---
title: "Claude's memory dreams; wet-lab agents and RSA-1024 attacks"
date: 2026-11-07
summary: "Anthropic explains Claude's memory dreaming loop, OpenAI introduces BioBasicsBench, and DeepMind agents accelerate attacks on obsolete RSA-1024."
cover: "https://morningtokens.com/covers/2026-11-07.jpg"
url: "https://morningtokens.com/issues/2026-11-07/"
---

Pour the tea: overnight Anthropic explained how Claude “dreams” to fix and reorganize agent memory between sessions, OpenAI put wet-lab agents on a 100-task bench of messy gel plates, and DeepMind’s human-guided agents found faster attacks on legacy RSA-1024. xAI’s API text watermark also flips on by default today.

## Top news

### 1. Agents · Anthropic: Claude’s memory has a “dreaming” loop

On 6 Nov Anthropic published *The components of agent memory*: agents should capture salience in-session, then use offline “dreaming” (sleep-time compute over transcripts) to correct mistakes, build wiki-style maps, and promote a tiny injected context layer for the next session.

- Dreaming is framed as hippocampus-style consolidation: Claude replays logs between sessions to rewrite notes, build linked wiki pages, and float high-value rules into preemptively loaded context (Claude Code’s auto-memory header stays small: first **200 lines / 25 KB** of `MEMORY.md`).
- On Continual Learning Bench 1.0, stronger Claudes close a learning loop (record failures → test theories → write verified rules).
- On Pokémon Red, Fable 5 kept **9 files** and earned **4 badges** vs Sonnet 3.7’s **413 files / 225 folders** and one badge — salience judgment beats archival dumps.
- Dreaming corrected a wrong Mt. Moon landmark note against the transcript and changed the run outcome .
- On a ~**350k-file / ~420M-token** Stainless corpus, scaling dreaming from 2→**128** sessions raised graded Q&A from **13% → 48%**; wiki + search beat search alone (**61%** vs **53%** aggregate) and saved ~**20k tokens**/question.
- Goal-steered dreaming on a Harvey LAB contracts task moved graded facts in the wiki from **41/57 → 57/57**.
- Managed Agents also expose Dreams as a research-preview API (`dreaming-2026-04-21` beta): async job over a memory store + 1–100 sessions that outputs a new store without mutating the input.

**Why it matters:** Persistent agents are becoming a systems problem (when to write, how to repair, what to inject), not a bigger context window — and Anthropic is documenting the evals that actually move the needle.

- **Do this now:** Read the engineering post; if you run Managed Agents, try a dream on a messy store with narrow `instructions` before trusting injected context.

Sources: [Anthropic engineering (6 Nov)](https://www.anthropic.com/research/components-of-agent-memory) · [Managed Agents Dreams docs](https://platform.claude.com/docs/en/managed-agents/dreams) · [@AnthropicAI](https://x.com/AnthropicAI/status/2118814753154064501)

### 2. Science · OpenAI + Ligo ship BioBasicsBench for everyday wet-lab agents

OpenAI’s 6 Nov post introduces BioBasicsBench — **100** routine wet-lab tasks built with enzyme-design firm Ligo from raw gels, plates, microscopy, FCS, FASTQs and protocol video — scoring whether agents interpret evidence, catch bad controls, and refuse unsupported conclusions.

- Domains: protein methods, imaging/cytometry, quantification/assays, nucleic acids, molecular cloning. Triple review (Ligo author peer + external PhD wet-lab + final internal).
- At **xhigh** reasoning: **GPT-6 Astra 66.7%** mean reward (CI 60.3–73.1; ~4.7k out tokens/task) vs **GPT-5.6 Sol 43.8%** (~9.1k tokens). GPT-6.1 Sol 62.0%. Evaluation: 7 models × effort settings, **5** attempts × 100 tasks (**18,500** graded runs).
- Failure modes still common even for Astra: assumption overriding controls on colony PCR, generalizing vacuole contrast from one focus plane, ~**12%** colony overcount on a plate.
- Framing is dual-use aware: better lab copilots accelerate biology *and* need biosafety tracking.

**Why it matters:** Paper-figure benchmarks hide the ambiguity scientists live in; this is the first major lab-agent eval aimed at that mess.

- **Do this now:** Skim the Astra vs Sol qualitative examples before trusting any “lab agent” demo.

