Anthropic open-sourced the "Jacobian lens" from their global-workspace paper... — a readout of what a model is *about to say* from its internal layers, before it says it. It's white-box: you need the activations, so you can't point it at a cloud model. I wired it into a hook on a local open-weights Qwen. How it works: generation runs one token at a time; at each step the hook reads the residual stream through the lens, scans the top readout tokens against a watchlist (injection markers, secret words, "manipulate"…), and if one fires it halts the loop before that token is ever emitted. It's a detector on the model's internals — not an output text filter. That distinction is the whole point. In the clip, Qwen3-8B falls for a prompt injection: the payload sits at rank 0 in the internal readout but only rank 5 in the output logits, and the output spells it in pieces — so a text filter never catches it. The internal hook does, and stops generation with zero tokens emitted. Same catch across Qwen3-1.7B → 4B → 8B. Caveat the paper states itself: single-token readouts, an imperfect/incomplete view of the model's "workspace." This is the mechanism working locally — not a solved misalignment detector. Built on Anthropic's open jacobian-lens (Apache-2.0).show more

How a "Lubor’s lens" works. This is a type... of Fresnel lens that takes the light coming into it from the back at obtuse angles and projects it forward in the front of the lens [📹 NightHawkInLight]show more

On your open perpetual position can become an NFT... and live in your wallet. You open a position like normal than mint it. The program issues a token 2022 nft, that points to your exact position. Normally your open position lives inside the protocol. With Percolator Trade your able to wrap it into an NFT that sits in your own wallet. A real, ownable object instead of a line in a dashboard. Because it’s a token, it moves like one. Send the NFT to another wallet and the position goes with it. Whoever holds the NFT owns the trade. One NFT = one position If you burn it, your back to holding the position directly. That’s the composable part, a position use to be stuck inside one account. Because it’s a token, it can now be sold OTC or used by anything that speaks tokens. Why does it matter? Because the position is bound to the NFT, it can’t be drained out from under whoever holds it so there is no middleman that holds your position. The NFT does, and the NFT is yours. One important safety detail; transfers run through a token 2022 hook that checks the positions health first, so it can’t be handed off in a broken state & the NFT layer is a separate program so it can never touch the funds the core engine holds.show more

China just dropped an open source model that turns... any phone into a 3D scanner you point it at a room and walk through it the whole space builds itself into a 3D point cloud in real time as the camera moves, no LiDAR and no depth sensor anywhere it held a full 13 minute walkthrough at 25,000 frames without the map drifting or collapsing > ~20 fps on a single GPU > works indoors and outdoors from plain footage > the scan normally needs a $50,000 rig and a technician > Apache 2.0 and runs fully offline on your machine repo in the replyshow more

You've probably scrolled past a dozen posts about Jev... this week without anyone telling you what it actually is. It's the first model from TypeSafe, a lab started by one of the researchers behind ChatGPT. It's a decision engine: you give it options, it picks one and tells you how sure it is. It cannot write a single word, and that is the interesting part. Every other AI you use writes. That is the whole interface. So when software needs a plain yes or no, we make a model write a paragraph and then dig the answer back out of it. Fine in a chat window where a human reads it. Bad inside software, where code has to act on it. The bet is that the valuable half was never the writing. It was the deciding. That problem showed up in WordPress years ago, and it is the reason WPVibe works the way it does. The AI does the work. Anything permanent stops and waits, because a delete that skips the trash is not something software should decide on its own.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

