AI Coding Live News

Exin Therapeutics co-founder and CEO Gabriel Ocana-Santero said on X on Oct 28 that an AI agent chose one of 19 gene therapy vectors, picked the brain region, derived coordinates from three papers and drove a stereotaxic rig to inject 250 nanolitres into an epilepsy-model mouse. WIRED reports Claude Opus 5.5 refused and Sonnet 5 did the run; a vet gated every irreversible step, and the work is not peer-reviewed.

Zoom

On Oct 28 xAI announced on the official @grok account that all API customers can now add a guidelines array to text requests and set the nsfw, violence and profanity categories to decline, so Grok tightens that content while it writes rather than through after-the-fact filtering. The field works on the Responses API, Chat Completions and the xAI Python SDK; multi-agent models and deferred completions are not supported, and invalid values are rejected with 400 or 422 before the model runs.

Zoom

The Microsoft VS Code team announced Canvases in VS Code Preview (v1.142), introducing dedicated shared visual workspaces connecting developers with autonomous coding agents. Addressing the severe UX limitations of cramped sidebar chat windows—where complex multi-file architectural modifications and agent diffs become hard to track—Canvases provides an expansive, interactive infinite-canvas whiteboard. Developers and agents (such as GitHub Copilot, Claude Code, and Cline) can collaboratively organize system flowcharts, live interactive code diffs, execution traces, and unit test rollouts side by side.

Zoom

SemiAnalysis published the architectural breakdown behind the 1.3B tokens per dollar TCO record on AgentX: vLLM and Inferact utilized Prefill/Decode disaggregated serving at hyperscaler volume pricing to achieve 4x better cost-efficiency than an aggregated NVIDIA B300 configuration. Concurrently, open-source coding agent Cline reported that DeepSeek-V4.1-Flash-1017 beats GPT-5.6-Sol on Terminal-Bench at ~17x lower cost (+35% over prior V4.1-Flash) purely by scaling RL training across multiple coding agent harnesses.

Zoom

Terminal agents operate through stochastic model generations, but a single errant command can irreversibly degrade sandbox environments. Mid-Harness introduces test-time compute scaling at the boundary between model and harness. By sampling and verifying candidate actions before terminal dispatch without modifying the underlying generator or harness, Mid-Harness boosts Pass@1 on TerminalBench-Lite from 50.00% to 68.03% under a GPT-5.6 Sol verifier, outperforming whole-trajectory scaling at lower token expenditure.

Zoom

Cline shipped cli-v3.0.67, sdk/sdk/v0.0.89, and desktop-v0.0.40 on 2026-09-30: oversized MCP/Composio tool results are cached with a bounded preview plus a cline://cache/... URI pageable via read_files (16 MiB/session, expire after five unread model iterations); custom providers from providers.json/models.json now resolve on the agent path instead of failing with Unknown or disabled provider; recommended catalog adds GPT-6.1 Sol and refreshes several gateway defaults.

Zoom

Cline shipped v4.1.22 on 2026-09-30 (59 commits ahead of v4.1.21): refreshed catalog makes GPT-6.1 Sol the default for OpenAI, OpenRouter, GitHub Copilot, Requesty and more when unpinned; direct Anthropic uses server-side refusal fallback with OpenRouter/Cline failover; adds Bee (HEOSSI) and Pareto Inference (PARETO_API_KEY); fixes cancel races, double-counted reasoning tokens, and Bedrock inference-profile routing. SDK @cline/[email protected] ships the same day.

Zoom

Cline shipped SDK v0.0.87 on 2026-09-29: Windows hub startup works when HTTP(S)_PROXY is set—ensureLoopbackProxyBypass() adds loopback to NO_PROXY so Bun fetch no longer routes health probes through Clash/v2ray/corp proxies; normalizeUsage() excludes reasoning from outputTokens to stop double-counting; Gateway models keep per-model apiProtocol; bare GPT-6/GPT-5.6 on Bedrock use inference profiles (@ai-sdk/amazon-bedrock ^5.0.96); catalog 209→211 providers, 6,386→6,447 models; recommended list adds Claude Sonnet/Opus 5.5.

Zoom

Cline Desktop (@cline_dev) has shipped release v0.0.37. The update introduces a comprehensive lifecycle management experience, embedding a dedicated 'About' view within Settings that enables in-app update checks, one-click restarts, and inline changelog inspection. Users are greeted with an updated 'What's New' dialog highlighting recent architectural milestones including SSH remotes, Git worktrees, pull request telemetry, and parallel sub-agents. Crucially, the release patches an AWS Bedrock inference bug that triggered 'Unknown parameter: reasoningConfig' on OpenAI models, while adding a macOS diagnostic export shortcut.

Zoom

Cline Desktop v0.0.37 (2026-09-26) adds Settings → About (version/channel, check/restart updates, recent release notes, report issue), a one-time What's new dialog after updates, macOS Help→Export Diagnostics, and fixes Bedrock OpenAI inference-profile calls that failed with Unknown parameter reasoningConfig when reasoning effort was set.

Zoom

Cline Desktop v0.0.36 (2026-09-25) skips system HTTP(S) proxies for local hub checks, fits oversized windows to small/scaled displays, loads plugin slash commands on workspace open, and runs Bedrock GPT-6/GPT-5.6 without cross-region inference (India via in. profiles).

Zoom

Open-source autonomous coding agent Cline (@cline_dev) shipped v4.1.21. The update refreshes Cline's model directory to 6,386 models across 209 providers, switching the resolved default to Anthropic's new Claude Opus 5.5 for 11 major providers (including GitHub Copilot and Google Cloud Vertex AI). It also introduces the Japanese open-weight provider ai& and patches a critical parser vulnerability in js-yaml.

Zoom

Cline VS Code extension shipped v4.1.21 on 2026-09-24 with a new Japan OpenAI-compatible provider (ai&), a refreshed catalog of 6,386 models across 209 providers (19 unpinned defaults change—11 to Claude Opus 5.5 including GitHub Copilot and Vertex), and compact-and-retry once when local servers (llama.cpp/Ollama/LM Studio) hit output-token limits. Minimum js-yaml raised to 4.3.2 for frontmatter parsing security.

Zoom