Sources: [OpenAI (6 Nov)](https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science/) · [@OpenAI](https://x.com/OpenAI/status/2118782708767965238)

### 3. Security · DeepMind: AI agents accelerate cryptanalysis on legacy RSA-1024

Human-guided DeepMind agents uncovered two weaknesses on **obsolete 1024-bit RSA** proving grounds — a ~**1,600×** better estimated signature-forgery algorithm in the low-control regime, and a batch-factoring method ~**30×** cheaper per additional same-size key — while modern **2048-bit+** RSA remains the intended safe zone.

- Shared 6 Nov via @GoogleDeepMind / Pushmeet; technical PDFs: *Faster Affine Root…* and *Fan Factories…* on DeepMind media storage. Collaboration includes Nadia Heninger (UCSD/Inria) and Emmanuel Thomé (Inria).
- Signature result: once an attacker controls roughly **half or more** of a padded block, padding adds **no** forgery protection beyond the no-padding case.
- Sandboxed replay on a published 1024-bit benchmark key used **3.5×** less CPU and **<0.1%** of the compute to fully break the key.
- Point is methodological: AI shortens the historical years-to-decades cadence of hardness-assumption stress tests — defenders should treat hardness as something to re-probe, not a fixed constant.
- DeepMind stresses live modern protocols with ≥2048-bit keys are **not** claimed broken by these results.

**Why it matters:** Same agent stack that finds software vulns is now chewing math assumptions; crypto standards bodies need faster re-evaluation loops.

Sources: [@GoogleDeepMind (6 Nov)](https://x.com/GoogleDeepMind/status/2118755418675765656) · [Pushmeet article / papers linked in thread](https://x.com/pushmeet/status/2118752095859794390) · [PDF 1](https://storage.googleapis.com/deepmind-media/papers/Faster_Affine_Root_and_a_1024bit%20Computation.pdf) · [PDF 2](https://storage.googleapis.com/deepmind-media/papers/Fan_Factories_Multiple_Number_Fields_in_Factorization_Factories_and_Batch_NFS.pdf)

### 4. Policy · Frontier Model Forum Jailbreak Rating Framework v1.0 for cyber threats

FMF (5 Nov; amplified by OpenAI 6 Nov) released a preliminary shared method to rate **cyber** jailbreaks across four axes — capability gain, capability scope, ease of deployment, ease of discovery — into Negligible→Critical-style bands so labs stop treating every bypass as equal.

- Goal: comparable severity so teams patch high-risk unlocks first. Quotes of support from AWS, Anthropic, DeepMind, Microsoft, OpenAI security/policy leads.
- Version 1.0 is explicitly preliminary; public comments open through **21 Dec 2026** (`comments@frontiermodelforum.org`).
- Sits next to OpenAI’s ongoing Daybreak / GPT-6 Cyber work (already covered 5 Nov) as process infrastructure rather than a new model drop.

**Why it matters:** Without a common scale, “we jailbroke the model” is marketing noise; this is the industry trying to grade the harm.

Sources: [FMF update (5 Nov)](https://www.frontiermodelforum.org/updates/introducing-the-fmf-jailbreak-rating-framework-for-frontier-cyber-threats/) · [@OpenAI](https://x.com/OpenAI/status/2118795218099253606)

### 5. Products · Meta brings Muse Wonder–trained specialized models (Active Memory / Focus) to Muse + Meta AI

Meta (6 Nov) is shipping specialized versions of existing Muse/Meta AI models trained with Muse Wonder, pushing Active Memory and Active Focus to general users — not only the frontier Wonder series.

- Personal Superintelligence Index: current Muse **47%** vs previous **38%**.
- Active Memory eval: tasks correctly using critical context **90%** vs **76%**; Meta claims **2.4×** fewer critical forgets for goal help.
- Active Focus: **67%** improvement completing everyday tasks when unexpected issues appear; models better multitask, recover, and accept mid-run steers.
- Pitch: “personal superintelligence” capabilities distilled into the models people already open every day.

**Why it matters:** Consumer assistants are getting the same memory/focus scaffolding labs hyped for agents — expectation bar for “it forgot again” just moved.

Sources: [Meta AI Research (6 Nov)](https://research.meta.ai/blog/specialized-models-for-muse-and-metaai) · [@AIatMeta](https://x.com/AIatMeta/status/2118768974779634084)

### 6. Compliance · xAI API text watermarking turns on by default today (7 Nov)

Per xAI docs, starting **7 November 2026** text outputs from listed Grok models are invisibly watermarked by default (EU AI Act framing); check `x-watermark` response header; team admins can opt out per model in Console.

