LAI #133: The Most Anticipated Model of the Year and Most of You Skipped It

Claude Fable, one of the most anticipated AI models of the year, was launched on June 9, pulled by the US government three days later, and brought back on July 1, yet a third of users have not tried it. The community is split, with 19% praising it for coding, 12% preferring it over Opus and Sonnet, and 11% finding it strong for agents, while 15% consider it overhyped or costly and 4% are frustrated by usage limits. The newsletter also highlights an open-source AI Research OS for persistent agent memory and Codex's Record & Replay feature for automating repeatable workflows.

Good morning, AI enthusiasts This week, I published something with Paul Iusztin that we’ve been working on for a while: an open-source system that gives your agents persistent memory across sessions using your own notes and research. Full details are below. We also cover: Let’s get into it If you have a task you repeat every week, you don’t need to keep prompting AI from scratch every time. For example, a weekly report is usually not a one-off prompt. It is a repeatable workflow with a few inputs that change each time. The problem is that people often save the prompt, but not the way they actually do the task. They forget the tabs they check, the fields they always fill in, the naming convention they use, or the final check they run before sending it out. Codex’s Record & Replay feature is useful for this. You can record yourself doing the workflow once on your Mac, and Codex can turn that recording into a reusable skill. The next time you need to perform the same task, you give it new inputs instead of rebuilding the whole instruction from memory. Before recording, pick one workflow with clear start and end points. Then note what changes each week, what stays the same, and what “done” looks like. If you want to bring AI into real workplace tasks and team workflows, check out our Master AI for Work https://academy.towardsai.net/courses/ai-business-professionals?utm source=Newsletter&utm medium=email&utm id=AItips course. — Louis-François Bouchard, Towards AI Co-founder & Head of Community Paul Iusztin and I also published a deep dive on turning your second brain into agent memory. If you’re like most of us, you have thousands of notes across Obsidian, Readwise, Notion, and Google Drive, and none of them follow you into your next Claude or Codex session. Every research session starts from zero. We built the fix: an AI Research OS that runs deep research across your notes and the open web, then stores what it finds as an LLM wiki, inspired by Karpathy’s idea, that your agents can query, maintain, and grow with every session. No vector database, no knowledge graph, nothing to host. Just Markdown, YAML, and folders. Google independently shipped the same architecture as an open standard Open Knowledge Format , which tells you the direction is right. The whole thing is open source as a Claude Code plugin, you can clone and run on your own notes today. Read the full article here https://www.decodingai.com/p/llm-wiki-agent-memory?r=1ttoeh&utm medium=ios&triedRedirect=true . Nobias0700 https://discord.com/channels/702624558536065165/983037843532308500/1524015219033112597 is working on EVA, a minimal self-evolving agent that safely rewrites, tests, and promotes better versions of itself inside a hardened Docker sandbox. The project aims to answer what it would look like if an agent could modify its own runtime through a gated release process instead of live self-mutation. EVA’s loop is active release candidate tests/ratchet kernel gate promotion ledger rollback. The kernel stays small and non-evolving. The evolvable release contains the agent loop, tools, adapters, memory, context compaction, TUI, and self-model. Currently, it’s experimental, but check it out on GitHub https://github.com/arturkorb3/eva-evolutional-agent and share your technical feedback in the thread https://discord.com/channels/702624558536065165/983037843532308500/1524015219033112597 . Claude Fable was one of the most anticipated releases this year, launched on June 9, pulled by the US government three days later, and only brought back on July 1. A third of you still haven’t tried it. Of those who have, the community is genuinely split: 19% say it’s amazing for coding, 12% think it’s way better than Opus and Sonnet, and 11% find it strong for agents and long tasks. But 15% think it’s good but overhyped or costly, and another 4% are frustrated by usage limits. So the people who’ve used it mostly like it, but cost and access are clearly holding back adoption. It’s now on usage-credit billing, though Anthropic says they aim to bring it back to subscriptions once capacity allows. What I want to know: if you haven’t tried it yet, is it because of the cost, because you’re worried it might get pulled again, or just because what you’re using now works fine? Let’s talk in the thread https://discord.com/channels/702624558536065165/833660976196354079/1523756611166928926 The Learn AI Together Discord community is flooding with collaboration opportunities. If you are excited to dive into applied AI, want a study partner, or even want to find a partner for your passion project, join the collaboration channel https://discord.gg/rj6m9AF7eC Keep an eye on this section, too — we share cool opportunities every week 1. Teranmix https://discord.com/channels/702624558536065165/784477688551178240/1522621958456475749 is looking for AI ML/DL enthusiasts to learn AI with mathematics. If you are interested in that side of learning, connect with him in the thread