SYSTEMS - AI Dynamics

Task Serialization and Parallel Execution Strategies

By

–

04 April 2023 6h29

I want to set up task serialization (only do this task after this task), which can then lead to parallel tasks that don’t rely on each other. Curious about your suggested approach

→ View original post on X — @yoheinakajima

4 April 2023

32k Context Length: Exploring AI Capabilities and Risks

By

@yoheinakajima

–

03 April 2023 6h04

If I know anything about us, once we have 32k context length… we’ll think of reasons we need more. But yes, definitely risks w this – tho still a worthy exploration as we better understand these tools.

→ View original post on X — @yoheinakajima

3 April 2023

AI agents dynamically generate new tasks after execution

By

@yoheinakajima

–

03 April 2023 4h28

Yeah, it generates new tasks at the end of each task execution based on the result, after defiling against remaining task list + most relevant past tasks.

→ View original post on X — @yoheinakajima

3 April 2023

Building Perpetual Agents: Autonomous AI Systems Design

By

@yoheinakajima

–

02 April 2023 8h12

Why do you think I’m building a perpetual agent 🙂

→ View original post on X — @yoheinakajima

2 April 2023

Improving AI Systems Through Context and Task Deduplication

By

@yoheinakajima

–

29 March 2023 6h40

Giving it relevant past task/results as context helps, but candidly definitely room for improvement in my system there. Also using the task prioritization step to also dedupe should help. Having more context (32k) makes this much easier in the future.

→ View original post on X — @yoheinakajima

29 March 2023

Autonomous Task Management in AI-Powered Language Models

By

@yoheinakajima

–

29 March 2023 6h30

4/8 The system maintains a task list for managing and prioritizing tasks. It autonomously creates new tasks based on completed results and reprioritizes the task list accordingly, showcasing the adaptability of AI-powered language models.

→ View original post on X — @yoheinakajima

29 March 2023

Unify Data Analytics and AI on Single Platform

By

@databricks

–

28 March 2023 21h47

If you’re seeing this Tweet, it means you need to unify all your #data, analytics, and #AI onto one platform… Like to confirm.

→ View original post on X — @databricks

28 March 2023

PRA and Datacenter Infrastructure Strategy Discussion

By

@jessyseonoob

–

28 March 2023 12h31

Bon bah on vas reparler de PRA #datacenter

→ Voir le post original sur X — @jessyseonoob

28 March 2023

Pinecone Task Storage: Scaling AI Agent Context Windows

By

@yoheinakajima

–

27 March 2023 20h02

Yeah, it has lots of issues now. Storing task/result pairs in Pinecone, and pulling relevant stuff for execution – but will be much easier to do complex stuff with 32k token limit.

→ View original post on X — @yoheinakajima

27 March 2023