dWeb education session: Capturing our time - capturing human existence (part 1) #TimePerception# #PhilosophyOfTime# #AttentionEconomy# #HumanExistence# #InformationOverload# #TimeAnxiety# #FutureOfHumanity# #MeaningfulLiving# #FeelingBehindInLife#

Email. Headline. Headline. Text. Email. Headline. Headline. Information overload. At Barclays Investment Bank, we leverage our expertise to cut through the noise, empowering leaders with the insights they need to move with certainty in a changing world. Powering Possible.

Long-running AI agents all hit the same wall eventually, context rot, and LangChain just laid out five concrete techniques to deal with it. Title: Context Engineering with Deep Agents: How To Remember Without Keeping Everything In Context URL: 🧩 The problem As agents accumulate instructions, tool results, and files, they eventually exceed the model's context window, degrading reasoning quality, much like how humans lose track of earlier details under information overload. 💡 Five techniques Offloading (moving large results to the filesystem), summarization (compressing older messages while writing them to file), skills (progressively loading full instructions only when relevant), subagents (isolating noisy work in separate context windows), and long-term memory (persisting learnings across sessions as markdown files) work together to manage context without discarding information. 🔧 Technical highlights All five are implemented as middleware hooked into the agent loop, automatically offloading results over roughly 20,000 tokens and user messages over 50,000 tokens to the filesystem. Because memory lives as plain files in storage you control, learned behaviors survive even when you switch model providers. 📊 Use case A market-research agent analyzing five competitors shows this in action: raw data exports, search results, and draft iterations pile up during the task, and context engineering keeps those intermediate artifacts from degrading reasoning quality in the final report. #AIAgents# #ContextEngineering#

Long-running AI agents all hit the same wall eventually, context rot, and LangChain just laid out five concrete techniques to deal with it. Title: Context Engineering with Deep Agents: How To Remember Without Keeping Everything In Context URL: 🧩 The problem As agents accumulate instructions, tool results, and files, they eventually exceed the model's context window, degrading reasoning quality, much like how humans lose track of earlier details under information overload. 💡 Five techniques Offloading (moving large results to the filesystem), summarization (compressing older messages while writing them to file), skills (progressively loading full instructions only when relevant), subagents (isolating noisy work in separate context windows), and long-term memory (persisting learnings across sessions as markdown files) work together to manage context without discarding information. 🔧 Technical highlights All five are implemented as middleware hooked into the agent loop, automatically offloading results over roughly 20,000 tokens and user messages over 50,000 tokens to the filesystem. Because memory lives as plain files in storage you control, learned behaviors survive even when you switch model providers. 📊 Use case A market-research agent analyzing five competitors shows this in action: raw data exports, search results, and draft iterations pile up during the task, and context engineering keeps those intermediate artifacts from degrading reasoning quality in the final report. #AIAgents# #ContextEngineering#

Might be a hot take, but I think we're overly infantilizing "retail traders" in general, but especially regarding the whole options UI/UX debate In an age of agentic trading and increasingly sophisticated retail traders, dumbing things down isn't the same as making options trading easier or more accessible. A big point to make here is that the on chain options sector as a whole, and particularly @DeriveXYZ here, actually benefits quite a bit more from builder codes and 3rd party front ends than perps platforms do. Perps UI/UX is largely solved imo. You can't really get much better than @HyperliquidX or @Lighter_xyz. Alternative front ends are cool for distribution, but the actual UI/UX is largely the same, and nobody really wants that to change much. Conversely, the "ideal" front end UI/UX for options is highly subjective. I love seeing the order book and I glean information from it. You might find it to be information overload and seizure inducing. I like a certain style of visual payoff simulator, you might prefer a written description. I've talked to a half dozen different teams who are building on top of @DeriveXYZ V3, and the opportunity for real differentiation and growing the pie is massive. Some are focusing on simpler UI/UX, some are looking at a more modular one, others are building prepackaged payoffs and structured products where the user doesn't even entirely know they're using options. A huge part of my @DeriveXYZ bull case is that a lot of you seem to think traders are too dumb to use options, without taking into account the rise of LLM idea generation with agentic execution and the alternative front end boom that's about to happen.

🔬 "It feels like having a team of 50 people doing all the work in a day." A Gemini-based multi-agent system generates, debates, and evolves scientific hypotheses, even surfacing a drug candidate that blocks 91% of scarring responses in liver fibrosis. Title: Co-Scientist: A multi-agent AI partner to accelerate research URL: 📝 Overview Co-Scientist is a collaborative multi-agent AI built on Gemini that generates, critiques, and refines novel scientific hypotheses. By automating the hypothesis generation and evaluation cycle, it acts as an AI research partner that accelerates breakthrough discovery. ❓ Challenges Solved Amid information overload and increasingly complex problems, researchers struggle to form breakthrough hypotheses. Connecting scattered facts across vast literature to identify promising research directions is hard. 💡 Methodology & Proposed Approach It organizes specialized agents into three phases. ・Generation phase: a Generation agent proposes novel hypotheses grounded in literature and data, and a Proximity agent clusters them to ensure diverse exploration ・Debate phase: a Reflection agent critiques as a virtual peer reviewer, and a Ranking agent prioritizes via pairwise comparison and Elo-based tournaments ・Evolution phase: an Evolution agent continuously refines and combines top hypotheses, and a Meta-review agent synthesizes final research proposals ・Most of the compute goes to verification, cross-checking claims against ChEMBL, UniProt, web search, and specialized tools like AlphaFold 🎯 Use Cases It is applied across life sciences: antimicrobial resistance, plant immunity, liver fibrosis treatment discovery, ALS mechanisms, cellular aging reversal, infectious-disease protein identification, metabolic disease, and aging biology. 📊 Results ・In liver fibrosis, it identified a drug candidate that blocks 91% of scarring-linked responses ・In cellular aging, it generated genetic leads that rejuvenated cells in the lab and cut screening analysis from months to days ・Over 100 institutions tested it, with collaborators including Stanford, MIT, Cambridge, and Calico ・Enterprise versions are deployed at organizations like Daiichi Sankyo, Bayer Crop Science, and U.S. National Labs #AIforScience# #AIAgents#

I have encountered a lot of stressful situations in life but nothing really prepares you for the first day of kindergarten.. > the instructions are so complicated over like ten emails. this zone, that zone. if you walk, do this. if you drive, do that. what do you mean you stopped for like 5s. there’s a sneak peek, meet your teacher, do your assessment. I mean you could have slow dripped this but no bam. > all the info is so disparate. go to this community for flyers. go to this website for food. you missed this email sorry we got flagged for spam. oh that event, yeah it was buried on page 4 of the weird in line picture in the email (and not the attachment). > you drop your child on the curbside and then just drive away.. is she going to be ok? like will she find her way to the class? i hope she’s not just hanging out at the playground 😅 > post drop off car logistics are the most aggro crazy taxi i have seen. parent swerving left on a four lane road where it’s right only. people honking if you wait a second too long. someone driving down the hill at speeds that aren’t safe. last minute swerve to find a parking spot. surprised there aren’t more accidents tbh. luckily we live in 2026 and LLMs solve at least the information overload problem. but my baby girl is five and my heart can’t believe it or handle it folks. Time is flying too fast!