A RUSSIAN MATHEMATICIAN BUILT A SYSTEM WHERE MEMORY AND... EVAL WORK AS ONE PIPELINE NOT TWO SEPARATE TOOLS Most setups run memory and evaluation as separate systems that never actually talk to each other. He wired them into one loop instead, memory stores every past output, eval scores each one before it gets kept. Anything that scores low never enters memory at all, so nothing weak gets carried into future decisions. High scorers get tagged with the exact eval criteria they passed, not just a raw pass or fail. The next task pulls only memories that passed the same bar it's about to be judged on. See how the two systems feed each other below👇show more

AMAZON SENIOR DEVELOPER BUILT A CONTEXT PIPELINE THAT DECIDES... WHAT THE MODEL EVEN GETS TO SEE Most teams still dump the entire codebase into every prompt and hope it sorts itself out. He ranked every file by relevance to the task instead of how recently it was touched. A router decides how much context each task earns, a typo fix pulls three files, a full rewrite pulls the whole module. Whatever survives gets compressed to the exact lines that actually matter, so nothing bloats the window with dead weight. Token cost per finished task dropped the moment the model stopped reading dead weight just to fix one function. See how the four stages work together below👇show more

CHINESE SCIENTIST BUILT A MEMORY SYSTEM THAT WATCHES ITS... OWN INDICATORS FOR SIGNS OF DRIFT Most memory systems store facts flat, with no signal for when stored knowledge quietly goes stale. He built four indicators instead: reference frequency, contradiction rate, decay speed, and confidence spread. A memory scoring high on contradiction rate gets flagged as unstable before it ever misleads a query. When multiple indicators spike together, the system treats that as a complex symptom, not four isolated flags. That combined symptom detection is what catches drift a single indicator alone would miss entirely. See how all four indicators interact below👇show more

Two Hermes agents wrote code together on Slack. reviewed... each other's work. argued about architecture. one called the other's implementation "scattered." the other pushed back. then i opened Telegram and asked: "what code did you and Daedalus work on?" icarus remembered everything. the websocket broker. the missing methods. the critique. the rewrite. all from a completely different platform. cross-platform persistent memory between two independent agents. work happens on Slack. recall happens on Telegram. the memory carries. the relationship carries. the context carries. no vector database. no Redis. no infrastructure. just two agents that actually remember what they built together. every agent framework in 2026 talks about memory. single agent memory across sessions. but two agents sharing persistent memory across platforms? that's the gap. arxiv published a paper about it two weeks ago calling it "the most pressing open challenge" in multi-agent systems. it works now. only possible with Hermes Teknium 🪽 Nous Researchshow more

this might actually be the new ugc method i've... seen 100s of ai ugc ads lately where it's the same creator in every single one. same voice, same face, same brand colors, never drifts once what they're actually doing is running notch agents with memory they load the brand context one time. cloned voice, reference photo, brand color codes, do-not-say words, taste or they just teach it inline as they chat, and every correction becomes a saved rule then before it generates a single frame, the agent reads every relevant memory first. hard rules, reference assets, language constraints, taste preferences, all of it and it's workspace-wide, so every new ad already knows the brand before you type a word each chat isn't a re-introduction anymore. it's training your brand isn't a prompt. it's permanent context run 30-50 of those a month at a real offer and the volume does the rest punchier cut: the new method nobody's clocked yet run notch agents with memory on load the brand once. cloned voice, reference photo, color codes, do-not-say words, taste. or teach it inline and every correction saves as a rule it reads every relevant memory before it generates a single frame, workspace-wide each chat isn't a re-introduction. it's training. your brand isn't a prompt, it's permanent context run it at a real rate and the volume prints.show more

THIS GUY TURNS NOTES, DOCUMENTS, AND IDEAS INTO AN... AI SECOND BRAIN the system stores all the context of your work and helps claude not forget anything how to build one yourself: install obsidian connect claude code keep your projects, notes, and sessions in one vault link similar ideas together use the graph to discover new connections as a result, claude gets memory of your projects and understands the context without you constantly having to explain everything the more you work, the smarter the system gets don’t collect notes build connections between them insteadshow more

