AI Coding Live News

Claude Code lead Boris Cherny on faster usage drain: every shared session reviewed, no regression found, fixes for a few smaller issues rolling out

Since Oct 21 many developers on X have complained that Claude Code was draining usage limits much faster. On Oct 28 (UTC) Boris Cherny, who leads Claude Code at Anthropic, replied on X that the team reviewed every session ID users shared, found no single root cause and no regression in Claude Code, and is rolling out fixes for a few smaller issues that made some sessions burn tokens faster. Most fast-drain cases traced back to one or two heavy sessions using xhigh effort, /goal, Workflows, Agent Teams or long SDK jobs.

Key Takeaways

  • The complaint post that started it said usage was draining 5x faster and drew about 1,660 likes and 240+ replies (a user claim, not official data)
  • Boris Cherny: the team checked every shared session ID, found no single root cause or Claude Code regression, and is rolling out fixes for a few smaller issues
  • Heavy features were the main driver: xhigh effort, /goal, Workflows, Agent Teams and long SDK jobs
  • Subagents inherit the session effort level by default, which adds up fast; /usage shows where tokens went
  • The official docs say Agent Teams use about 7x more tokens than standard sessions when teammates run in plan mode
Read full story
Linked Models & Agents:

Kakao if(kakao)26: Kanana Space + Kanvas turn KakaoTalk into an agentic interface; closed beta from December

On 2026-10-13 at if(kakao)26, Kakao said it will make KakaoTalk (~50M users) an integrated agentic AI interface: Kanana Space (two-finger swipe anytime for messaging, schedules, settings; later shopping/gifting/reservations/transfers, with user approval on consequential acts); PC Kanvas for building agent teams, with a Talk entry planned H1 2027; plus Kanana-o multimodal, an AI conductor that routes by request complexity, and Project Mosaic for cross-service memory. Pre-registration opened Oct 13; Kanana Space closed beta in December.

Key Takeaways

  • Official: if(kakao)26 (2026-10-13–14); tech overview Kakao Tech
  • Kanana Space: summon anywhere in Talk; messaging/schedules/search/settings first, then commerce/transfers; user must approve consequential actions
  • Kanvas: PC agent builder with local memory and per-agent browser sandboxes; small closed beta as early as this year; Talk hub for owned/partner/3rd-party agents targeted H1 2027
  • Stack: Kanana-o omni (text/image/voice); on-device vs large via AI conductor; encoder/decoder planned open-source (not released yet)
  • No public agent leaderboard yet—treat as product roadmap + demo, not GA
Read full story
Linked Models & Agents:

Grok Bot adds a Shopify connector for orders, inventory and listings; Shopify announces @grok and @bot connectors

On 2026-10-08 @bot said Grok Bot now connects to Shopify to check orders, track inventory, and update listings; Shopify announced matching connectors for @grok (business Q&A) and @bot (agent teams). A structured connector avoids the browser bot checks that blocked earlier workflows. Scopes and write operations are not yet detailed.

Grok Bot adds a Shopify connector for orders, inventory and listings; Shopify announces @grok and @bot connectors

Key Takeaways

  • Official: @bot and @Shopify announced the same day (2026-10-08)
  • Capabilities: orders, inventory tracking, product listings
  • Shopify also launched a @grok connector (business Q&A) alongside @bot (agent teams)
  • Structured connector instead of browser login, avoiding earlier 'Verify Human' blocks
  • Not disclosed: scopes, refunds/discounts, quotas; not yet in the Grok Bot changelog at ingest
Read full story
Linked Models & Agents:

OpenRig trends: YAML rigs turn Claude Code, Codex, and Pi into recoverable multi-agent teams; npm 0.6.4, 4.4k★

OpenRig wraps multiple coding harnesses into YAML-defined rigs with seats, queues, and a local daemon/TUI so Claude Code, Codex, and supervised Pi run as one recoverable team. Verified now: GitHub ★4482 / 306 forks; npm @openrig/cli 0.6.4 (2026-10-02); ~4560 weekly downloads.

OpenRig trends: YAML rigs turn Claude Code, Codex, and Pi into recoverable multi-agent teams; npm 0.6.4, 4.4k★

Key Takeaways

  • Repo mvschwarz/openrig (Apache-2.0): ★4482 / 306 forks verified via GitHub API; site openrig.dev
  • npm @openrig/[email protected] published 2026-10-02T05:45:35Z; ~4560 downloads in the prior 7 days
  • v0.6.0 requires Node 22/24; native Windows unsupported; macOS/Linux + tmux
  • 0.6.4 turns web UI off by default and adds host/origin allowlists; many Claude/Codex delivery/resume fixes
  • Starters: dual Codex, dual Claude, or Claude owner + Codex checker; Pi is a qualified supervised runtime
Read full story
ADSponsored

Breakthrough in Self-Organizing Agent Teams: Dynamic Role Emergence Boosts Complex Task Resolution by 27.4%

Researchers have published a seminal framework titled 'Self-Organizing Agent Teams Learn to Reason Together' (arXiv: 2609.22682). Overcoming the rigidity of hardcoded hierarchical agent structures, the architecture leverages graph rewriting to allow LLM agents to dynamically self-organize sub-teams and communication topologies, improving complex problem-solving rates by 27.4%.

Breakthrough in Self-Organizing Agent Teams: Dynamic Role Emergence Boosts Complex Task Resolution by 27.4%

Key Takeaways

  • Replaces hardcoded managerial agent hierarchies with emergent, self-organizing dynamic role specialization.
  • Employs utility-driven graph rewriting to dynamically prune noisy communication links, improving information flow by 61%.
  • Achieves a 27.4% performance lift over static multi-agent baseline frameworks on complex engineering benchmarks.
  • Full benchmark harness and topological simulation codebase open-sourced on GitHub and Hugging Face Papers.
Read full story