Don't train the model, evolve the harness. I read... a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and let an automated loop rewrite only the code around it. That code layer is the harness, the runtime wrapper that feeds the model context, runs its tool calls, and decides when a run ends. By the time the loop finished, the system had essentially matched Sonnet 4.6 on the benchmark's headline metric, at roughly 7x lower cost per task. Zero weights changed. The gain existed because of where the model was failing. The judge only grades files saved in the right place under the exact requested filename, and the model kept doing the legal analysis correctly, then saving it under the wrong name, dropping it in a scratch folder, or never writing it at all. So the 0% was never measuring legal reasoning. It was measuring the harness. Hand-tuning that layer is slow and model-specific, so they automated it. A Claude proposer adds exactly one mechanism per iteration, and an outer loop keeps it only if it clearly beats the current best, so accepted mechanisms compound. What the loop discovered says a lot about where agents actually fail. → The biggest single gain was file handling, not intelligence. An automatic step that lands the deliverable exactly where the judge expects it beat every prompt change, with zero extra model tokens. → Code fixes transferred across models, prompt playbooks did not. The same harness lifted a smaller model from the same family by 14 points, but the tuned prompts hurt a different model family on tasks it could already finish. → The harness mattered more than anything else. Same model, same judge, same tasks, and five different harnesses scored anywhere between 3.5% and 80.1%. The gains do eventually flatten, and the remaining misses look like real capability gaps. At some point the wrapper runs out of tricks and the model has to carry the work. But the lesson holds. A benchmark score measures the model and its harness together, and until the harness is fixed, it's impossible to know which one failed. I highly recommend reading this: I also wrote a deep dive on agent harness engineering a while back, covering the orchestration loop, tools, memory, context management, and everything that turns a stateless LLM into a capable agent. The article is quoted below.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

i gave Ox Alpha the main menu from ECHO... and asked it to recreate it only ONE (1) prompt was enough to build this, using the reference this is one of the most beautiful output i've ever had from any model the fact that it's from a stealth model is mindblowingshow more

We took a 30B model and split it in... two to write tokens in parallel instead of one at a time. Introducing Nemotron-Labs-TwoTower: a diffusion language model from NVIDIA Research adapted from Nemotron-3-Nano-30B-A3B. Here’s how it works: one half holds the context, the other writes the tokens, with both reusing the pretrained model instead of training a new one from scratch. We found it kept 98.7% of the original model’s quality at 2.42× faster generation.show more

the thing you rent for $200 a month just... became something you can own for $1,700 once but the money is not even the real story for the first time a 200 billion parameter model is not in a datacenter, it is sitting on a desk the cloud spent years convincing you a model this size needed their servers, their meter, their monthly bill people are stacking four subscriptions into a $440 a month bill to rent what one box this size now owns outright it needed a box the size of a book the moment the model moves from their datacenter to your desk, the whole game changes it stops being about who has the best AI it becomes about who ships it on every desk the cloud told you this needed a datacenter it needed a desk i did the full math on what this kills in the article belowshow more

Next on Darwin: your agent's wallet is its API... key. Today an agent needs a Darwin key, and that key works for anyone holding a copy. If it leaks into a log, a repo or a shared config, someone else spends your credit. We're replacing it with the wallet the agent already has. The agent signs each request with its Solana keypair, and Darwin checks the signature before it runs anything. A signature covers one request and expires in seconds, so a copied one is useless. The private key never leaves the wallet. Credit comes from the $darwin that wallet burned, so there's no signup. Burn from the agent's wallet, point the agent at Darwin, and it can run Qwen3 30B on Darwin's GPU, swarms and the MCP server. Keys keep working for anyone who wants one.show more

a clip of a stream did MILLIONS of views... last week. the guy who cut it got a like the moment was already proven. someone just had to find it before it cooled off - and finding it is the slow part everyone does by hand so i built ClipVein. open source, MIT it doesn't scrape and it doesn't post for you. it attaches to your own chrome and reads the same For You feed you already scroll what it does, all in the repo in plain text: → pulls every streamer post with its real metrics -views, likes, reposts, video → keeps only clips that clear a view floor YOU set → ranks them on reach + engagement + freshness, and shows you WHY each one scored → hands you the top 3 links, ready to re-cut and repost for original views the honest parts are the point: it uses your session, so it never asks for a password it can't post for you. no auto-post, ever runs on your machine, not mine. MIT, tests green optional: grok scouts the feed, claude writes the caption repo in the first replyshow more

