First Jev use case published live on Bannerbear! Instant... field mapping between template and source, when names are slightly different eg template - photo - name - company_name data source (eg Airtable) - avatar - full_name - business Jev figures it out in one click.show more

Jev dropped and people immediately started doing stupid sh*t... with it people gave this thing trading bots, browsers, Doom, drones, dinosaurs and tax forms and basically said: “you decide.” here’s what happened: > jev-trader Jev gets a new Monad block every ~300ms and decides whether to place a live limit order. no essay. just the decision. 1,911 stars ▸ ⁠ > jev-ultrafast a browser agent where Jev decides every click. the text model only wakes up when something actually needs to be written. 16,758 stars ▸ ⁠ > jev-doom-agent someone compiled actual Chocolate Doom to WebAssembly and let Jev make the tactical decisions every frame. yes. Doom. ▸ ⁠ > jev-t-rex-runner remember that stupid Chrome dinosaur? now Jev plays it. jump → duck → run → repeat ▸ ⁠ > typesafe-chess Jev went against a real chess search engine. two games. colors swapped. the search engine won both — and overruled Jev’s first instinct on roughly half the moves. ▸ ⁠ > jev-drone camera → Jev → drone. a simulated quadrotor has to clear five stations while Jev looks at the situation twice a second and decides what happens next. ▸ ⁠ > tax-doc-classifier then someone gave it IRS forms. 261 documents. 100% strict accuracy. roughly $0.001/page. ▸ ⁠ > killmyidea this one is evil lol tell it your startup idea. Jev looks at it from different angles and gives you: KILL / FIX / SHIP ▸ ⁠ > jev-curate throw huge Parquet / JSONL datasets at it. Jev judges 1,500+ rows/sec and keeps only the stuff that passes your rules. ▸ ⁠ > pg-jev and now it’s inside PostgreSQL. ask questions about your own tables in plain English → get the decision back. ▸ ⁠ and this is the weird part: none of these need Jev to write you a beautiful paragraph. they need it to look at a situation and pick: BUY / WAIT CLICK A / CLICK B JUMP / DUCK KILL / FIX / SHIP KEEP / DROP that’s basically the whole Jev idea. LLMs think and write. Jev decides. code does. full setup + my three-question Jev test belowshow more

This prompt is super useful for human resources. One... Excel template with 30 fully encrypted PDF payslip links. When the number changes in Excel, it updates in the PDF. Kimi literally created a template and workflow for you to automate your work. Prompt: Generate 30 individual PDF pay slips from the master list. 1. Design (Template): Do not just print the row. Apply a formal 'Corporate Letterhead' template to each PDF (Company name at top, distinct 'Earnings' vs 'Deductions' sections, grey footer). 2. Logic (Security): Password protect each PDF using the employee's ID last 4 digits. 3. File Logic: Name each file strictly as [Dept]_[Name]_[Month].pdf. Create a summary Excel sheet with hyperlinks to all 30 local files for easy checking. Ensure all data and exhibits are fully consistent between Excel and PDF files. The company name is Radiohead.show more

Jev + GrokBot is the best AI agent system... I’ve built in my life It just made my setup CHEAPER and FASTER than what 95% of people are running... setup takes literally 7 minutes: prompt → GrokBot → Jev decision → GrokBot execution → result step 1 → open TypeSafe AI , create API key (keep it off chat paste) step 2 → tell Grok Bot: store TYPESAFE_API_KEY in the secure field step 3 → prompt Grok Bot: install typesafe-sdk on Agent Computer + smoke system_one (Choice) step 4 → tell Grok Bot: build the usage lab (router, dry-run, config, logs) - or clone Github below step 5 → add skill jev-usage-router: before browser / research / retry / extra bot → call the router, honor action step 6 → stay shadow first, read logs, then active when you trust it - kill switch: bypass jev or enabled: false step 7 → flip active: GrokBot obeys route - Jev decides - GrokBot executes - humans control irreversible actions the result: Jev + GrokBot the best and fastest agent running directly on your computer rn, I’ve already tested it on routine tasks - and the results are genuinely incredible You can come up with endless ways to use Jev + GrokBot - but the most important thing is to install it as soon as possible Copy this 2028 setup, explore my repo below - then read the full Jev deep dive ↓show more

