Skip to content

AI Dynamics

Global AI News Aggregator

Rechercher

@hwchase17

Managed Deep Agents combines durable workflows computer use and sandboxes

By

@hwchase17

–

11 October 2026 17h38

this is the summary slide that describes how all agents in the future will look

very much aligns with our vision for managed deepagents https://t.co/bXc78RL145

durable workflows: builds on LangGraph/LSD https://t.co/uWayApPuuV

can use a computer: uses Langsmith Sandboxes… https://t.co/FivPNMTJ8Q pic.twitter.com/CR2YKJoPjM
— Harrison Chase (@hwchase17) 11 octobre 2026

this is the summary slide that describes how all agents in the future will look very much aligns with our vision for managed deepagents https://
docs.langchain.com/langsmith/pyth
on/managed-deep-agents-overview
… durable workflows: builds on LangGraph/LSD https://
docs.langchain.com/langsmith/depl
oyment
… can use a computer: uses Langsmith Sandboxes

→ View original post on X — @hwchase17

11 October 2026
Internal agents’ proactive work raises delegated identity design questions

By

@hwchase17

–

11 October 2026 15h09

historically, most of our internal agents (openswe for coding, gtm agent for outreach) have acted "on behalf of" whoever is using them but as they start to do more proactive, background work… I wonder if that should change. eg i really like the idea Hone put forward of agents

→ View original post on X — @hwchase17

11 October 2026
Developers weigh credential models for internal enterprise agents

By

@hwchase17

–

11 October 2026 15h05

what is the future of building internal company agents? how will their identity work? 1. fixed set of credentials
2. "on behalf of" flow (uses credentials of whoever is using it)
3. some fixed credentials, others "on behalf of"

→ View original post on X — @hwchase17

11 October 2026
Open SWE model routing reportedly cuts median task costs by 64%

By

@hwchase17

–

10 October 2026 6h31

agree – most orchestration steps don't need a frontier model for Open SWE we moved model choice into the harness, so each task goes to the cheapest model that still does the job, tested against quality. median cost per task dropped 64% https://
langchain.com/blog/how-to-bu
ild-a-model-router-in-the-harness
…

→ View original post on X — @hwchase17

10 October 2026
Jev handles calibrated binary decisions inside agent harnesses

By

@hwchase17

–

10 October 2026 6h31

good framing from @ch3nweiii – a lot of agent steps are yes/no calls, not generation

Jev answers those as typed questions with calibrated probabilities, so the frontier model sticks to the hard work

where those calls sit in a harness: https://t.co/TgYoOiLc7F…
— Harrison Chase (@hwchase17) 10 octobre 2026

good framing from @ch3nweiii – a lot of agent steps are yes/no calls, not generation Jev answers those as typed questions with calibrated probabilities, so the frontier model sticks to the hard work where those calls sit in a harness: https://
langchain.com/blog/building-
a-harness-with-jev
…

→ View original post on X — @hwchase17

10 October 2026
Goodhart’s Law Complicates Evaluation Driven Development for Autonomous Agents

By

@hwchase17

–

09 October 2026 10h28

This is great point Goodharts law: when a measure becomes a target, it ceases to be a good measure Initial take: eval driven development works for narrowly scoped things, but for more autonomous agents it doesn’t So then – how do you hill climb those?

→ View original post on X — @hwchase17

9 October 2026
Jev LangSmith Evaluation Separates Trajectory Difficulty From Correctness

By

@hwchase17

–

09 October 2026 9h06

trajectory labeling is really several questions, not one pass/fail – nice framing here that's how Jev as a judge works in LangSmith evals: difficulty and correctness each get their own typed answer, in one pass, on every trace https://
langchain.com/blog/jev-is-no
w-available-in-langsmith-evals
…

→ View original post on X — @hwchase17

9 October 2026
LangChain Guide Places Jev Decision Models Inside Agent Harnesses

By

@hwchase17

–

08 October 2026 21h03

Sam on where decision models fit in a harness and how to use Jev with LangChainhttps://t.co/TgYoOiLJXd

https://t.co/pRYMKQuLGq
— Harrison Chase (@hwchase17) 8 octobre 2026

Sam on where decision models fit in a harness and how to use Jev with LangChain https://
langchain.com/blog/building-
a-harness-with-jev
…

→ View original post on X — @hwchase17

8 October 2026
London event on AI agents in production and workshops

By

@hwchase17

–

07 October 2026 21h51

interrupt london is next tuesday really looking forward to hearing from Orange and OVO on what's actually working with agents in production. we're also running hands-on workshops on Deep Agents and Engine

→ View original post on X — @hwchase17

7 October 2026
Deepagents adds dynamic tool loading for skills

By

@hwchase17

–

07 October 2026 20h58

One cool thing deepagents now supports: dynamically loading tools when is a skill is loaded Some skills require specific tools that you may not always want to have available. This now allows you to pair them With openai/anthropic models, it’s possible to do this in a way where

→ View original post on X — @hwchase17

7 October 2026

←Previous Page

1 2 3 4 5 … 103

INNOVATION GENERATIVE AI RESEARCH LLMS TOOLS MACHINE LEARNING CODE MARKET TRENDS TECHNOLOGY BUSINESS BIG TECH ETHICS AGENTS ENTERPRISE AI SOFTWARE AUTOMATION APPS COMPUTING DATA POLICY OPEN SOURCE MULTIMODAL AI CREATIVE AI REGULATION CULTURE PROMPT ENGINEERING EDUCATION SOCIETY SAFETY ECONOMY INVESTMENT AI HARDWARE AGI HARDWARE JOBS STARTUPS INDUSTRY ROBOTICS SECURITY WORKFORCE CYBERSECURITY HEALTHCARE AI SYSTEMS SUSTAINABILITY WEB3 DECENTRALIZED AI

AI Dynamics

Global AI News Aggregator

About
Archives
Contact

Rechercher