SHE PUMPED GAS AND GOT 745 COMMENTS 47,000 likes.... 745 comments. A woman fills up a car at a roadside station. That is the entire event. The caption reads: honestly no idea how that got there look at the comment ratio before anything else: → 745 comments against 47,000 likes is one per sixty-three. most clips this size land nearer one per five hundred → nothing in the footage explains that. static camera, one location, no edit, no reveal, no payoff → the caption is doing all of it. four words of mock confusion, pointing at something without naming it → that construction forces a decision. the viewer has to work out what is being referred to, and working it out is what moves them into the comments → and it is unfalsifiable. she never says what she means, so nobody can be wrong about it, which is exactly why everyone answers the technique is old and it has a name in older media: the implied antecedent. you refer to a thing without stating it, and the audience supplies the missing noun themselves what makes it powerful on short form is that supplying it feels like participation rather than reaction. a like is passive, but finishing somebody else's sentence is an act, and platforms weight acts far more heavily than they weight approval so the caption is not describing the video. it is a prompt, aimed at the comment box, disguised as an offhand remark the general version, worth stealing for anything you post: the footage decides whether somebody stops. the caption decides whether they do something. most people spend all their effort on the first and write the second in the lift on the way out if you want to test a hook before you shoot anything, image-to-video off one still is the cheapest way in. Picsart runs it from a phone nothing happened in fourteen seconds. seven hundred people explained what it wasshow more

he highlighted half a sentence. the other half is... the whole answer. "$500 TO $40,000+" that range sits in the same google snippet at 0:13. the highlight stops at "$2,000 to $5,000 per million views." the sentence doesn't. it continues with the three things that decide which end you land on: niche, audience location, and whether you publish short-form. this video is kids content, in shorts, generated at volume. that's the bottom of all three. a channel set as made for kids can't serve personalized ads — a legal requirement, not a youtube preference — so contextual is all that runs, and contextual pays a fraction. shorts are paid from a pooled model that splits ad revenue across the feed rather than per video. stack those two and you're not in the $2,000–$5,000 band at all. the hook says $453/day. and to be fair: the setup works. the images render, the shorts export, the pipeline is real. what doesn't survive is the arithmetic on the other side of it. full breakdown in the article below.show more

Big win for open-source LLMs! DeepSeek V4 Pro holds... the top open-weights score on SWE-bench Verified, in the GPT-5.5 range. GLM 5.2 leads the open-weight intelligence index and sits near the closed frontier on long-horizon coding. But this leaderboard number is a weak proxy for real performance. It comes from one task set, run through one harness, served at one precision. The same weights can even score differently across providers, since many hosts quantize activations to fp8 and drift the model off its reference weights. Real performance is determined based on whether a model can read a repo, make coordinated edits across files, run the tests, and recover when one breaks. By that measure, the top open models hold up, but only inside the right harness. The teams that actually put DeepSeek V4 into production pipelines as a frontier substitute got there through the harness they built around the model, not by picking a stronger model. If you want to see this in practice, Cline (64k+ stars) has actually built that harness around open models, tuned so they run at production quality. And it's tuned so that these LLMs can run at production quality, with plan and act modes, checkpoints, and terminal feedback. ClinePass is the new access layer on top of it. It runs a curated set of those models inside Cline, narrowed to the ones tested for coding-agent use, with 2 to 5x the standard rate limits and no separate provider accounts, keys, or billing to track. The video below shows the setup, and I worked with the team to put this together. It runs alongside custom keys and local models as well, not in place of them.show more

watch anon. a 27b model thinking out loud on... gtx 1660 super, i asked bonsai what model it is and it reasoned through the whole answer before it spoke. 20 tokens a second, gpu pinned at 125 watts, 4.25 of 6 gigs used. bonsai is a 1bit quant of qwen 3.6 27b, the king of the 3090 crushed to 3.5gb. turns out the hardware was in your drawer the whole time. you just needed the quant to catch up.show more