🚨 One photo of your face. That's all someone... needs to become you on a live video call. In real time. Right now. The tool is free and open source. It's called Deep-Live-Cam. One image. One click. You become anyone on a live webcam feed. No training. No datasets. No waiting. Instant. Your face. Your expressions. Your mouth movements. All stolen from a single photo. Here's what this thing does: → Upload one photo of any face → Turn on your webcam → You are now that person. Live. In real time. → It matches your pose, your expressions, even your lighting → Mouth masking so the swapped face moves its lips when you talk → Multi-face mapping. Swap different faces on different people in the same call. → Virtual camera output. Plug it into Zoom, Google Meet, Teams. Nobody knows. → Works on NVIDIA, AMD, Intel, and Apple Silicon Here's the part that should terrify you: Your boss could be on a Zoom call with someone wearing your face right now. A scammer could call your parents looking exactly like you. A stranger could take your LinkedIn photo and become you in a video meeting. IShowSpeed's reaction when he saw it: "What the F**! This shit is crazy!" SomeOrdinaryGamers: "That's fucking freaky dude... that's so wild." This was the #1 trending repo on GitHub the day it launched. 1,600 stars in 24 hours. 80K+ stars today. No one is ready for what this means. And it's already out there. 100% Open Source.show more

Found a great production use case for Jev. I... used Jev to organize ~2.3K AI research papers. The total cost was $0.14, and it took about 83 seconds. The process: The papers already had old tags, which I ran through a previous open model (DeepSeek V4 Flash). However, I wasn't confident in the classifications, and I didn't want to spend more on tokens unless I spent time tuning it into a good LLM classifier via few-shot (more expensive). Too tedious, too costly, and unsustainable. Luckily for us, we now have Jev to help us with organizing papers better. So Jev first went through all the papers and retagged them. It agreed with 75% of the previous tags. Jev found about 579 high-confidence topic changes. I evaluated reliability by manually labeling 30 disagreements and accepted all of them. I was astonished by Jev's classification capabilities. We applied and verified all changes in production. I'm much more satisfied with the classifications, but I think there is still room for improvement. Check out the papers here: I will experiment with Jev more. The takeaway is that pipelines can be significantly improved by carefully combining System One and System Two models. Jev clearly unlocks more interesting ways to organize papers and offer a more useful discovery layer for research papers. More updates on that soon.show more

this is pure f*cking treasure TypeSafeAI engineers spelled out... in their docs exactly how Jev fits inside an agent, and these patterns are perfect one rule behind all of them: the LLM thinks, jev decides, code acts I mapped them into 9 live schemes: > model routing jev picks the cheapest model that can do the step > guardrails screens what your agent reads before it acts > tool-call gating every tool call gets allow, ask or deny before it runs > inbox triage the agent only opens what actually needs a reply > reranking jev scores 30 passages, the agent gets the best two > llm evals grades the output and sends it back if it falls short > bulk labeling one question fanned out over a huge table, the agent reads the counts > real-time control games, bots, trading loops: a decision every tick > confidence gate act, confirm or hand it to a human. your code sets the thresholds, not the LLM why it works: > ~100 ms per decision > $0.042 per 1M input tokens, output tokens free > calibrated probabilities on every answer one LLM does the thinking. jev makes the thousand small calls in between save this before you wire your next agentshow more

Top 12 agentic use cases for Jev: (bookmark this)... Jev handles semantic decisions that ordinary code cannot express reliably. It returns typed answers and probabilities, while code continues to cover the workflow. Here are 12 practical use cases for Jev: 1. Browser next action > Convert the current DOM state into a bounded action such as click, type, or stop. Code executes only valid operation-target pairs. There are already several open-source Jev web agents. 2. Context compaction > Decide which events from a long agent trace should remain. The selected text stays verbatim instead of being replaced with a generated summary. 3. Skill and context loading > Compare the current user turn against the available skills. Load only the instructions needed for that turn instead of filling the context window with every skill. 4. Typed tool-call compilation > Map a natural-language request to a function and fill its typed arguments. Each argument is evaluated separately before code allows execution. 5. Citation verification > Check whether a quoted passage exists and whether the surrounding evidence supports the claim. The output can be supported, unsupported, or contradicted. 6. Extraction verification > Run a cheap extractor first, then use Jev to verify questionable fields. Clean records stay on the fast path while uncertain ones reach a reasoning model. 7. Agent trace evaluation > Turn raw trajectories into queryable labels such as progress and repetition. This avoids asking another LLM to write a full review of every run. 8. Semantic regression tests > Replay a trace suite against a new agent build. Semantic checks can then pass or block prompt, model, tool, and policy changes in CI. 9. Jevgrep code search > Search a codebase by what the code does rather than its exact words. Jev scores candidate snippets and returns the most relevant code first. 10. Entity alignment > Compare two candidate records and decide whether to merge, review, or keep them separate. Candidate generation remains deterministic while Jev handles semantic identity. 11. Retrieval reranking > Let embeddings retrieve a broad candidate set, then use Jev to reorder passages by relevance. The generation model receives the most useful evidence first. 12. Memory promotion gate > Capture a completed agent trace, then judge whether its corrections contain a reusable lesson. Trace-backed lessons can be promoted while task-specific noise is discarded. If you want to see the final pattern in practice, it is already implemented in the Beacon open-source project. Beacon captures full sessions across Claude Code, Codex, Cursor, OpenCode, and 20+ agent harnesses, and then Jev identifies which workflows and corrections are worth learning from, so that a lesson discovered by one agent can become available to the others. GitHub repo: (don’t forget to star it ⭐) If you want to dive deeper, I also wrote about a similar mechanism in a hands-on guide. It covers building a Jev-style decision path with open models, entirely locally. Read it below.show more

