◈Bluesky50
YHacker News50
XX / Twitter50
listening to
Jev
150
mentions
tracked
tracked
net sentiment
+25%
48 positive
92 neutral
10 negative
volume & sentiment over time
Sep 25, 2026 · Daily
sources
most discussed
decision / models
active days
1
what people keep raising
- decision / models 36
- built 15
- models 9
- model 7
- open-source / alternative 4
- performance 3
mentions
Showing 1–25 of 150 mentions
-
X X / Twitter 1w ▲ 0 positiveSeriously, I am now bored with Jev. Its one week of Jev and I think, I am done with experiments and done with slop coming out as Jev + * Blah blah blah 🙌Come on, Silicon Vally AI tech bros, throw something new in the market so that lame fans can cheers 🍻 like as always 🍾 🚀 If you have VC money then spend 💸 to buy mor… Seriously, I am now bored with Jev. Its one week of Jev and I think, I am done with experiments and done with slop coming out as Jev + * Blah blah blah 🙌Come on, Silicon Vally AI tech bros, throw something new in the market so that lame fans can cheers 🍻 like as always 🍾 🚀 If you have VC money then spend 💸 to buy more clothes, make a laughable launch video 🎥 and put that 💩 out, Bros!view source ↗
-
X X / Twitter 1w ▲ 0 positive built@__syumai Loved this, Syumai. I've featured jevyoumean on https://t.co/6rvbCXTB3W, a directory of things people have built with Jev, with a free download and credit to you: https://t.co/TTCy5nk0D5 @__syumai Loved this, Syumai. I've featured jevyoumean on https://t.co/6rvbCXTB3W, a directory of things people have built with Jev, with a free download and credit to you: https://t.co/TTCy5nk0D5view source ↗
-
X X / Twitter 1w ▲ 0 neutral model@marcos_placona @grok @opencode yea dude do it it feels nearly unlimited lol i have a codex setup that asks jev api to suggest a model suited as orchestrator for the task complexity, then that gpt6 luna, sol or astra orchestrator spins up a deepseek 4.1 flash worker on my opencode go plan using codex-router @marcos_placona @grok @opencode yea dude do it it feels nearly unlimited lol i have a codex setup that asks jev api to suggest a model suited as orchestrator for the task complexity, then that gpt6 luna, sol or astra orchestrator spins up a deepseek 4.1 flash worker on my opencode go plan using codex-routerview source ↗
-
X X / Twitter 1w ▲ 0 positive builtOPENAI'S CO-INVENTOR JUST BUILT AN AI MODEL THAT DOES NOT HALLUCINATE his new venture Type-Safe AI launched a model called Jev it runs 200 times faster than what you use now it costs 400 times less to run the big one is that it stops making things up on the spot instead of guessing an answer it checks its own outp… OPENAI'S CO-INVENTOR JUST BUILT AN AI MODEL THAT DOES NOT HALLUCINATE his new venture Type-Safe AI launched a model called Jev it runs 200 times faster than what you use now it costs 400 times less to run the big one is that it stops making things up on the spot instead of guessing an answer it checks its own output against a strict set of rules before it ever gives it to you if the answer cannot be verified it says so instead of inventing a confident lie that single change is what breaks most AI in real work, the made up facts nobody catches until it is too late a model you can trust to say I do not know is worth more than a fast one that bluffs whole industries have been waiting on exactly this before they let AI near anything that matters tomorrow I break down how a verified model like this changes the way you build agents that actually shipview source ↗
-
X X / Twitter 1w ▲ 0 positive@Jchammond_ It's a battle arena where players respond with each game tick with their next move. I haven't tested Jev yet, but my goal is to see how well Jev works vs these deterministic coded bots. https://t.co/I1zJwMI4GD @Jchammond_ It's a battle arena where players respond with each game tick with their next move. I haven't tested Jev yet, but my goal is to see how well Jev works vs these deterministic coded bots. https://t.co/I1zJwMI4GDview source ↗
-
X X / Twitter 1w ▲ 0 neutralFair point: treat Jev's outputs as scores until you've checked them on your own data. `jev batch run --merge` scores a labelled CSV in one run, so you can pick a threshold before gating CI on it. `--abstain-band 0.4,0.6` sends the unsure ones to a person. https://t.co/3MhbPbXlyP Fair point: treat Jev's outputs as scores until you've checked them on your own data. `jev batch run --merge` scores a labelled CSV in one run, so you can pick a threshold before gating CI on it. `--abstain-band 0.4,0.6` sends the unsure ones to a person. https://t.co/3MhbPbXlyPview source ↗
