Search Latent Space

Find your next rabbit hole.

Articles, conversations, profiles, and grounded writeups.

?
Search tips

Keyword matches words; semantic matches meaning and exact titles or names; hybrid combines both. In keyword mode, use quotation marks for exact phrases. Author matches published credits. Year applies to posts; wiki entries have no author or publication year. You can also use author:"Ada" or type:podcast in non-regex searches.

Reset filters

Select Apply filters to update results.

2104 results

WebSim, WorldSim, and The Summer of Simulative AI — with Joscha Bach of Liquid AI, Karan Malhotra of Nous Research, Rob Haisfield of WebSim.aiPodcast · Latent.Space · 2024-04-27PodcastLatent.Space2024-04-27
Together AI

An AI cloud company combining open-model research, inference, fine-tuning and customer-owned model development with distributed GPU infrastructure.

Organization · 2026-09-17
Organization—2026-09-17
Apple's OpenELM beats OLMo with 50% of its dataset, using DeLighTAI News · 2024-04-26AI News—2024-04-26
Together AI: Making Open Models Practical Across the Stack

Together connects data selection, model architecture and GPU systems to lower the cost of building and serving models. Its goal of 5,000 tokens per second reaches beyond faster chat.

Writeup · Date unavailable
Writeup——
Snowflake Arctic: Fully Open 10B+128x4B Dense-MoE Hybrid LLMAI News · 2024-04-26AI News—2024-04-26
Toran Bruce Richards

AutoGPT’s founder described using programming techniques from games to chain language-model predictions, and advocated open source as a way to broaden access to AI.

Person · 2026-09-20
Person—2026-09-20
OpenAI's Instruction Hierarchy for the LLM OSAI News · 2024-04-25AI News—2024-04-25
Training a 70B Model Means Debugging the Whole Stack

The engineering behind reliable clusters, predictable training runs, and evaluations that measure useful coding capabilities.

Writeup · Date unavailable
Writeup——
Perplexity, the newest AI unicornAI News · 2024-04-23AI News—2024-04-23
Training a Million-Token Context Window Is Only the Beginning

Gradient’s context-extension work combines positional scaling, distributed training and carefully constructed data. The harder test is whether a model can use the extra information.

Writeup · Date unavailable
Writeup——
FineWeb: 15T Tokens, 12 years of CommonCrawl (deduped and filtered, you're welcome)AI News · 2024-04-23AI News—2024-04-23
Training IDEFICS: the engineering behind an open multimodal model

How Hugging Face’s M4 team connected pretrained models, built interleaved web data, debugged unstable attention and planned a smaller successor.

Writeup · Date unavailable
Writeup——

Join Latent Space.

Sign in with Google, or get the newsletter by email.

Loading Google sign-in…

or subscribe by email

Free. Change your preferences or unsubscribe any time.

Explore Latent Space Pro Full weekday AINews by email. Support our work.