Delta Opens New Home for Conductor Chats

// 3h agoPRODUCT UPDATE

Delta Opens New Home for Conductor Chats

Delta now imports Conductor conversations as private threads, preserving the reasoning behind past coding work as Conductor winds down. The migration covers chats—not complete workspaces—so users should also export backups for files and attachments.

// ANALYSIS

Delta is turning a shutdown event into a strong wedge for agent-memory infrastructure: developers may change tools, but they increasingly expect their coding context to survive.

–Imports local Conductor chats directly into Delta and can organize them into projects
–Keeps conversations adjacent to code, reinforcing Delta’s core context-and-collaboration pitch
–Cloud users must transfer workspaces locally before Conductor’s November 20 shutdown
–The importer does not preserve complete workspaces, making separate backups essential
–Support for Claude Code is available now, while Pi, Codex, and broader ACP integrations are still coming

// TAGS

deltaagent-memorycontext-engineeringcoding-agentai-codingdevtoolhosted-service

DISCOVERED

3h ago

2026-11-10

PUBLISHED

4h ago

2026-11-10

RELEVANCE

8/ 10

AUTHOR

zeddotdev

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH55m ago

Meta's AutoRefine Calibrates Code Judges

Meta’s AutoRefine paper presents a prompt-rewriting loop that uses noisy workflow outcomes—tests, merges, and abandons—to recalibrate LLM code judges, while abstaining when outcomes cannot be explained by the judge’s inputs. On held-out diffs from a deployed coding agent, agreement rose from Scott’s π 0.16 to 0.51. ([paper](https://arxiv.org/abs/2611.09291))

INFRA1h ago

Browser Use Cloud Clears CAPTCHA Bottleneck

Browser Use’s stealth cloud browser combines hardened Chromium, residential proxies, and automatic CAPTCHA solving for AI agents. The company reports 90.5% successful visits across 100 bot-protected sites in its own benchmark.

RESEARCH1h ago

Sycophantic AI Warnings Miss Their Mark

A preregistered study of 2,610 people found that warnings reduced perceived AI objectivity and trust, but did not reliably reduce users’ belief that they were right or their willingness to repair interpersonal conflicts. [Read the paper](https://arxiv.org/abs/2606.21317)