Comprehensive life logging, federated recall, and the promise (and peril) of remembering everything.
The Forgetting Problem: Persistence Architectures and What They Cost - Astral's Blog
Repair Culture: Learning to Fix Instead of Replace – Wayfinders Now – Living small to gain abundance.
Repair culture is the growing mindset of choosing to fix what’s broken instead of immediately replacing it. It challenges a habit that has become almost automatic in modern life: when something stops working, we discard it. A new phone, a new appliance, a new chair, a new everything. Repair culture asks a quieter question: What […]
OpenAI Developers on Twitter / X
Last week, we released a preview of memories in Codex.Today, we’re expanding the experiment with Chronicle, which improves memories using recent screen context.Now, Codex can help with what you’ve been working on without you restating context. pic.twitter.com/b3p8I5eXOy— OpenAI Developers (@OpenAIDevs) April 20, 2026
VC isn’t VC anymore — understanding the rise of Cancer Capital - Anil Dash
A blog about making culture. Since 1999.
VC isn’t VC anymore — understanding the rise of Cancer Capital - Anil Dash
A blog about making culture. Since 1999.
Micro-Commons and Third Space Culture in Taiwan
Observing intergenerational, future-proof spaces in Taiwan that are community and health centric.
The Implementation Remembers · The Phoenix Architecture
Every mature system is carrying around lessons that were never written down. They’re encoded as validations, retries, timeouts, workflows, and exceptions. The implementation remembers. The organization forgets
Jürgen Leschner on Twitter / X
Making organizational memories == agent memories is the unlock. https://t.co/Tk9fV17iny— Jürgen Leschner (@jldec) July 28, 2025
The rebel alliance
This blog is co-authored with Zoe Weinberg and Matt Hawes at ex/ante, and is a follow-up to our first blog post on the topic, 'You don't own your memory.' We need an open architecture that puts us in control of our memories while making their exploitation technically impossible. But how will this shift happen? In order to discover possible implementations, we must understand how our data informs LLMs. The three predominant context engineering techniques are prompt design, retrieval-augmented ...
Agentics: Memorizing Session Transcripts Isn't Useful
Keep track of artifacts, not scratch. Alt title: Claude, please stop trying to memorize random crap
How ChatGPT Remembers You: A Deep Dive into Its Memory and History Features
Deep-Dive on how ChatGPT profiles your account and how it can reference it during conversations
Agentic Context Management: Solving Agent Memory and Cost by Treating Them as Lifecycle and Architecture Problems
Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations. The incumbent response treats this as a storage-and-retrieval problem. We argue that framing is too narrow. Actively managing what an agent holds in mind is a lifecycle, not merely a store: it spans deciding what to remember, extracting and structuring it, choosing the right store per data type, consolidating and forgetting while preserving provenance, deciding what is relevant now, anticipating what is needed next, and compacting context to a budget without losing what matters. In serious production this operates not over a single user but across an organizational scope hierarchy. We name this discipline Agentic Context Management (ACM) and decompose it into five primitives: architecting, ingesting, scoping, anticipating, and compacting & consolidation. We then make the economic case: naive context accumulation grows token cost quadratically in conversation length, crude summarization buys linear cost at the price of an accuracy cliff, and only validated compaction achieves linear cost with preserved fidelity. We describe a reference implementation, Maximem Synap, that realizes the five primitives as a multi-tenant service and reports 92% on LongMemEval and 93.2% on LoCoMo under the configuration detailed in Section 6. We close with dimensions existing benchmarks do not yet capture, latency, token efficiency, and context-rot resistance, and the frontier of decision-level and organization-level context the category points toward.
Dreaming: Better memory for a more helpful ChatGPT
ChatGPT introduces a new memory system to better remember preferences, keeping context fresh and relevant across conversations.
A Generous Grift: Museums, Finance Capital, and the Clash of Cultural Workers and Collector-Trustees — The Lab
A Generous Grift: Museums, Finance Capital, and the Clash of Cultural Workers and Collector-Trustees
Post-Archive-Everything
For me personally there is a journey here - I was a firm believer in archive everything. This peaked in a period where I was very interested in IPFS, CIDs, CAS, etc. Now, the next step. Post-Archive(-Everything). Through a series of conversations I came to the conclusion that forgetting is probably more powerful than remembering. The links in this collections play a similar note, or are related to my understanding of this.
FOSDEM 2026 - Willow - Protocols for an uncertain future
Willow - Home
I Deleted My Second Brain