-
X X / Twitter 1w ▲ 0 positive model@morganjingram Yeah see like I’m not even on instinct or muse yet lol But I do way more “real coding” than I thought I’d ever do. Like more deterministic builds less model reasoning. Exploring Jev @morganjingram Yeah see like I’m not even on instinct or muse yet lol But I do way more “real coding” than I thought I’d ever do. Like more deterministic builds less model reasoning. Exploring Jevview source ↗
-
X X / Twitter 1w ▲ 0 positive@suidevelopers Just finished my first side project on Sui. Using Jev to help better understand transactions. https://t.co/KXcx1EU6wL @suidevelopers Just finished my first side project on Sui. Using Jev to help better understand transactions. https://t.co/KXcx1EU6wLview source ↗
-
X X / Twitter 1w ▲ 0 neutral刚知道 JEV/LAYA，这玩意儿能简化我们的分类、采样和数据录入流程，现在只差说服我主管了。 刚知道 JEV/LAYA，这玩意儿能简化我们的分类、采样和数据录入流程，现在只差说服我主管了。view source ↗
-
X X / Twitter 1w ▲ 0 positiveJev Jev Jev Jev 🚀 https://t.co/jDqSTWyR66 Jev Jev Jev Jev 🚀 https://t.co/jDqSTWyR66view source ↗
-
X X / Twitter 1w ▲ 0 positive built@rorzio Loved this, Rory. I've featured your post on https://t.co/6rvbCXTB3W, a directory of things people have built with Jev: https://t.co/nJGM0Xe8kk @rorzio Loved this, Rory. I've featured your post on https://t.co/6rvbCXTB3W, a directory of things people have built with Jev: https://t.co/nJGM0Xe8kkview source ↗
-
X X / Twitter 1w ▲ 0 negativei guess people got afraid to try breaking JEV after seeing max p=0.06 on BEGJEV lol. there is 0.69 ETH there and counting, up for grabs. it costs about 5 bucks worth of tokens to try. i thought the initial rubric was unbreakable too, but someone broke it. https://t.co/BiXTZ3Es0K i guess people got afraid to try breaking JEV after seeing max p=0.06 on BEGJEV lol. there is 0.69 ETH there and counting, up for grabs. it costs about 5 bucks worth of tokens to try. i thought the initial rubric was unbreakable too, but someone broke it. https://t.co/BiXTZ3Es0Kview source ↗
-
X X / Twitter 1w ▲ 0 neutral@jesusislord Jev @jesusislord Jevview source ↗
-
X X / Twitter 1w ▲ 0 neutral@typesafeai @allietheicon Building a real router based on Jev in Pi right now. How's the energy in Discord? I want to stay focused for now. @typesafeai @allietheicon Building a real router based on Jev in Pi right now. How's the energy in Discord? I want to stay focused for now.view source ↗
-
X X / Twitter 1w ▲ 0 neutral@CompleteSkeptic I joined for Jev and apparently stayed for the pigeon roadmap 😂 @CompleteSkeptic I joined for Jev and apparently stayed for the pigeon roadmap 😂view source ↗
-
X X / Twitter 1w ▲ 0 neutral modelA browser agent just searched Google Flights in 7 seconds Browser Use open sourced Jev Ultrafast and I can't stop watching the demo One goal: "find one-way flights Zurich to London." It types the cities, picks the date and waits for results to checks them Every browser agent I've used does this in minutes. Screensho… A browser agent just searched Google Flights in 7 seconds Browser Use open sourced Jev Ultrafast and I can't stop watching the demo One goal: "find one-way flights Zurich to London." It types the cities, picks the date and waits for results to checks them Every browser agent I've used does this in minutes. Screenshot, think, click, screenshot again, think again. This one throws that whole approach out: 1. No screenshots. It reads the page as a numbered table of buttons and fields 2. One model call picks the action AND the element at the same time 3. A tiny LLM only wakes up when something needs to be typed 4. Browser calls on the same task dropped from 1,092 to 101 Same agent opened a Wikipedia article in 2.8 seconds. Ran a hotel search with filters in 1.9 It's still an MVP. No iframes, no file uploads, no pop-up tabs yet But speed was the #1 reason nobody used browser agents. They were slower than doing it yourself Here's how to try it: 1. Clone the repo 2. Run uv sync 3. Add your TypeSafe + OpenRouter keys 4. Run uv run jev 5. Hit "Start demo" and watch it https://t.co/GsBLEC6mtZview source ↗
-