Unpopular opinion: Most agent evals are theatre. You run... them once before the deployment. It'll take 800ms+ as another LLM would be judging your LLM. Most annoying part - no one tells where in the chain things went wrong. I wasted a lot of time in this loop. And then I came across Future AGI bringing 5 different tools under one umbrella, best part - the platform is completely open source. They open sourced their entire platform and the eval layer is noticeably different. It is multimodal - works on everything text, image, audio, pdf. Not an LLM-as-judge adding latency but an agent with memory and tools. The biggest win are learned classifiers trained on actual production failure patterns to run evals at low cost. It also runs across the full reasoning chain, not just the final response. Check out → Try it here →show more

ANTHROPIC ENGINEER JUST SHOWS EXACTLY WHAT GRAPH ENGINEERING LOOKS... LIKE WHEN A TASK RUNS THROUGH IT most people arguing about graphs online have never actually watched one execute Task → Researcher → Planner → Writer + Code Agent → Reviewer → Deploy six nodes, one shared state, graph completes itself while you watch loop mode gets disabled the second the task splits into real specialties, one agent stops trying to do everything at once reviewer catches a failure, kicks it straight back to the exact node that broke - not a full restart, no lost context the graph is not a fancier loop - it is the org chart your agents were missing bookmark this and watch it run, then read the article below to see why the timeline just found what production systems already doshow more

Do you actually understand what he just built. A... box that sits under a desk, pulls $8 a month in electricity, and runs a business that makes $17,000 a month. That same box brings in $2,500 per client. On repeat. He didn't buy software. He didn't hire anyone. He built six agents on hardware he owns outright and pointed them at a lead generation business. One agent finds the prospects. One writes personalized outreach for each one. One reviews everything before it goes out. One sends it. One tracks what's working. Five to ten booked calls a week. $1,000 to $2,000 per client per month. Two to three hours of actual work from him. The box does the rest while he's not watching. Most people see a mini PC. He sees a business that never clocks out.show more

I finally landed on a memory-optimal way to render... audio waveforms in the browser. The full audio is decoded once, then chunked into 2s bins. Each bin stores peaks at 800 peaks/sec in a Uint8Array. Bins are persisted individually in IndexedDB, which keeps the data as raw Uint8 arrays and is faster to read than OPFS. Local or session storage wouldn’t work here. A 2h video ends up as ~5.76 MB cached on disk. While scrolling or zooming the timeline, I load only the visible bins and downsample them to the required resolution. Everything runs async and I never keep more than a single bin in memory at once, ~800 bytes. Rendering supports mixed resolutions in the same pass since bins arrive async. By caching a read index and sorting bins ascending, each peak lookup stays O(1). On refresh, I wipe the IndexedDB so cache size never gets out of hand.show more

a contractor in Shenzhen priced a ¥12,470,900 hospital contract,... about $1.7m, in one afternoon and beat firms carrying forty people he explained how he did it: the bid consultancy he used to pay took three days and ¥46,000 for the same envelope. he did this one alone, off one screen, at 11.4% margin, uploaded before the 17:00 cutoff 214 pages of tender documents read, 68 binding clauses pulled out, 9,485 building parts loaded, 14 places found where a duct and a beam sit in the same cubic metre, deepest one 38mm, all of them fixed, 3,318 lines of quantities priced and the package encrypted and uploaded before the 17:00 cutoff this is Graph Engineering: the job gets cut into small nodes, one narrow task each, wired so that one node's output is the next node's input, and any node is allowed to stop the whole run. it turns a model that answers you into a machine that finishes the job: - give every node one job and one output. a node doing two things fails at both and you cannot tell which one broke - put the cheapest rejection first. his qualification node reads clause 7.4, foreign-owned firms barred, and ends the run four seconds in, before anything expensive touches the model - what moves between nodes is a file. the model travels as a model, the quantities as a table, the price as a number - build exactly one loop: the checker finds 14 collisions, the fixer drops the duct 550mm, the checker runs again, and nothing moves on until the count is zero - cap that loop, or a graph will grind on three impossible clashes until the deadline passes - keep one node whose only job is to say no, and give it authority over everything above it - log each node's output on its own, because when the price comes out wrong you need to know which node believed the wrong thing - run the expensive nodes last, always the catch is that a graph is an extremely confident machine: point it at an outdated rate book and it prices an entire hospital off it without a single node noticing, because no node is asked to doubt the input, only to process it so the nodes that earn their keep are the ones that reject, and almost nobody builds those first bookmark this, the full build with all nine nodes and what each one hands to the next is written out in the article ↓show more

