Latent.Space

🆕 Presenting: The 2025 AI Engineering Reading List latent.space/p/2025-papers 1 paper/blog/model family per week for every week of 2025, for you to run paper clubs or binge over the break.

On @latentspacepod with @polynoamial he dropped that banger quote and I’ve been obsessed with the onboarding problem for coding agents since. Really resonated with me.

Interesting dive into the LLM application layer in a recent @latentspacepod on @cline. What will the spectrum of coding aids look like? Will MCPs take over search (and anything else apart from the orchestrating LLM)? podcasts.apple.com/de/podcast/lat…

ChatGPT users are spoiled, but tbh everyone else is lacking at the same time. Firstly its no secret that reasoning models need loads of context - read "God Is Hungry For Context" by @latentspacepod for every other AI you need to frontload a ton of context every single time you…

Hear @GregKamradt talk about ARC-AGI-3 with @swyx and @FanaHOVA on @latentspacepod * Why interactive benchmarks? * Defining Intelligence * Play through of ARC-AGI-3 games

i've been looking for "brainrot education" for the gen alphas and someone finally sent me a channel that translates @dexhorthy and @RLanceMartin's content for those who are of deficit in attention this channel is 8 weeks old and has 22k followers x.com/latentspacepod…

Want to hear about Agent Leaderboard v2 directly from the AI Engineer behind it all? 🧑‍💻 @ptkbhv went on the @latentspacepod to talk about this update with @swyx and @FanaHOVA, listen here: youtube.com/watch?v=Mp0gxU…

Best AI related podcasts you have listened to?

HUGE news for game developers: On the latest episode of @latentspacepod, it was revealed that @cline, the open-source AI coding agent for VSCode, is actively working on JetBrains integration. This is massive for Unity (C#) and Unreal Engine (C++), which both prefer JetBrains IDEs

Today's LS paper club will be on Muon, the new optimizer behind @Kimi_Moonshot K2! join in 2 hours: lu.ma/j3yxf6bp

New @latentspacepod with @speak is pretty timely, @swyx’s prodding on the conversational onboarding approach and efficacy. Still exploring and experimenting, for SMS, in @givecareapp. As always…how to build scaffolding that scales with new models, price and compute.

Even if AI translation has zero latency and therefore there is no *point* in learning because we can all communicate through a babelfish device... "In German, for example, the verb comes at the end so the minimum latency is the whole sentence" - @adhsu on @latentspacepod…

I really enjoyed this discussion and love what @adhsu and Speak are doing with language learning. We’re approaching fully automated on-demand language learning over voice.