X X / Twitter 1w ▲ 0 negative modelsThey can't jack up prices. If they do, we're offloading even more to our local models and cheap LLM alternatives like Jev. There was a time around February, where it looked like the frontier labs had some kind of monopoly. The advances of the summer have killed that nightmare. To believe in Q3 of 2026 that OpenAI cou… They can't jack up prices. If they do, we're offloading even more to our local models and cheap LLM alternatives like Jev. There was a time around February, where it looked like the frontier labs had some kind of monopoly. The advances of the summer have killed that nightmare. To believe in Q3 of 2026 that OpenAI could hike the price and force us to pay more, is to be uninformed about where the industry is at.view source ↗
-
X X / Twitter 1w ▲ 0 neutral@slapyamamas @Jev Day 1627 of saying yes to Slapy's quest of getting jev to change his pfp to this. https://t.co/JUec7CAZ6a @slapyamamas @Jev Day 1627 of saying yes to Slapy's quest of getting jev to change his pfp to this. https://t.co/JUec7CAZ6aview source ↗
-
X X / Twitter 1w ▲ 0 negative open-source / alternativeTypeSafe's Jev doesn't write text, it returns probabilities. So we built jev, an open-source CLI that turns them into exit codes: jev noul "Is this angry?" --state-file msg.txt --fail-under 0.7 0 = yes, 10 = no. A semantic `if` for scripts and CI. https://t.co/3MhbPbXTon TypeSafe's Jev doesn't write text, it returns probabilities. So we built jev, an open-source CLI that turns them into exit codes: jev noul "Is this angry?" --state-file msg.txt --fail-under 0.7 0 = yes, 10 = no. A semantic `if` for scripts and CI. https://t.co/3MhbPbXTonview source ↗
-
X X / Twitter 1w ▲ 0 positive@Jchammond_ Really neat idea on how to use Jev in a game. I'm working on a Jev-related game too... @Jchammond_ Really neat idea on how to use Jev in a game. I'm working on a Jev-related game too...view source ↗
-
X X / Twitter 1w ▲ 0 neutral@spacepope Distilling jev is actually a customer base tho🤣 I don’t see it out of question that it’s part of business https://t.co/N0g9PL0zjF @spacepope Distilling jev is actually a customer base tho🤣 I don’t see it out of question that it’s part of business https://t.co/N0g9PL0zjFview source ↗
-
X X / Twitter 1w ▲ 0 neutral@iyzebhel @james2_0 Would you be able to give a breakdown of your workflow? I want to talk to Jev!! @iyzebhel @james2_0 Would you be able to give a breakdown of your workflow? I want to talk to Jev!!view source ↗
-
X X / Twitter 1w ▲ 0 positiveJev + GrokBot is the best night shift I've ever hired It ran my X account for 8 hours while I slept - and didn't make a single mistake... setup takes literally 8 minutes: prompt → GrokBot → Jev approves every action → GrokBot executes → morning report step 1 → open typesafeai, create API key (keep it off chat paste… Jev + GrokBot is the best night shift I've ever hired It ran my X account for 8 hours while I slept - and didn't make a single mistake... setup takes literally 8 minutes: prompt → GrokBot → Jev approves every action → GrokBot executes → morning report step 1 → open typesafeai, create API key (keep it off chat paste) step 2 → tell GrokBot: store TYPESAFE_API_KEY in the secure field step 3 → prompt GrokBot: install typesafe-sdk on Agent Computer + smoke system_one (Noul) step 4 → add skill jev-night-guard: before every like / reply / repost / DM / follow → ask Jev 3 typed questions: safe_to_run, on_brand, route step 5 → hard gates: noul ≥ 0.90 → RUN, stakes high → ASK ME, anything else → BLOCK step 6 → irreversible stuff never runs alone: money, DMs from brands, big accounts, quote-posts on heated threads → morning queue step 7 → shadow mode for 1 night, read the logs, then flip active - kill switch: enabled: false the result: → 3,412 actions overnight. replies, likes, drafts, DMs. → 47 blocked: prompt injections, fake "free Grok credits" links, scam accounts, "this coin will 100x" replies. → Jev cost: $0.02. 14.2 hours of my time back. → 6 waiting for me at 8am: a $2k sponsorship, a podcast invite, a reply to Karpathy. GrokBot is the hands. Jev is the bouncer. Copy this setup, then read the full Jev deep dive below ↓view source ↗
-
X X / Twitter 1w ▲ 0 neutral@jesusislord @jesusislord jev @jesusislord @jesusislord jevview source ↗
-
◈ Bluesky 1w ▲ 1 positiveI’d like to see a character-level Jev bot. Maybe I will make them if they ever give me access to it. I’d like to see a character-level Jev bot. Maybe I will make them if they ever give me access to it.view source ↗