

How does ChatGPT work: An in-depth look for Programmers A bit about what's going on behind the scenes, in case you probably don't know yet

codedoodles.substack.com/p/how-does-c...

Alignment faking in large language models A paper from Anthropic's Alignment Science team on Alignment Faking in AI large language models

How LLM’s fake alignment with user demand. Interestingly someone else described it to me how llm’s want to please. www.anthropic.com/research/ali...

Facebook's Little Red Book Creating a better digital version

Super interesting how facebook saw itself www.map.cv/blog/redbook

www.greptile.com/blog/make-ll...

On Long Term Software Development - Bert Hubert Recently the Dutch Electoral Board (where I am also a very part time advisor) invited me to do a talk reflecting on their open source Abacus vote tabulation software. Much software is now provided as ...

berthub.eu/articles/pos...

The Software Architecture of Palia Players experience the art and soul that our development team has poured into the game, but the infrastructure that makes it all possible behind the scenes is hidden from view. We are proud of what ou...

"The Software Architecture of Palia" #rustlang

www.singularity6.com/news/softwar...

The FlyWire connectome: neuronal wiring diagram of a complete fly brain Artificial intelligence and human expertise meet to generate a map of all the connections in the fly brain. The resource is already being used by experimentalists and theoreticians to further our unde...

Hard to overstate how pleased I am that the FlyWire consortium converted our FAFB ("Full Adult Fly Brain") EM volume into a connectome, and that the resulting science has been (and will be) so impactful. Thanks to everyone involved. #neuroscience www.nature.com/immersive/d4...

howtomarketagame.com/2021/11/01/d...

Amusing ourselves to death This is perhaps one of the most striking passages I have read for a while. It describes the modern world with startling accuracy. In our fear of an increasingly authoritarian rule, we have allowed …

otpok.com/2014/01/03/a... one of the most deeply unsettling books I know