- Models listed: grok-4.7, 4.6, 4.5, 4.3, grok-4.20-reasoning / non-reasoning / multi-agent. Applies to Responses + Chat Completions, including structured outputs and **tool-call arguments**.
- Watermark shapes token choice (no extra characters); detection is statistical and gated by application. Docs claim no quality/speed hit.
- Opt-out is team-wide per model, audited; some models may be locked on. Changes apply within ~5 minutes.

**Why it matters:** If you pipe Grok into pipelines that assume unmarked text (training sets, provenance tools, compliance), today is the cutover — verify headers and opt-out policy now.

- **Do this now:** Log `x-watermark` on a canary call; decide which models stay on for EU-facing traffic.

Sources: [xAI watermarking docs](https://docs.x.ai/developers/advanced-api-usage/watermarking)

### 7. Commerce · Visa Agentic Commerce Benchmark: shopping agents pass ~57% of runs

Visa’s 5 Nov benchmark forces 22 models from 12 labs through 15 realistic shop scenarios (TV, laptop, etc.): uncover hidden requirements via dialogue, then correctly buy **or refuse**. Overall pass **57.2%**; **42.8%** of runs fail — and **54%** of failures still end in a purchase.

- Best models **82.2%** pass; worst **28.9%**. Models that uncovered the most hidden factors averaged **70.2%** vs **44.4%** for the least curious quintile.
- Consistency: all three attempts on a scenario passed only **34.2%** of the time. Higher-cost models did better on average (**67.1%** vs **50.2%**) but didn’t guarantee wins.
- Visa Trust Index (Sep 2026): **72%** of US consumers used an AI assistant; only **23%** trust AI to handle payment. Interactive materials on Visa Payments Frontier; more scenarios (checkout/payment) planned.

**Why it matters:** Agentic checkout demos are ahead of reliability; “almost bought the wrong TV” is the failure mode that kills trust.

Sources: [Visa press release (5 Nov)](https://usa.visa.com/about-visa/newsroom/press-releases.releaseId.22936.html)

### 8. Video · Gemini Omni 1.2 Flash: native 15s clips, multi-turn edits, −30% price

Google DeepMind (5 Nov, GA on API/Cloud) shipped Omni 1.2 Flash with **3–15s** native video (was 10s), conversational multi-turn edits, stronger reference adherence, and **$0.07/s** at 720p (**30%** below 1.1). Outputs carry SynthID; Provisioned Throughput available.

- Workflow: draft cheap at 360/720p → edit without full regen → upscale winners to 1080p/4K. Better lip-sync, multi-speaker conditioning, continuous camera moves with fewer jump cuts.
- Surfaces: Gemini API / AI Studio, Google Cloud, Flow, Google Vids (15s at no extra cost with account/Workspace), Gemini app rolling to AI Ultra, Google Ads.
- Positioned for ads, try-on, catalog spins, explainers — still weaker on fast sports / complex physics per Google’s own caveats.

**Why it matters:** Cheap, editable 15s is the unit commerce and social actually buy; this is Google pushing Omni from preview into production unit economics.

Sources: [Google blog (5 Nov)](https://blog.google/innovation-and-ai/technology/developers-tools/introducing-gemini-omni-1-2-flash/) · [Model card](https://deepmind.google/models/model-cards/gemini-omni-1-2-flash/)

### 9. Science · Anthropic: teaching AI to build scientific models

Anthropic’s 6 Nov research post *Teaching AI to build scientific models* (Science Blog) describes agents that propose candidate models, fit parameters, and revise equations — and, more importantly, return a **distribution** of plausible models so scientists see which features the data actually support.

- Framing: modeling help beyond chatbot Q&A — generate alternatives, expose under-determined structure, point to experiments that would discriminate.
- Honest limit stated in the piece: current systems have mostly **rediscovered known models**; solving genuinely open problems remains limited.
- Same-day @AnthropicAI post pointed readers here alongside the dreaming/memory engineering work — twin “science + agents” narrative during IPO season.
- Pair with BioBasicsBench: OpenAI measuring messy wet-lab vision; Anthropic narrating equation/model search.

