Fireworks AI

Engineering blog · fireworks.ai/blog

Watch

48posts0this week0watchers

WatchOpen blog (opens in a new tab)

Fireworks AIBlog1w

Reinforcement learning: Why alignment of numerics and MoE routing matter

Fireworks AIBlog2w

Fireworks AI

Fireworks AIBlog2w

Every byte counts: ARCv3 and the case for cross-region RL

Fireworks AIBlog2w

Introducing Ember-1

Fireworks AIBlog3w

The frontier isn’t a model. It’s a router.

Fireworks AIBlog3w

Phylo brings frontier AI to more scientists with open models on Fireworks

Fireworks AIBlog4w

DeepSeek-V4.1-Flash on Fireworks: Astra-level DeepSWE at 1/15th the cost

Fireworks AIBlog4w

Gen-1 Slides: Opus 5-level decks at a fraction of the cost

Fireworks AIBlog31 Aug

Training API now generally available | Fireworks

Fireworks AIBlog26 Aug

DeepSeek V4 Pro: Tops SWE-Bench & Cuts Cost per Task by 3x vs. Fable 5

Fireworks AIBlog26 Aug

Fireworks AI

Fireworks AIBlog26 Aug

Post-training Kimi K3 with Harvey for long-horizon legal work

Fireworks AIBlog12 Aug

Can open models carry readable silent signals before they speak? Reproducing J-Lens Readouts on Kimi K3 & Qwen3.5-9B

Fireworks AIBlog10 Aug

Fireworks AI

Fireworks AIBlog5 Aug

Your AI Performance Stack is Fireworks Models with Voyage AI embeddings

Fireworks AIBlog30 Jul

Three Tests to Run Before You Switch from LoRA to FullFT

Fireworks AIBlog29 Jul

Fine-Tune Your Own Embedding Model from an LLM — for the Price of a Coffee

Fireworks AIBlog27 Jul

Kimi K3 on Fireworks: Frontier Intelligence You Can Own

Fireworks AIBlog26 Jul

Fireworks AI

Fireworks AIBlog26 Jul

Trilogy’s Playbook for Open-Weight Cybersecurity with Kimi K3

Showing the newest 39 of 48 posts. Browse by feature trail