Bret Taylor: The AI Architect https://
latent.space/p/bret Presenting our conversations with @btaylor
, the legendary CEO of @SierraPlatform
, Chairman of @OpenAI
, and creator of Google Maps/Facebook Likes on the future of Software Engineering, and building great products and teams
@latentspacepod
-
Bret Taylor: The AI Architect and Software Engineering Future
By
–
-
The AI Engineer Lifecycle: Next in Series
By
–
next in this series – the AI Engineer lifecycle https://t.co/5HQ0mTV1Dg
— Latent.Space (@latentspacepod) 8 février 2025next in this series – the AI Engineer lifecycle
-
Pydantic AI: Agent Engineering with Graphs and Tools
By
–
Agent Engineering with Pydantic + Graphs https://
latent.space/p/pydantic with @samuelcolvin
! We've heard from @jxnlco 3 years running that @Pydantic Is All We Need, and this is even more true today with the launch of Pydantic AI! With a little @marimo_io love at the end 🙂 -
LLM Gateway: Simplifying 100 AI Engineering Decisions
By
–
🆕 LLM Gateway: The One Decision That Removes 100 AI Engineering Decisions
— Latent.Space (@latentspacepod) 6 février 2025
quick pod/post ft @PortkeyAI @jumbld ! https://t.co/5HQ0mTV1Dg pic.twitter.com/ltjTSIJeTiLLM Gateway: The One Decision That Removes 100 AI Engineering Decisions quick pod/post ft @PortkeyAI @jumbld !
-
Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas
By
–
The Agent Reasoning Interface: o1/o3, Claude 3, ChatGPT Canvas, Tasks, and Operator ft @karinanguyen who is teasing her keynote at @aiDotEngineer Timestamps •00:11 Introducing Karina Nguyen
•02:21 Karina's Journey to OpenAI
•04:45 Early Prototypes and Projects
•05:25 -
DeepSeek’s price pressure forces OpenAI to cut o1-mini costs
By
–
## DeepSeek's impact on o3-mini and o1-mini buried in today's announcement is a 63% (2.7x) price cut for o1 mini – and o3-mini is priced the same. This is much lower than the 25x price cut needed/predicted to match the DeepSeek R1/v3 price curve. In other words, the "USA x.com/latentspacepod…
-
AI Engineers Achieve Total Victory Consensus
By
–
total victory of the ai engineer cant believe this is consensus now
-
Production AI Engineering Starts with Evals
By
–
"Why does Production AI Engineering start with Evals?"
— Latent.Space (@latentspacepod) 28 janvier 2025
the AI Engineer SDLC, silly
next in our @lizziepika lightboard series of short explainers (again, need to reshoot with better markers and idea of where the camera ends, but just trying out this new format)
h/t to @doppenhe… https://t.co/4TSaiWOAJc pic.twitter.com/ED2nFmL8Ke"Why does Production AI Engineering start with Evals?" the AI Engineer SDLC, silly next in our @lizziepika lightboard series of short explainers (again, need to reshoot with better markers and idea of where the camera ends, but just trying out this new format) h/t to @doppenhe
-
Building Custom Tools with OpenAI o1 for SWE-Bench
By
–
🆕 short pod – how @shawnup got SOTA SWE-Bench Verified
— Latent.Space (@latentspacepod) 28 janvier 2025
with @openai o1… by building his own tools (on @weights_biases Weave) to look at data! https://t.co/clyqvZNhHQ pic.twitter.com/ALmUSSAjiJshort pod – how @shawnup got SOTA SWE-Bench Verified with @openai o1… by building his own tools (on @wandb Weave) to look at data!