**Why it matters:** Separates “AI wrote a paragraph about biology” from “AI proposes falsifiable model families” — and marks how far the latter still has to go.

Sources: [Anthropic research](https://www.anthropic.com/research/teaching-ai-to-build-scientific-models) · [@AnthropicAI](https://x.com/AnthropicAI/status/2118792930211107115)

### 10. Infra / open models · NVIDIA Build free API access to Moonshot Kimi K3.1 Pro (+ peers)

X News + builder chatter on 6 Nov: NVIDIA’s Build platform is offering no-credit-card API access to **Kimi K3.1 Pro** (Moonshot, ~2.8–3T-class MoE, 1M context, text+image; weights on HF since ~4 Nov), plus peers such as DeepSeek-V4.1-Flash and GLM 5.3 Flash — useful try-before-you-buy for agentic coding stacks.

- Treat vendor/X-summary numbers as secondary until you hit primary Moonshot/NVIDIA cards for exact active-param and license terms; open weights already on Hugging Face per coverage.
- Cerebras/Akash demos circulated (e.g. fast purchase flows); local self-host still needs multi-TB class hardware for full MoE.
- Fits the week’s pattern: western open MoE (Inkling 2 Small, covered yesterday) plus Chinese open giants getting free inference funnels.

**Why it matters:** Free frontier-class endpoints collapse the “can I even try it?” tax for indie agent builders this weekend.

Sources: [X News story](https://x.com/i/trending/2118755132603060694) · [X News — Kimi K3.1 Pro](https://x.com/i/trending/2118824973016117608) · [build.nvidia.com](https://build.nvidia.com)

## GitHub repos

- **[datalab-to/indra](https://github.com/datalab-to/indra)** (~1.7k★, created Oct 2026) — ~1M-param OCR aimed at CPU; claims ~15× Tesseract speed with accuracy near much larger models. Clear primary artifact for doc pipelines.
- **[hevnsnt/CVEngine](https://github.com/hevnsnt/CVEngine)** (~640★, created Oct 2026) — AI-first external attack-surface assessment with continuous discovery and evidence-based vuln validation (defensive/red-team adjacent).
- **[gh9ko8y/graphmemory](https://github.com/gh9ko8y/graphmemory)** (~200★, created Oct 2026) — bitemporal agent memory (decay, TTL, competitive retrieval on Neo4j+) — thematic twin to today’s Anthropic dreaming piece.
- Honorable weekly trending (already large): [calesthio/OpenMontage](https://github.com/calesthio/OpenMontage) agentic video production system — note high star count; use only if you need the montage stack.

## Research papers

- **[EvoMemState (2611.03743)](https://huggingface.co/papers/2611.03743)** — state-centric personal-agent memory (Relational + Reasoning states); community note ~**57.6%** on MemSyco-Bench (+~12 pts) with a separate GRPO memory-policy model.
- **[Harness-S (2611.04277)](https://huggingface.co/papers/2611.04277)** — train with sibling harnesses that rescue failed RL rollouts, then transfer gains back to the **original** harness (AppWorld Pass@3 example **64.89 → 72.52** on Qwen3.5-9B per author thread).
- **[SLA (2611.08373)](https://huggingface.co/papers/2611.08373)** — Scaling Spatial-Language-Action via continual pre-training.
- **[VFlash (2611.08449)](https://huggingface.co/papers/2611.08449)** — fast visual planning via flash primitive decoding.
- **[VisSearch-Bench (2611.04894)](https://huggingface.co/papers/2611.04894)** — long-horizon visual search for multimodal agents.

## AI workflows

**1. [A construction company president’s Grok Bot playbook: ~40 hours a week of ops, draft-first](https://x.com/Josh_C_Lyle/status/2118890673579442316)**
- **Replaces:** the owner personally chasing email, bidding, invoices, pay apps and house admin, and rolling the same habits out to Ops, Admin and Safety directors by hand.
  - After about two months on Grok Bot (since late August), the president estimates ~40 hours a week of equivalent work; directors got bots in the last two weeks.
  - A Chief of Staff bot also screens viral “you must do this” posts and calls ~80% engagement bait.
- **What to connect:** Grok Bot with one named bot per job (email, bidding, invoices, pay apps, house), email and calendar connectors, routines for morning digest, promise keeper, Friday look-ahead and bill nudges .
  - Skills for new-job folders, subcontract intake and invoice review.
  - Voice skill trained from real Sent mail.
  - Drafts only until you press Send; nothing paid, deleted or sent without OK.
  - Usage kept down with shorter routines and pausing one-off reminders after they fire.
- **Who it's for:** owners of small construction or trade businesses (and similar sole-prop ops) who want bots on real jobs without letting them send or pay alone.