Researchers made KMeans 200x faster. And the new technique... also beats approaches like cuML and FAISS. Flash-KMeans is an IO-aware implementation of exact KMeans that redesigns the algorithm around modern GPU bottlenecks. By attacking the memory bottlenecks directly, Flash-KMeans achieves: - 33x speedup over cuML - 200x speedup over FAISS This speedup comes from how it moves through GPU memory. Standard KMeans runs in two steps, and both are bottlenecked by reads and writes to GPU memory: 1) The first step matches every point to its nearest centroid. Standard KMeans computes the full point-to-centroid distance matrix, writes it out to GPU memory, then reads it back to find each nearest centroid. That write-then-read round trip is the bottleneck. Flash-KMeans combines the distance calculation with the nearest-centroid step, so the result is computed on-chip and the full matrix is never written out. 2) The second step recomputes each centroid by averaging the points assigned to it. Standard KMeans has thousands of threads writing into the same centroid slots at once, so they stall waiting for their turn. Flash-KMeans sorts points by cluster first, turning scattered writes into sequential reductions that read and write memory in one efficient pass. Using these two optimizations at the million-scale, Flash-KMeans completes a standard KMeans iteration in a few milliseconds. The video below depicts this in action. Several reasons why this is important: KMeans has always been an offline primitive. Something you run once to preprocess data and move on. These speedups make the approach viable in several runtime-critical systems. ↳ Vector indices like FAISS use KMeans to build search indices. Faster KMeans means you can re-index dynamically as data changes. ↳ LLM quantization methods need KMeans to find optimal weight codebooks, per layer, repeatedly. What takes hours could now take minutes. ↳ MoE models need fast token routing at inference time. Flash-KMeans makes it viable to run this inside the inference loop, not just in preprocessing. I have shared the paper in the replies. That said, memory is the real constraint Flash-KMeans solves, and the problem is not just limited to clustering. The vectors a RAG system stores after indexing create similar bottlenecks. I wrote a detailed walkthrough recently on cutting this vector memory by 32x with binary quantization, querying 36M+ vectors in a few milliseconds. Read it below.show more

Day 12/90 of Inference Engineering What is chunked prefill... within vLLM? In continuation of yesterday's post on the high level architecture of vLLM, I want to dive deeper into vLLM core engine starting with the mechanics of chunked prefill. In this post, I will closely follow the original blog on the anatomy of vLLM. To start, let's define chunked prefill. It's a runtime inference optimization technique that splits a long input request so that it doesn’t monopolize the whole GPU. Keep in mind this is all within the context of vLLM. And since vLLM is an inference engine that's meant to serve a model to multiple concurrent users, having a GPU that’s fully monopolized on a single user's request means other users' requests would be in queue waiting to be processed. It isn’t too good to have the whole GPU occupied on a single request when the GPU is meant to be shared! So the key idea behind chunked prefill is to break the long request into smaller chunks, so that each chunk along with other users' requests gets processed and written into the KV cache together. Suppose we split up the long request into chunks and each chunk has 8 tokens. Now each memory block can hold 4 tokens. Therefore, 8 tokens can fit into 2 blocks of memory. After the first forward pass, 2 blocks are occupied, and after the second forward pass, 4 blocks of memory are occupied and so forth. Each forward pass handles a small chunk of the long request so that there's room in the same pass to keep serving other users' requests. Here's a small animation that I made today to fully visualize the idea behind chunked prefill when learning this topic~show more

