@yulmu_coffee BOZO SCORE 98.9 / 100 종결 BOZO · 남의 글 전달자 팔이 █████████░ 94 정신승
@yulmu_coffee BOZO SCORE 98.9 / 100 종결 BOZO · 남의 글 전달자 팔이 █████████░ 94 정신승리 █████████░ 89 자아 █████████░ 91 공허 ██████████ 100 형식 ██████████ 98 "남의 트윗만 옮겼다. 본인 의견은
Crawled from X, GitHub, blogs, and docs. Jev classifies, de-duplicates, and ranks. Every row links back to the original source.
Fresh crawls from X, GitHub, and the web. Newest first.
@yulmu_coffee BOZO SCORE 98.9 / 100 종결 BOZO · 남의 글 전달자 팔이 █████████░ 94 정신승리 █████████░ 89 자아 █████████░ 91 공허 ██████████ 100 형식 ██████████ 98 "남의 트윗만 옮겼다. 본인 의견은
@redp314 @typesafeai Not sure Jev has the reasoning prowess to review a PR, sure it generates probability fast but those probabilities are poorly calibrated
@mvanhorn @typesafeai Jev did something nutz . We can now cross channel communicate across slack, email, claw control panel, code editors… the same information, context and CONVERS
JEVINIK - Evaluating stocks insanely fast with @typesafeai's Jev It pulls market data, signals, risk & filings around any stock, then calls the next 30 days: 🐂 BULLISH 🐻 BE
@mikegee @typesafeai How do you pass visual information to Jev ? It seems to work with text only based on documentation?
@alz_zyd_ Hopefully Jev by @typesafeai will help enforce some discipline. I’ve been thinking about this new idea of setting Decision as the primitive, rather than tokens. It might
@JustLingonberry @agent_device @typesafeai No OCR. agent device returns the accessibility tree and this library sends it to Jev as JSON
@obie @typesafeai Jev is genuinely interesting. It compresses a workflow we’ve spent decades doing in data science, including building a clean dataset, training a classification o
Now you can try jev from @typesafeai yourself on your least favorite platform: LinkedIn. Try it now (sponsored by me for now): https://t.co/ndNFEGbAdi https://t.co/JsrvMcBC1R
Helpful observations if you're building on @typesafeai jev: 🎲 It is not deterministic. 🎢 Reordering choices shifts confidence (I saw ~26%). ⛔️ At a confidence target, ordering
@AbdelStark @typesafeai isn't jev whatever @ylecun was trying to achieve through JePas?
Most teams still use frontier models like a smarter intern. @typesafeai Jev is closer to a function. You don’t ask it to “think about the ticket.” You ask: urgent? billing? needs h
Corent’s brain uses @typesafeai Jev now. Not to generate the output, to make the decision before the output gets generated. When a request comes into Corent, you don’t need to te
@unicodeveloper @typesafeai jev 🤝 us
@flarrs315 BOZO SCORE 91.7 / 100 종결 BOZO · 수익률 찡찡이 팔이 ████████░░ 78 정신승리 ██████████ 98 자아 █████████░ 92 공허 █████████░ 89 형식 █████████░ 91 "걍 찡찡거리는 병신" @typesafea
@lancehasson @typesafeai Yes! I actually started building it so that it exposes all in game actions via MCP / API so anyone can connect their agents to it. Then Jev came out and
@DSJayatillake @typesafeai I think Jev will be useful for sprinkling around the use cases and harnesses. not a full replacement at all. like, why can't Jev be part of a precommit
e2e + jev from @typesafeai ⚡ I'm building an open-source framework for running e2e tests with agents. supports web, mobile (and more!) available soon: https://t.co/G3XB2L8tiC htt
@ShenSeanChen @bot @Muse @SpaceXAI @AIatMeta @alexandr_wang Have you tried Jev by @typesafeai yet.
i don’t think i’ve had my feed ever stuck on one topic as much as the past 3 days with jev and @typesafeai . incredible motion