Urgent.News

What's breaking now, across thousands of outlets.

Editions

AI

Slack Code taps into collective vibe, puts AI agents into the group chat

Developers can now invite the whole team along for their quality time with the coding bot

Slack Code taps into collective vibe, puts AI agents into the group chat

Slack has introduced Slack Code, a new feature that brings AI coding agents into group chats for collaborative development. These agents can work alongside human developers on project channels, allowing everyone to observe and review their progress. Tagging an agent in a Slack conversation initiates a code channel, where users can monitor the agent's actions, view live HTML previews, and provide feedback or changes.

Once the task is completed, the channel automatically archives itself, leaving a searchable record of the project. Slack Code caters to various stakeholders, including product managers and designers, who can now participate in the development process without needing to use separate tools. The company emphasizes that humans maintain control over the agents, with the ability to pause, redirect, or stop them during the workflow.

Higher-stakes actions, such as deploying code to production, require approval from a human expert. Slack has partnered with several companies, including Anthropic, Cognition, GitHub, OpenAI, and Vercel, to develop integrations for Slack Code. The company plans to open the APIs to the broader developer community, potentially expanding the reach of code channels beyond software development to other tasks.

Alongside Slack Code, Slack is enhancing its Agent DMs and providing an Agents tab for easy access to agents, their sessions, and status. Additionally, a new "Add to Slack" feature allows users to deploy third-party agents with minimal effort. Slack believes that this feature will bring AI-assisted coding into the open, allowing team members to observe and provide input during the development process.

The company is currently offering Slack Code to users, but further details about access, rollout, and available integrations remain unclear.

Written by urgent.news from The Register Science's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

This story

This is one outlet's version. Read the fullest account.

Read the original at theregister.com →

More in AI

acc vs acc_norm: Why Length Bias Skews LLM Eval Scores

Your fine-tune gains three points of acc_norm on HellaSwag and loses two points of acc . Same checkpoint, same harness, same seed.

  • "acc" measures highest summed log-likelihood of candidate continuation
  • "accnorm" divides sum by byte length of continuation string
  • Length bias can skew LLM evaluation scores significantly

More from Thursday 20 August →