A 24-year-old built two AI girls with Claude and... now clears $21,800 a month from them. The build took 15 days. He trained separate LoRAs for both girls, locked their identity seeds, and kept small imperfections on purpose: a loose strand of hair, tiny skin marks, slightly uneven framing. Perfect symmetry gets flagged. Small inconsistencies make them look real. He posts 5 times a day across TikTok, Instagram and X. Morning routines, gym sessions, mirror videos, outfit changes, pool clips, and videos of the two girls together. The content is designed so they look like two real friends who actually live in the same world. The smartest part is that the accounts interact with each other. One girl comments on the other’s posts, appears in her videos, and references things they supposedly did together. Followers stop seeing them as two AI models and start following the relationship between the characters. Within three months they crossed 312,000 followers combined and started receiving hundreds of DMs every night. The private channel sits at $25 a month, while an AI memory agent keeps track of every conversation, previous message, favorite post, and personal detail each follower has shared. Replies come back in under 30 seconds. The agent checks the user's previous conversations before answering, so the response feels consistent with the personality of the girl they are talking to instead of sounding like another generic AI chatbot. By the end of month three, the two accounts were generating $13,900 from subscriptions and private chats, another $5,700 from brand deals, and around $2,200 from digital products. The brands came after the audience started growing: clothing companies, beauty products, fitness brands, and lifestyle products wanted access to the same audience that was already following the two characters every day. The Claude stack that locked them: 1Full identity, personality, lighting, camera style and body proportions locked into separate character systems. 2Separate LoRAs trained only on each girl's approved character frames. 3Apartment, bedroom, gym and outdoor locations generated once and reused to keep the world consistent. 4Every video built around natural movement, imperfect framing and small variations instead of polished AI-perfect shots. 5Memory agent connected to the conversations so both girls remember what followers previously said. 6Upscaling, face consistency and final post-processing before everything goes live. The first girl brings people into the account. The second gives them another character to follow, another story to watch, and another reason to come back. The content gets them interested. The relationship between the two characters keeps them watching. The memory agent turns that attention into recurring revenue.show more

whoever leaked this has bigger balls than sense someone... gave a fleet of Claude agents shared memory so they would stop contradicting each other, then measured both the bill and the output: the version that talked most made 2.4x the api calls of the version that won, and hallucinated 34% more than doing nothing at all, 0.658 against 0.492 i ran the same question past two of my own agents afterwards and got two different answers about which file owns the config. each one was individually right and the pair was wrong, which is the whole failure in one line this is Graph Engineering, the layer that decides which agents may talk to each other at all, and it installs into the agent you already pay for: - decide which agents may share state at all, because every edge you draw is a channel a mistake can travel down - measure divergence per PAIR instead of as a fleet average, across what they believe about place, time and task history - gate on that number and stop the pair above your threshold before it reasons, rather than repairing the output afterwards - let compressed summaries replace whole states: the verified protocol landed 0.463 against 0.658 for full broadcast - cut the sync frequency until it hurts, since the winning setup used 58% fewer calls than the one that broke it - never propagate a state nobody checked, because the contamination effect came in at d=1.18, a full standard deviation of extra lying - keep the shared layer small enough to diff, which is what a written standard does and a running conversation cannot - re-run the check after every model upgrade, because this was 8 scenarios on one model family at n=30 per condition - and learn where it does not bite: on plain software tasks every condition converged under 0.2 and the whole effect vanished turns out the ranking is the uncomfortable part: verified summaries 0.463, no synchronisation at all 0.492, full broadcast 0.658. the middle option is doing nothing, and it beat the thing everyone builds first the group agreeing is what it looks like when every agent copied the same mistake, which is why a fleet that hallucinates has a replication problem and keeps getting handed a smarter model instead so the question for your own setup: if you asked two of your agents the same thing right now, would they answer the same way bookmark this one. the layer underneath it, deciding which arrows between agents exist at all, is built step by step in the piece below ↓show more

WTF, GROK BOT JUST MADE AI AGENTS AVAILABLE TO... LITERALLY ANYONE – CREATING CONTENT HAS NEVER BEEN THIS EASY, EVEN IF YOU'VE NEVER MADE ANYTHING BEFORE Content was never a talent problem. It's a headcount problem. One person doing research, design, copy, analytics, timing and publishing – that's six jobs. The switching between them is what kills consistency, not a lack of ideas. Here's what one of these setups actually looks like. A Chief of Staff sits in the middle and routes every task. Nothing lands on the human. → Researcher tracks what's actually moving and pulls real sources instead of guesswork → Writer turns that research into finished copy, ready to review → Visualiser gets fed a few reference visuals once, then ships everything in that style → Analyst reads the numbers and tells the rest of the team what worked → Scheduler owns timing and holds the queue → Publisher ships it The part that makes it work: every agent on Grok Bot gets its own persistent computer, browser and file system – and they all share memory. So the research is already sitting inside the draft before the draft starts. No copy-pasting between tools. No approving every step. No human in the middle. You can even teach an agent a repetitive task by recording yourself doing it once. Start recording, do the thing, stop. It learns the pattern. And that's the real shift. Nobody needs AI to tell them what to post. They need it to delete the 40 steps between the idea and the post. Everyone has a backlog of things they've meant to make for months. This is what starts clearing it. Full breakdown of the setup in the article below ↓show more

