/ai

DSPy 3.4.0 adds Jev and System one model support · Digg

DSPy 3.4.0 adds Jev and System one model support

The release announcement also introduces ReAnchor, a new optimizer described as specifically for calibrating outputs with confidence.

TLDR

A post announcing DSPy 3.4.0 says the release adds native support for Jev and System one models, for use with compatible signatures. It also describes a new optimizer, ReAnchor, as specifically for calibrating outputs with confidence.

Featured Source

DSPy 3.4.0 adds Jev and System one model support

The release announcement also introduces ReAnchor, a new optimizer described as specifically for calibrating outputs with confidence.

Combined views

75.8K

11 Sources, first seen 6h ago

733 likes

Today's Rank

#11

Today's Rank

#11

6h ago

first seen 6h ago

Combined views

75.8K

11 Sources, first seen 6h ago

733 likes53 comments448 saves114 reposts

6h ago

first seen 6h ago

TLDR

A post announcing DSPy 3.4.0 says the release adds native support for Jev and System one models, for use with compatible signatures. It also describes a new optimizer, ReAnchor, as specifically for calibrating outputs with confidence.

Featured Source

53 comments

448 saves

114 reposts

Sentiment

Positive100%0%Negative

Summary

Sentiment

Positive100%0%Negative

Many accounts welcomed DSPy 3.4.0’s native Jev support and ReAnchor optimizer because it adds needed threshold calibration for typed signatures while keeping familiar interfaces stable.

Based on 20 sentiment-bearing replies from 17 accounts across 4 conversations.

Summary

Many accounts welcomed DSPy 3.4.0’s native Jev support and ReAnchor optimizer because it adds needed threshold calibration for typed signatures while keeping familiar interfaces stable.

Based on 20 sentiment-bearing replies from 17 accounts across 4 conversations.

7601234567890123456789

7601234567890123456789

7601234567890123456789

7601234567890123456789

11 Sources

@isaacbmiller1DSPy 3.4.0 was just released! This release includes native support for Jev and System one models inside of DSPy! Use it with compatible signatures. This release also includes a brand new optimizer, ReAnchor, specifically for calibrating outputs with confidence.

@dbreunigJust released Jev support for DSPy, with a new optimizer that calibrate’s Je’s output thresholds against your metric. Works with existing DSPy signatures and metrics, can switch between LMs and Jev with one line.

@CShorten30RT @isaacbmiller1: DSPy 3.4.0 was just released! This release includes native support for Jev and System one models inside of DSPy! Use it…

@lateinteractionRT @dbreunig: Just released Jev support for DSPy, with a new optimizer that calibrate’s Je’s output thresholds against your metric. Works…

@CompleteSkepticthis is an honor! 🥹

@omarsar0Pay attention to System One models if you are building custom harnesses and agentic workflows. Great to see DSPy integrate Jev and now support System One models for calibrating agentic workflows. I'm amazed at how naturally System One models like Jev fit into these frameworks. I am using Jev to build my own custom harnesses like here: https://academy.dair.ai/resources/jev-decisions-in-a-pi-sdk-harness So far, I've had great success with guardrails, routing, and verifiers. However, I am starting to see other interesting applications in other parts of the agent harness, like: > structuring skills and better optimizing them > more efficient tool calling for agents > dynamic workflows (i.e., dynamically generating harnesses with orchestrator + subagents patterns) that leverage Jev-like models for more optimally structuring outputs/information traveling between these workflows > enhance coordination between agents > dynamic and smarter loading (like tools and MCP) of system prompts, and really, all areas of context engineering that benefit from smarter and faster decision-making capabilities > RLM + System One Models And the list goes on and on. Just a wonderful time to explore new ways to work with agents.

@DSPyOSSDSPy 3.4.0 out, with: (1) native support for Jev and System One models - in the timeless DSPy syntax. (2) a brand new optimizer, ReAnchor, specifically for calibrating outputs with confidence. (3) lightning-fast import speeds for the LLM abstraction, via sibling library LM15)