you should spend some time connecting jev to an... AI employee like viktor... the goal is to get back work that needs fewer corrections from you. here's the setup: -> give viktor a goal and the source material. he figures out the steps, researches, uses your connected tools and produces the draft -> jev handles the evaluation. give it a specific requirement, the relevant evidence and a section of the draft. it returns a structured judgment with probabilities and confidence -> work that meets your criteria comes back for your review. fixable issues go back to viktor with the requirement he needs to address, then through the checks again -> uncertain judgments and missing evidence come to you. those are the decisions worth your attention instead of another round of “please check everything” -> apply it to your content... does the opening promise something useful, do the five posts actually say different things, did the draft invent a claim about something you tested -> if the source only supports three useful posts, the system should flag that instead of inventing two more. cap the revision rounds so it knows when to stop and ask -> save the corrections you approve in viktor’s working guide. the next assignment starts with those instructions already in place viktor creates. jev evaluates. your feedback improves the next assignment. the full setup is in the article below.show more

MOST PEOPLE WHO BUILD WEBSITES USE CLAUDE CODE THE... WRONG WAY A few people train it properly and get the bottom one. The difference is not the model. It is the skills you feed it. Regular Claude without web-design systems produces clean but average product pages. The same Claude, loaded with the right skills, starts delivering sites that look like they cost $5,000. Those skills are free right now. They live on GitHub. The exact names sit in the article below. One set of prompts. One trained workflow. Suddenly every luxury brand page you build stops looking like a template and starts looking like money.show more

Macy's on 34th in NYC . It was reported... that a group of migrant gang members were allegedly shoplifting at the name-brand shop when they said the person recording the attacked the person. This is an ongoing issue at Macy's and other shops across NYC. The way this works is they send out crews to shoplift, then the stolen products are them sold by a different group . This is very organized and are making tons of money. ( sent in by a source)show more

THIS ENGINEER SKIPPED 7,862 WORDS OF AI ROADMAP AND... SHIPPED ON A WEEKEND a Pi Zero 2W, an IMX500 camera and a solar panel, that's the whole stack inference runs on-chip so there's no cloud, no latency and no monthly bill Spotted Dove at 0.95, King Parrot at 0.88, runs forever on sun code is open source and the 3D files are free, you just print the case and buy the parts and it works better than most paid wildlife monitoring services out there full video: code (open source): 3D print files: solar power board: save this so you actually have everything in one place when you decide to build itshow more

What happens when you give the most advanced open-source... agent a coin's fees to trade with? | OpenHuman has 41,559 stars on GitHub and trending. It runs 500 agents in one process and decides with jev, a model that returns calibrated odds instead of prose. I went ahead built it a trading floor for these agents. A live room where tiny humans act out real trades on Solana, with team totals and a desk you can follow. I will also be using the coin's fees to fund a separate bankroll. So far I have funded eight scouts more more than 24 hours now, and they have been hard at work. Funded solana Wallets : FNJ77aURP9PPVyRoDc4y11LqMrAzjksacXpuRq7vxKum Cqp8BJqSMoSBLL1XXkybmUGPW3u32TFUF3qBFb9XUzDo GXsJTRrgTnrVJwZCLcQTgCSzG3MoxtTXYHnj1PsTWq1Y 2jR1Gwb62nrwD9SSmtUUtEF1fMJcrT8w4D7W6qr4SuTr GXsPWRhFpcB1Z6fwE2xiAjZkJgqUotqbaPE71WDhgA7b 5xSjNURqSZWbrFYTpo8awZXAjEJpsM8iubUwaN4G8YPj 9pphfYZj5ZXvXY4URtJska7ibuBi7yfXsJnRng5Qcjzd CCCfd1QjUESnifQ4Szwjhz6n7xBFsat5CSP2P9KrKA11 Every trade is onchain. Track their performances here on the terminals :show more

