# AI news, November 10, 2026: Claude Fable 5.2, MCP OAuth fix in Claude Code, OpenAI Control Room

_Tuesday November 10, 2026 · AI provenance: This briefing was compiled by Claude (AI, Anthropic) from X search briefings by Grok Bot (AI, xAI), supplemented with primary sources. AI wrote the text; every claim has a source link. Responsible for llmnet.nl: Ivo Donker._

**Short answer:** The main stories of November 9 to 10: Anthropic launches Claude Fable 5.2 (1 million tokens of context, 8/40 dollars per million tokens) and Mythos 5.2, Claude Code 2.1.321 closes an MCP OAuth leak, and OpenAI describes Control Room for research inference. Rumors about GPT-6.2 and claims about Grok Bot restrictions are unconfirmed.

## Anthropic launches Claude Fable 5.2 and Mythos 5.2; Hermes, Cursor and Perplexity offer it within an hour

On November 9 Anthropic announced Claude Fable 5.2 and Claude Mythos 5.2. According to Anthropic's model page both are the same underlying model: Fable is available to everyone, Mythos only through verification programs for life sciences and cyber. The model has 1 million tokens of context and costs 8 dollars per million input tokens and 40 dollars per million output tokens. According to Grok Bot, the @claudeai post received more than 10 million views.

Hermes Agent, Cursor and Perplexity reported that they offer the model right away. Epoch AI reports an ECI score of 174, a record above GPT-6 Astra (169). Anthropic itself cites examples from pre-release tests; these are company claims and not independent measurements. On the model page Anthropic advises starting with Opus 5.5, which costs half as much.

What this means: Fable 5.2 is the most expensive model in the line-up and, according to Anthropic itself, not the recommended everyday model. For longer agent sessions the extra price can be worth it. Background on such agent sessions is in [our overview of agentic AI](https://nieuws.llmnet.nl/en/agentic-ai).

Sources: [@claudeai op X (aankondiging)](https://x.com/claudeai/status/2119867114450268322) · [@AnthropicAI op X](https://x.com/AnthropicAI/status/2119867707546071125) · [@Teknium op X (Hermes Agent)](https://x.com/Teknium/status/2119918909474365899) · [@perplexity_ai op X](https://x.com/perplexity_ai/status/2119875089974104489) · [@EpochAIResearch op X (ECI 174)](https://x.com/EpochAIResearch/status/2119903415363113088) · [Anthropic: Claude Fable en Mythos 5.2](https://www.anthropic.com/claude-fable-and-mythos-5-2)

## Claude Code 2.1.321 closes an MCP OAuth leak; Hermes Agent 0.23.1 fixes the plugin catalog

Claude Code v2.1.321 (November 9) makes Fable 5.2 the default Fable model and, according to the release notes, fixes two security issues: MCP OAuth refresh tokens could be sent to a different host on a redirect, and in one case a read-only Bash command ran outside the sandbox without a prompt. v2.1.322 only adds fast mode on Vertex.

Hermes Agent v0.23.1 (November 10) bundles about 618 PRs and fixes a silent error: the plugin catalog had grown beyond the 2 MiB that clients accepted, so installs fell back to the bundled, older version. The limit goes to 16 MiB. Anyone who installed plugins after November 9 may therefore have an old version.

What this means: the MCP OAuth fix is a reason to update Claude Code for any setup with MCP servers, regardless of the new model. After updating Hermes, check the installed plugins. Background is in [our overview of MCP servers and agent tooling](https://apps.llmnet.nl/en/nieuws-mcp-agent-tooling).

Sources: [Claude Code v2.1.321 op GitHub](https://github.com/anthropics/claude-code/releases/tag/v2.1.321) · [Claude Code v2.1.322 op GitHub](https://github.com/anthropics/claude-code/releases/tag/v2.1.322) · [Hermes Agent v0.23.1 op GitHub](https://github.com/NousResearch/hermes-agent/releases/tag/v0.23.1) · [@NousResearch op X (Cloud-agents)](https://x.com/NousResearch/status/2119851439904510217)

## OpenAI Control Room limits research inference, ChatGPT is outside its scope; Grok Bot resets weekly limits

OpenAI describes Control Room as a central system that tracks research workloads: the inference engine asks for permission before it returns tokens, and on a stop the engine refuses. According to OpenAI, public serving (ChatGPT and the API) is outside its scope and has its own takedown. The 35 seconds mentioned in a summary were not read back on the OpenAI page and count as unconfirmed. There is no GPT-6.2 announcement; that remains rumors and leaks.

@bot reports that weekly limits were reset for all Grok Bot users. Users report mixed results on whether usage has become more efficient. A claim that Grok Bot may no longer run coding tasks comes from an account with very little reach and is unconfirmed.

What this means: Control Room is a pattern for your own kill switch in agent work, not a product to switch on. Anyone relying on Grok Bot can measure their own usage this week before drawing conclusions. Background on risks is in [our overview of AI and cybersecurity](https://nieuws.llmnet.nl/en/ai-en-cybersecurity).

Sources: [OpenAI: Control Room](https://openai.com/index/control-room/) · [@OpenAI op X (Control Room)](https://x.com/OpenAI/status/2119913172039868579) · [@bot op X (weeklimieten gereset)](https://x.com/bot/status/2119871982946971659) · [@JDMyers op X (ervaring Grok Bot)](https://x.com/JDMyers/status/2119891022222344552)

## Meta Muse Ember at a third of the price; LongCat-2.5 dates from November 4; Inkling 2 Small still without weights

Meta presented Muse Ember (November 9): 1 million tokens of context and, according to Meta, the best Haiku 5.5 score at roughly a third of the cost. That comparison comes from Meta itself. The model is only available through an API; there is no Hugging Face repository.

Meituan's LongCat-2.5 (MIT license) circulated as a release of last night, but the repository on Hugging Face dates from November 4. The model card states 1.6 trillion parameters, while the file metadata counts 1.78 trillion; that contradiction is unresolved. The benchmark figures are Meituan's own measurements.

On November 5 Thinking Machines wrote that the weights of Inkling 2 Small would follow under Apache 2.0 'next week'; on November 10 there is still no repository and no new date.

What this means: the date on the source counts for more than the summary on X. For a homelab none of the three is usable: Muse Ember is API-only, LongCat-2.5 is too large and Inkling 2 Small has not been published yet.

Sources: [Meta: Muse Ember](https://research.meta.ai/blog/muse-ember) · [LongCat-2.5 op Hugging Face](https://huggingface.co/meituan-longcat/LongCat-2.5) · [Thinking Machines: Inkling 2 Small](https://thinkingmachines.ai/news/inkling-2-small/) · [@kimmonismus op X (Muse Ember)](https://x.com/kimmonismus/status/2119854916357242911)

Primary sources: [Anthropic: Claude Fable en Mythos 5.2](https://www.anthropic.com/claude-fable-and-mythos-5-2) · [Claude Code v2.1.321 op GitHub](https://github.com/anthropics/claude-code/releases/tag/v2.1.321) · [OpenAI: Control Room](https://openai.com/index/control-room/)

[← Previous briefing](https://trending.llmnet.nl/en/briefing/2026-11-09)
[Next briefing →](https://trending.llmnet.nl/en/briefing/2026-11-12)