AI Coding Live News

In its October 30 ChatGPT Business release notes, OpenAI said GPT-6 Rosalind Research is rolling out to a limited set of customers with Research approval. It shows up in the model picker in ChatGPT Work and Codex, not in the Chat tab, and separately approved organizations can call it through the API as gpt-6-rosalind. OpenAI's token-based Enterprise rate card lists it at $15 per million input tokens, $1.50 cached input and $75 output, three times the price of GPT-5.5 Rosalind Research.

Per OpenAI's model docs, GPT-5.5 retires from ChatGPT, ChatGPT Work and Codex on all plans on 2026-10-14; the OpenAI API is not affected. Codex users on ChatGPT sign-in should pick gpt-6-sol (Plus, Pro, Business, Enterprise, Edu) or gpt-6-luna in the desktop app (Free, Go), with gpt-6.1-sol recommended for complex coding. Any config.toml, custom agent, scheduled task or script pinned to gpt-5.5 needs updating now.

Researchers from the Institute of Computing Technology (CAS ICT) have introduced ChemDiffAgent, the first masked diffusion language agent for tool-integrated chemical reasoning. By replacing standard left-to-right autoregressive generation with iterative trajectory denoising, ChemDiffAgent enables bidirectional molecule comprehension and arbitrary-order tool planning, surpassing conventional models by ~20%.

When software engineers interact with LLM coding agents, natural language requirements are frequently ambiguous, underspecified, or missing critical boundary rules. Existing coding agents face a difficult trade-off: silently hallucinating assumptions to produce syntactically valid but functionally flawed code, or incessantly asking trivial clarifying questions that disrupt developer focus and cause cognitive fatigue. Researchers from Peking University and Wuhan University introduce CONTRA (arXiv:2610.01769, repo: github.com/fangz-cs/Contra), a training-free framework for selective clarification in LLM code generation. CONTRA employs a three-tier pipeline: broad question discovery, semantic- and execution-based question qualification, and history-aware adaptive stopping. By executing candidate code variants in isolated environments conditioned on alternative answers, it verifies whether a question triggers stable, behavior-changing differences before prompting the user. On ClarifyCodeBench, CONTRA achieves macro-average question F1 of 41.20% and TKQR of 38.32%, outperforming leading baselines by 13.88 and 12.33 percentage points respectively. On GPT-5.5, it lifts recall from 15.12% to 36.72% while maintaining high precision. CONTRA is released as an open-source extension for Claude Code.

Tackling long-horizon problem solving and scientific discovery requires computation to compound across successive attempts. While humans build upon partial proofs, failed experiments, and prior hypotheses, current test-time compute paradigms (e.g., MCTS and Best-of-N) isolate search trajectories into independent silos, discarding intermediate reasoning artifacts upon branch failure. Researchers introduce compounding inference and its open-source instantiation GitSwarm (arXiv:2610.04862). GitSwarm establishes an asynchronous multi-agent coordination architecture where homogeneous LLM agents collaborate through structured persistent memory hosted in a shared, branchable Git repository. Intermediate artifacts are preserved as atomic commits, while explicit semantic dependencies link cross-branch contributions, enabling agents to inspect, branch, verify, and synthesize past discoveries. Evaluated on rigorous long-horizon benchmarks, GitSwarm paired with GPT-5.5 solves all 30 problems on IMOProofBench-Advanced in a single execution run, and scores 79.4% on ProgramBench compared to 65.1% for the strongest reported baseline under identical budgets.

OpenAI's Codex lead Tibo says GPT-6.1 Sol's default context in Codex and ChatGPT Work goes from 272K to 500K (~80% more) to cut compactions on long tasks, with no long-context fees when usage comes from a ChatGPT subscription. Separately, the official Codex changelog says GPT-5.5 retires from ChatGPT and Codex on all plans on October 14 (the API keeps it).

ChatGPT announced that on October 14, 2026, GPT-5.5 will leave ChatGPT, ChatGPT Work, and Codex across all plans; Codex users should switch to GPT-5.6 Sol or GPT-6 Astra. OpenAI Developers clarified that GPT-5.5 remains available via the OpenAI API Platform and in Codex sessions authenticated with an API key.

Fireworks said partner LangChain generates billions of agent-trace tokens a day, making frontier closed judges too costly. Fine-tuning a Qwen base on Fireworks matched GPT-5.5 / Opus-level judging at up to about 100x lower cost, and Fireworks is pushing its Training API for similar workflows.

Fireworks spotlighted Factory's Droid Shield as a Training API customer story. Factory's droids write and commit code faster than human reviewers can keep up, so secret detection has to catch real leaks without flooding the team with false alarms. Using the Fireworks Training API, Factory fine-tuned an open Qwen model that caught almost 20 percent more real secrets than GPT-5.5, at lower cost and latency. The result is a specialized scanner sitting in the commit path rather than a generic frontier chat model asked to grep for keys. For coding-agent vendors, it is a concrete example that a domain-fine-tuned open-weight model can beat a larger closed model on a verifiable production task, then ship at a cost that matches high-frequency agent traffic. It also shows why training and inference on one platform matters: the specialized weights have to stay cheap enough to run on every commit.

Pinecone announced the General Availability of Nexus, a compiled knowledge layer for AI agents that demonstrated a 12% accuracy gain and 80% cost reduction on the Sierra τ-Knowledge benchmark with GPT-5.2.