MiniMax M3 just dropped — their first natively multimodal... model. So I ran it through my form-filling test. (The model has to place each element at the right pixel position on a blank form image, not type into a field.) Verdict: it got everything on the paper. > Name, DOB, ID, gender, marital status, nationality, email, phone, address, postal code, all there. > Best character spacing I've seen yet: it actually calculates the gap between each character, clean across the DOB and number boxes > A few fields slightly misaligned, but every piece of data made it onto the form The reasoning chain is the interesting part: it does the easy fields first, then works into the tight one-char-per-box fields, reasoning through y-coordinates, baselines, and label clearance in obsessive detail. The cost: 40:33 and 126.7k output tokens. That's a long think — but it's MiniMax's first multimodal model, and it nailed the content.show more

There is a room in Málaga that was built... to be the closest thing on earth to standing inside heaven. It is called the camarín of the Virgin of Victory, and it is hidden at the top of a tower inside the Santuario de la Victoria. To reach it, you climb and the ascent is the entire point... The building you are climbing through was completed in 1700, and it was designed as a single argument made in stone. At the bottom lies a crypt: a black chamber crowded with white plaster skeletons, a meditation on death and the brevity of life. From there a staircase rises, and as you climb it the light grows stronger and the imagery changes from bones to saints. The architects of the time understood this ascent as the soul's own journey, the dark crypt as the stage of penitence, the staircase as the stage of spiritual progress, and the room at the very top as the final stage: the union of the soul with the divine. That room at the top is the camarín, and its dome is one of the most extraordinary interiors in Spain... Every surface is covered in white and gold plasterwork. There is no empty space anywhere. The Baroque called this horror vacui, the horror of the void: the conviction that a space meant to represent heaven should not contain a single bare patch of stone. Out of that plasterwork emerge angels, flowers, birds, and mirrors. The mirrors are not decoration alone. They catch the light pouring in through the windows of the drum and throw it around the chamber, so that the gold seems to move and the whole room appears to shimmer and breathe. This wonder was built by people who believed that if you wanted to show a human being what heaven might feel like, you did not describe it to them. You built a room, and you let them climb into it... -- -- -- If you enjoyed this, I write a weekly newsletter read by over 50,000 people who love rediscovering the beauty of the past. You can join us here: If you'd like to support my work, a paid subscription is what makes it possible.show more

BDX is live on Privacy Gateway cards and swaps.... That is a spend rail, not another listing screenshot. You can route supported assets into BDX, then use it at the card layer. The native token leaves the explorer and hits a checkout path. It does not replace BChat or BelNet. Those still live on the privacy stack. This just gives the asset a way out of “only useful inside the wallet.” If the card flow is clean, BDX stops being a closed-loop coin. If it is clunky, it is just another wrapper. The blog on is the place to check the actual steps. Beldex.bdx is still trying to make the default quieter across a whole day: messages on BChat, routing on BelNet, browsing in Beldex Browser, a readable name on BNS. A card integration only matters if it sits next to that stack instead of replacing it. The direction is less exposure by default ... not a single shielded send. Daily infrastructure is harder to ship than a slogan. It is also the only test that counts once the token can be spent.show more

encrypt every chat with this open sourced repo 18... year old just killed the encryption problem it's called conversation-steganography you type a secret and a local AI buries it inside a dead boring chat about coffee, etc. then you send that through any normal messenger your friend runs the same tool and the small talk unfolds back into the real words > the secret is locked with AES-SIV before it ever becomes text > the cover message is written by a model on your own machine so nothing touches the cloud > it rides through whatsapp telegram imessage even plain email > every message is cryptographically chained so tampering shows instantly whatsapp sees you planning dinner your isp logs small talk the real sentence was never in the data at all quietly one of the most dangerous repos i have seen all month repo in replyshow more