Wow! Vision Jev can find several objects of the same type!
They told us it couldn't be done, but we have a few tricks up our sleeves hehee
Full disclaimer: Very low performance in crowded or low res conditions.
It is becoming f*cking dangerous: a model that never writes a single word now judges every move your Claude AI agent makes
-> Create a folder named JEV LAB on your PC and launch Claude Code inside it
-> Install the Jev CLI: npm install -g jev-axi
-> Grab a key at console.typesafe.ai and run: jev-axi config set apiKey YOUR_KEY
-> Run jev-axi setup safety so every command Claude runs gets checked first. Dangerous downloads get denied, routine tests pass for free
-> Run jev-axi setup git-hooks to stop any commit that sneaks in a password or API key
-> Feed it anything your agent reads: jev-axi guard < email.txt
Hidden "ignore your previous instructions" tricks get flagged in under half a second
-> Run jev-axi setup supervise --project to catch the moment your agent quits early or gets stuck in a loop
The whole setup takes around 5 minutes
Turn Claude into an agent with a second opinion: every command screened, every page checked for prompt injection, every commit scanned for secrets. For a fraction of a cent per check
Bonus: pipe a broken build into jev-axi triage and it finds the root cause for you
Bookmark this article and check repo below:
github.com/shiftynick/jev…
Here's another JEV TIP in honor of JEVDAY
Jev can answer as many questions as you can fit into context in parallel. You can ask hundreds in one call, and since output is free, why not?
100 questions on a 32k token input document:
~$0.00001 per question
~1ms per question
i don't know anything about it! if i had to guess based on what i know about jev so far -
1. provide as much structured context as possible, rather than either alone
2. model does better with hi res images rn so probably at least 1080px (~512kb-2mb jpegs is sweet spot)
3. escalate to smarter models in cases where jev is not confident, they are slower, but better than getting stuck
4. bounding boxes are still kinda experimental so i would use them as one of several signals what to do rather than go all in on them
5. think a lot and do evals with a coding agent to try and decompose the goal into multiple typesafe calls and programmatic steps rather than shove too much into one step
@shrirambalaji i don't know anything about it! if i had to guess based on what i know about jev so far -
1. provide as much structured context as possible, rather than either alone
2. model does better with hi res images rn so probably at least 1080px (~512kb-2mb jpegs is sweet spot)
3.
77 Followers 815 FollowingDeFi's largest gamified experiment: a recursive flywheel of seven composable mechanics designed for users to create like never before.
157K Followers 57 FollowingXRP is the native token of the XRP Ledger (XRPL), a decentralized blockchain built for payments.
X account managed by @Ripple & @XRPLF. Not investment advice.
409K Followers 26K FollowingHelping the world move value since 2019. Try PayBox today. Title Partner of MoonPay X Games League. Posts here not for UK or EEA users - follow @moonpay_UK!
338 Followers 835 FollowingNot really a code rockstar. More of a code singer/songwriter. Improv / literature / internet poisoned woke millenial
He/Him
Mastodon: @[email protected]
40K Followers 167 FollowingAI infrastructure that developers love 💚
Run inference, sandboxes, batch processing, training, and many other things on Modal
8.5M Followers 385 FollowingUnparalleled reporting and commentary on politics and culture, plus humor and cartoons, fiction and poetry. Get our Daily newsletter: https://t.co/CW0Z2jGCyB
7.5M Followers 3K FollowingPop Base is your best source for all pop culture related entertainment and news. For press inquiries: [email protected] | All other inquiries: [email protected]
157K Followers 79 FollowingSane + 🌶️ takes in an insane AI world... AI capabilities researcher: co-created RLHF/ChatGPT @ @openai now trying to right the wrong 🤭 (ceo @typesafeai)
254K Followers 6K Followingcreator of @moltbook, building at @meta superintelligence labs, talking to AI agents all day :) founded @octaneai @yesnoerror @zapchain, ycs12
392K Followers 4K FollowingCo-founder of @ethereum I CEO of @MetaMask I Chairman of @ConsensysMesh, @Consensys & @Sharplink $SBET. Building on #ETH. Views expressed are my own.