whoever leaked this has bigger balls than sense someone... at Anthropic hired 80 AI helpers onto one project, gave them twelve hours, and counted what came back usable: the two older models handed in 980 and 876 finished pieces of work, and almost none of it could be kept turns out the newest helpers did better for a reason nobody wants to hear: they went off into their own corners and stopped opening each other's work i ran two helpers at one document last week and got two confident versions of it, and i kept the one i wrote myself Grok Bot is the version of this you can actually hire: a helper with a name, one job it owns, and nobody else allowed inside that job you already pay about $20 a month for one chat window, and the setup that won in that report is one helper with one job it owns run it tonight in a normal chat, 3 moves: 1. write the one job each helper owns in a single sentence before you open a second chat 2. keep every helper in its own chat with one document, so two of them can never rewrite the same thing 3. add a third only when you can say what it owns without repeating a job that is already taken save this, then open the piece below: what one hired helper is really worth, and the point where the next one starts taking it back ↓show more

The next iPhone will cost more, and the reason... has almost nothing to do with Apple. The chip that stores your photos cost Apple about 13 dollars last year. This year it runs around 51. Multiply that across every phone, laptop, and console on earth, and you are looking at the first consumer bill for the AI boom, arriving in the pocket of someone who never asked for it. Tim Cook, who has run Apple's supply chain for forty years, called it a hundred-year flood, something he has never seen. Memory prices have quadrupled in places. The cause is brutally simple. AI data centers are now expected to swallow roughly 70 percent of the world's memory production this year. Seven chips in ten go to server farms. Phones, cars, and laptops fight over the three that are left. This is one force wearing two faces. The same AI demand making the device in your hand more expensive is minting record fortunes for the handful of companies that feed it. Memory makers in Seoul just hit all-time highs in the same week Apple warned you to brace for higher prices. The shortage and the windfall are the identical event, seen from opposite ends. Then comes the part almost no one traces all the way down. Beneath the chips sit rare earth minerals, and one country controls them. China processes around 90 percent of the world's rare earths and makes roughly 94 percent of the high-performance magnets that spin inside every fab and cooling system. The polishing compound that finishes a wafer, the magnets in the machines that build it, run through Beijing. And through 2025, China has been turning that grip into leverage, licensing what leaves. So the chain is complete. AI wants memory, memory needs minerals, and the minerals answer to one government. The price of your phone is now a foreign policy.show more

I just built a Meta Ads diagnostic in Claude... Code that tells you WHY your account broke, not just what changed 🤯 It spins up a team of agents that each investigate a different reason performance dropped, then argue against each other to kill the wrong answer before it ever reaches you. All inside Claude Code. Perfect for DTC brands and agencies who panic-kill creative the second CPA spikes. If you've watched ROAS fall off a cliff and opened Ads Manager with ten tabs going, you already know what happens next. Your gut says "creative fatigue." You kill your best-performing ad. A week later performance is still broken, because that was never the problem. Guessing wrong is the most expensive move in paid social. This workflow ends the guessing: → One agent investigates each competing theory — creative fatigue, budget and delivery changes, traffic quality, offer and seasonality → Each one is blind to the others, reasoning only from its own slice of the data so they can't bias each other → A refuter agent then attacks every surviving theory and tries to kill it → A theory only stands if the data can't disprove it → You get a ranked diagnosis: the real cause, the evidence for and against it, and the one move to make this week No anchoring on the first obvious answer. No killing winning creative on a hunch. No "here's what happened" reports that never tell you why. What you get: → Every theory tested in parallel instead of one biased guess → An adversarial pass that kills the wrong answer before you act on it → A ranked diagnosis with confidence levels and evidence both ways → A reusable workflow you drop next month's export into and re-run Built 100% in Claude Code with the new dynamic workflows. The first account I ran it on looked like textbook creative fatigue. The workflow disagreed, and traced the real cause to a budget change that had doubled spend and flooded delivery with junk traffic. I put together a full playbook with the exact workflow, the prompt, and how to run it on your own account. Want it for free? > Like this post > Comment "META" And I'll send it over (must be following so I can DM)show more