https://discord.com/channels/702624558536065165/784477688551178240/1522621958456475749 2. Imarkusss https://discord.com/channels/702624558536065165/998978160605540454/1524107091856330892 is building an early-stage startup applying machine learning to simulate and predict how drugs, proteins, and biochemical compounds interact. He is looking for ML/AI engineers to collaborate, so if you are interested in this domain, reach out to him in the thread https://discord.com/channels/702624558536065165/998978160605540454/1524107091856330892 I have been saying it for so long now, efficientnet1995 https://discord.com/channels/702624558536065165/830572933197201459/1524178460300546160 made it funny with their meme. AI-DLC + Claude Code: The End Of Vibe Coding, A Complete Hands-On Guide https://pub.towardsai.net/ai-dlc-claude-code-the-end-of-vibe-coding-a-complete-hands-on-guide-7e6cf6e026a2?sharedUserId=tai-tech by Pravin Borate https://1pravin-borate.medium.com/?source=post page---byline--7e6cf6e026a2--------------------------------------- AWS open-sourced AI-DLC, a phase-gated methodology that turns Claude Code from an autocomplete tool into a disciplined engineering partner. This article shows how to build a Task Management API, showing how workspace detection, requirements analysis, user stories, and design documents each require explicit approval before code generation begins. Extensions such as security baselining and property-based testing add blocking gates, while a persistent audit trail and a state file allow sessions to resume across tools. 1. Governance by Design: Four Principles for Building Safe, Compliant AI Agents https://medium.com/towards-artificial-intelligence/governance-by-design-four-principles-for-building-safe-compliant-ai-agents-a3dbecf845bb?sharedUserId=tai-tech by MongoDB https://medium.com/@MongoDB?source=post page---byline--a3dbecf845bb--------------------------------------- AI agents now act directly on production systems, and this article argues that recent database-deletion incidents at Replit and Cursor were governance failures rather than technical ones. The piece lays out four pillars for safe agent deployment: identifying regulatory constraints such as HIPAA and the EU AI Act; layering input, execution, and output guardrails; enforcing deny-by-default access with least privilege and human oversight; and establishing agent identity through OAuth On-Behalf-Of and SPIFFE for auditability. 2. How are World Action Models evolving? — Taking a glimpse into the future of Robotics https://pub.towardsai.net/how-are-world-action-models-evolving-taking-a-glimpse-into-the-future-of-robotics-part-i-26c8a1e2696f?sk=44169f13b5ae14ecb323770665e292be by Kim Hyun Bin https://medium.com/@kimhyunbin106?source=post page---byline--26c8a1e2696f--------------------------------------- World Action Models push robotics beyond video prediction toward genuine physical reasoning, and two recent papers show how. ImageWAM swaps costly video generation for an image-editing backbone, leveraging its internal KV caches to drive a flow-matching action expert, cutting FLOPs by a factor of 6 while achieving 93% success on RoboTwin 2.0. HWM, from Yann LeCun’s team, tackles long-horizon planning by pairing coarse and fine latent world models, lifting Franka’s pick-and-place success from 0% to 70% without task-specific rewards. 3. Multi-Aspect E-Commerce Semantic Engine Using Qdrant Multivectors https://pub.towardsai.net/multi-aspect-e-commerce-semantic-engine-using-qdrant-multivectors-e1e7aacaeab3?sharedUserId=tai-tech by Divy Yadav https://yadavdivy296.medium.com/?source=post page---byline--e1e7aacaeab3--------------------------------------- A semantic search engine for e-commerce hit a wall when a single embedding tried to represent specs, images, and reviews at once. The author rebuilt it using Qdrant multivectors, storing SigLIP image embeddings, ColBERT token-level text matrices, and BGE embeddings of extracted review findings at a single point. Query decomposition routes intent before embedding, prefetch stages narrow candidates, and personalization reranks results. Benchmarks show 95% Recall@3 with 2.2ms latency, alongside honest caveats about scale and when this complexity is actually worth building. 4. Claude Agent SDK Observability and Production Hardening: Your Agent Works. Now Prove It: Typed Output, Real Costs, and Traces You Can Search https://pub.towardsai.net/claude-agent-sdk-observability-and-production-hardening-your-agent-works-8fbc36a81806?sk=345fdf6efc413b649164e2ec18662363 by Rick Hightower https://medium.com/@richardhightower?source=post page---byline--8fbc36a81806--------------------------------------- This article shows how to turn a working Claude Agent SDK script into an operable service with structured output, cost tracking, and OpenTelemetry. Structured output gives downstream code typed JSON instead of paragraphs. Cost tracking puts a dollar figure on every run, including the failures. OpenTelemetry exports traces, metrics, and logs to the dashboards you already watch. By the end, you will know how to wire all three and which footguns to step around. If you are interested in publishing with Towards AI, check our guidelines and sign up https://contribute.towardsai.net/ . We will publish your work to our network if it meets our editorial policies and standards. LAI 133: The Most Anticipated Model of the Year and Most of You Skipped It https://pub.towardsai.net/lai-133-the-most-anticipated-model-of-the-year-and-most-of-you-skipped-it-008f4b548707 was originally published in Towards AI https://pub.towardsai.net on Medium, where people are continuing the conversation by highlighting and responding to this story.