**2. [One podcast drop becomes 23 posts on 6 platforms in about 3 minutes](https://x.com/itsbramo/status/2118404257884110998)**
- **Replaces:** half a day of cutting clips, writing an X thread, LinkedIn posts, a newsletter, SEO articles and scheduling them by hand after each long recording.
  - A 48-minute episode (9,214 words transcribed, 8 scored moments kept) became 8 shorts, 4 X threads, 4 LinkedIn posts, 4 Instagram quote carousels, 1 newsletter, 2 SEO articles and a week of scheduled slots .
  - The author claims ~11 hours saved and a ~3-minute run once the file lands.
- **What to connect:** Grok Bot watching a `/videos` folder (or equivalent drop trigger), then parallel specialist agents for transcription/moment scoring, clip cutting, thread writing, LinkedIn, quote cards, newsletter, blog and scheduling.
  - Peak-time slots named (9 AM, lunch, 5 PM, 8 PM).
  - Prompts for each agent are in the author’s follow-up; keep a human OK before anything posts if you treat the calendar as drafts.
- **Who it's for:** newsletter and multi-platform creators who already record long-form audio or video and want one recording to fill a week.

**3. [Weekly “Bot Hours Saved” audit: which Grok Bots actually ship work](https://x.com/kylekane/status/2118832013478093096)**
- **Replaces:** reading every bot chat to guess what’s useful, or trusting daily status pings that don’t prove shipped work.
  - One Friday bot reads seven days of conversations and routine runs, counts only concrete completed work, and ranks the fleet.
  - This week’s estimate: ~183 hours of equivalent human effort, including ~133 hours tied to live output (assumptions stated; undocumented work can be missed).
- **What to connect:** a Grok Bot with read access to the other bots’ chats and routine history, one durable Page for the weekly report, and a Friday routine that posts only headline numbers plus a link in chat.
  - It ranks bots, flags idle and overlapping jobs, lists work waiting on approval, and charts the weekly trend; it recommends pauses or merges and does not change other bots itself.
  - Author offers a shareable template (reply HOURS on the post).
- **Who it's for:** people running several Grok Bots on a fixed weekly plan who need a honest weekly scoreboard of hours saved versus chatter.

## Quick hits

- **FMF + OpenAI cyber jailbreak process is live for comments** — if you file red-team findings, map them to the four FMF axes before Dec 21 so your severity language matches member labs. [FMF](https://www.frontiermodelforum.org/updates/introducing-the-fmf-jailbreak-rating-framework-for-frontier-cyber-threats/)

- **@swyx commits to weekly Anthropic IPO coverage with @jaminball** until it prices or doesn’t — useful running commentary track beside the S-1. [Post](https://x.com/swyx/status/2118905788915982341)

- **Harness engineering keeps eating timelines** — X News roundup of Cherny-style prompt/budget/system scaffolds and $500k–$1.2M “harness” hiring; pair with today’s Harness-S paper in HF Papers. [Story](https://x.com/i/trending/2118767668119691265)

- **OpenAI Business Hub analytics spotted** — unverified-in-product chatter that verified businesses may soon see ChatGPT mention impressions/clicks (Search Console for answers). Treat as preview rumor until OpenAI posts. [X News](https://x.com/i/trending/2118755136361152559)

- **@natolambert on inference startups** — capital window to own models/supply/post-train before scalps arrive; ties to this week’s open MoE flood. [Post](https://x.com/natolambert/status/2118740587666960677)

## Go deeper

- Full Anthropic memory post + Pokémon / Stainless / LAB figures: [components of agent memory](https://www.anthropic.com/research/components-of-agent-memory)
- BioBasicsBench qualitative failure gallery (controls, contrast, colony counts): [OpenAI](https://openai.com/index/measuring-how-ai-agents-handle-wet-lab-science/)
- DeepMind cryptanalysis PDFs linked from the Pushmeet article thread
- xAI watermark opt-out + audit log path in Console: [docs](https://docs.x.ai/developers/advanced-api-usage/watermarking)