That’s Sr Adv Naidu representing #ElectionCommissionOfIndia & ECI is... proposing to CJI to publish #Bengal #SIR supplementary lists on a daily basis Imagine, the first supplementary list came out at midnight and even after 19 hours we can’t access it - people don’t know who all are deleted and how many made it to the final voter list But before SC - ECI vowing to publish sup list daily!!! Had they published data on a regular basis - as & when matters were adjudicated - had they published data per 1 lakh people basis - they wouldn’t have to release data of 29 lakh people in one go, as they have done - which is of course a heavier file. But CJI laments it’s only in Bengal that SIR is creating so much noiseshow more

MOST PEOPLE WHO BUILD WEBSITES USE CLAUDE CODE THE... WRONG WAY A few people train Claude the right way and get the bottom one. The difference is not the model. It is the skills you feed it. Regular Claude without web-design systems produces clean but average product pages. The same Claude, loaded with the right skills, starts delivering sites that look like they cost $5,000. Dark hero. Cinematic pizza shots. Smooth scroll reveals. Menu cards that feel expensive. Zero templates. Those skills are free right now. They live on GitHub. The exact names sit in the article below. One set of prompts. One trained workflow. Suddenly every food brand page you build stops looking like a template and starts looking like money.show more

🇺🇸 ELON FIRES UP GROK FOR X’S FOLLOWING FEED... AND FLIPS THE FUTURE ON Elon just rolled out the next big switch on X: the Following feed now has a Grok-ranked mode. Same people you follow, but with a smarter sort running underneath it. Update the app and you’ll see the option right away. Tap the Following tab and choose what you want: Grok’s ranked feed or the classic unfiltered chronological stream. One click, instant swap. No drama. It’s the first real taste of X with Grok baked in, and it already moves like a platform built for the future. Source: X Freeze, Muskonomyshow more

NERVE NOW READS EVERY TWEET BEFORE YOU DO. I... ADDED A CT NARRATIVE ANALYZER AND IT CAUGHT A META SHIFT 47 MINUTES BEFORE THE FIRST VIRAL THREAD. +0.9 ETH. the pipeline was fast. jev scores in 190ms. sentinel kills honeypots for free. grok reads telegram and discord. but ct moves faster than all of them. a kol tweets. quote tweets stack. the meta shifts. by the time it hits telegram the entry is gone. so i plugged a twitter narrative analyzer straight into nerve. it does not read individual tweets. it reads the shape of the conversation. > how many unique accounts mentioned this ticker in the last 60 minutes versus the last 6 hours. ratio above 4x means acceleration > are the accounts engaging each other or just posting into the void. reply chains mean real heat. isolated tweets mean paid shills > did the narrative exist 24 hours ago or did it spawn today. new narrative plus volume equals early. old narrative plus volume equals exit > is smart money ct talking about it or lifestyle ct. same ticker, completely different signal the analyzer runs every 3 minutes. outputs a ranked list of accelerating narratives with confidence scores. jev takes it as context and matches against live pools in 190ms. tuesday night the analyzer caught a shift into ai agent tokens 47 minutes before the first thread with 100+ likes. three pools matched the narrative. sentinel cleared all three. jev confirmed. pool 1: +320%. held and trimmed. pool 2: +85%. full exit on the jev downgrade. pool 3: stopped out. clean loss within the limit. +0.9 ETH. the edge was 47 minutes. everyone scrapes tweets. nerve reads what the timeline is about to care about. that is not the same thing.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

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

One of the craziest use cases I’ve found for... Jev: verifiers. I am so excited about this that I at least wanted to share the high-level idea. I used Jev to build a custom verifier for the /goal feature in my agent harness. It checks whether the goal is actually complete after every turn, making continuous verification cheap enough to scale. This means I can run more of these verifiers (previously handled by another expensive reasoning model) more frequently to keep the agents on track. System One models are perfect for verification. I think of this as scaling harnesses further by cleverly combining System One and System Two models. I have a feeling this will enable a new wave of scalable test-time compute methods. Watch this space closely. I've just started to experiment with this and am already seeing really good results. I need to explore and figure out a way to benchmark it. I will share more once I have more results. This is an insane unlock for long-horizon agents. You heard it here first. And you can expect to see more harnesses embracing this new pattern. Full guide dropping in the next couple of days.show more