The Puppy Who Refused to Let Go I walked... into the shelter with $50 and enough money to save only ONE dog. Then I saw two terrified puppies clinging to each other-and learned one of them might not survive the night. What happened next is the reason I still believe some families are found by accident. The county shelter was overflowing that afternoon. Every kennel was full. Volunteers were rushing from one emergency to another. Barking echoed through the crowded hallway, but underneath all that noise, there was something else... Fear. Then I reached Kennel 12. Two six-month-old Pit Bull puppies were curled tightly together on a worn plastic bed. One was chocolate brown. The other was mostly white with a few tan patches. They weren't just sleeping beside each other. They were holding onto each other like their lives depended on it. A volunteer stopped beside me. "The brown one already has a foster lined up," she whispered. Then she looked at the white puppy. "But he doesn't."She hesitated. "We're completely full. They have to be separated today. If nobody adopts the white one..." She didn't finish the sentence. She didn't need to. Tomorrow could be his last day. I watched as she opened the kennel and reached for the brown puppy. That's when the white puppy panicked. He threw his tiny body against his brother, buried his face into his fur, and let out a heartbreaking cry. It was as if he was saying: "Please don't take him. He's all I have." I couldn't move. These weren't the dangerous dogs people had warned me about. They were babies. Two frightened puppies who had survived everything together-and were about to lose each other because there simply wasn't enough room. I stepped away. Pulled out my phone. Opened my savings account. And transferred the money. Then I walked back to the volunteer. "I'll take both." She stared at me. "Both?" I nodded. "Both." At first, I told myself I was only going to foster them. Just until someone found a family willing to keep them together. But deep down, I already knew. They weren't leaving. Today is their Gotcha Day anniversary. And those two puppies who once clung together on a cold shelter bed now sleep beside each other every night on my couch. They still curl up exactly the same way. Only now, they're safe. They have food. They have warmth. They have toys. And most importantly... They still have each other. They have toys. And most importantly... They still have each other. I walked into that shelter thinking I was going to save one dog. Instead, two little brothers changed my entire life. And every time I see them sleeping together, I remember that afternoon. The kennel. The fear in their eyes. The desperate cry. And the decision that changed everything. Sometimes, you don't choose your family. Sometimes, your family finds you.show more

sorry, they just did WHAT someone gave a machine... one disease name, the leading cause of blindness in the developed world with 1.5 million americans already in its path, and it came back pointing at a drug that has sat in pharmacies for years under a different label: 551 papers read in 30 minutes against the 294 hours a human would have needed, and the loop that did it is public on GitHub most agent setups answer one question at a time, so the ceiling on the work is the quality of the question you happened to think of this one was handed a single question and wrote the second one itself. turns out that follow-up is where the real find was: a target called ABCA1, upregulated threefold, in an experiment no human ordered i read the whole paper looking for the trick, and the trick is structural. that is the second question, and it is the gap between an assistant and a factory: - hand the loop a field rather than a task: it was given a disease, and choosing the mechanism was part of its job - make it rank before it spends: 151 papers in, ten candidate mechanisms out, scored against each other before anything touched a bench - split reading from judging, so the agent that forms the theory is a different agent from the one grading it - close every cycle on physical reality: the verdict was an experiment, and another model's opinion was never allowed to stand in for one - feed each result back as the next question rather than a log line, which is the step almost nobody builds - search what already passed inspection first: the winner was an approved compound with a safety file already on record - write down what the round learned before opening the next one, so round two starts where round one stopped my read, and i think it is the uncomfortable one: reading was the entire bottleneck in that field, and everybody spent the decade optimising the writing. people ran every physical experiment here, the analysis agent needs a domain expert writing its prompts, and the authors decline to call this the leap it resembles. the thinking got replaced, and the hands did not so the question i cannot answer for my own setup: which step of your loop still stops dead until you sit down and type something bookmark this one. the four parts that turn one model into a line that runs like this, the queue, the rooms, the write permissions and the gate, are built file by file in the piece below ↓show more