◈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 48 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 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 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 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 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 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 ↗
-
◈ 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 ↗
-
X X / Twitter 1w ▲ 1 positive@mysticaltech @DataChaz yeah, that’s impressive! have you tried Opus 5.5 or Jev yet? @mysticaltech @DataChaz yeah, that’s impressive! have you tried Opus 5.5 or Jev yet?view source ↗
-
X X / Twitter 1w ▲ 1 positive@BLUECOW009 Jev did better in my tests @BLUECOW009 Jev did better in my testsview source ↗
-
X X / Twitter 1w ▲ 0 positive@noisyb0y1 Jev is genuinely useful @noisyb0y1 Jev is genuinely usefulview source ↗
-
X X / Twitter 1w ▲ 0 positive models📢 TYPESAFE AI · JEV IS NOW LIVE ON https://t.co/kgZeByAQj2 API 🚀 Responds in about 70–500ms, and costs $0.042 per million input tokens (output free), making it a fit for ticket routing, moderation, risk scoring, and agent branching. 🧮 Worth actually reading "70–500ms" once more directly against the newly confirmed GL… 📢 TYPESAFE AI · JEV IS NOW LIVE ON https://t.co/kgZeByAQj2 API 🚀 Responds in about 70–500ms, and costs $0.042 per million input tokens (output free), making it a fit for ticket routing, moderation, risk scoring, and agent branching. 🧮 Worth actually reading "70–500ms" once more directly against the newly confirmed GLM-5.3-FlashX's own genuinely comparable, considerably fast "200 tokens/sec" generation speed, worth appreciating these two figures describe genuinely different things, latency versus throughput, worth being genuinely curious whether a developer building a genuinely latency-sensitive pipeline should prioritize Jev specifically for its own explicit millisecond-level response guarantee over a comparably fast, but not explicitly latency-benchmarked, generative model. 💭 Worth actually reading "output free" once more as a genuinely specific pricing structure worth checking directly against the newly confirmed four-tier discount system, worth appreciating Jev's own genuinely unique, input-only pricing model sits entirely outside that broader percentage-discount framework applied to this account's own more conventional, text-generating models. 🎯 Worth actually reading "Choice, Score, and Noul questions in parallel" directly against the fuller documentation. 👉 Try now: https://t.co/xSnqFyNE3M 🔗 https://t.co/XdOzfnbUkW @justinsuntron @BAI_AGI #TRONEcostarview source ↗
-
X X / Twitter 1w ▲ 0 positive@spaceman_gilda Welcome! This week's goal for everybody in AI -- show how your stuff works with Jev 🤣 @spaceman_gilda Welcome! This week's goal for everybody in AI -- show how your stuff works with Jev 🤣view source ↗
-
X X / Twitter 1w ▲ 0 positive performanceLooks like Jev from @typesafeai is still the king for now, compared to Kev 4b (now available via @OpenRouter ) since it is a bit too big for my laptop GPU. Kev 4b is certainly getting really close, actually showing better performance on 2 tests. Interestingly Jev via OpenRouter is 4x faster than Jev direct from @types… Looks like Jev from @typesafeai is still the king for now, compared to Kev 4b (now available via @OpenRouter ) since it is a bit too big for my laptop GPU. Kev 4b is certainly getting really close, actually showing better performance on 2 tests. Interestingly Jev via OpenRouter is 4x faster than Jev direct from @typesafeaiview source ↗
-
X X / Twitter 1w ▲ 0 positive decision / modelsHas anyone trained a Jev / Laya type model on finance data yet? Seems like it would be a no brainer to train it on specific setups for stock / crypto trading. It could act as a layer in an LLM powered quant for quick decision making based on patterns. Has anyone trained a Jev / Laya type model on finance data yet? Seems like it would be a no brainer to train it on specific setups for stock / crypto trading. It could act as a layer in an LLM powered quant for quick decision making based on patterns.view source ↗
-
X X / Twitter 1w ▲ 0 positive built@shimadaeisuke Loved this, Keisuke. I've featured your post on https://t.co/6rvbCXTB3W, a directory of things people have built with Jev: https://t.co/nJGM0Xe8kk @shimadaeisuke Loved this, Keisuke. 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 positive built@itIsGokulNair Loved this, Gokul. I've featured your post on https://t.co/6rvbCXTB3W, a directory of things people have built with Jev: https://t.co/nJGM0Xe8kk @itIsGokulNair Loved this, Gokul. 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 positive modelsWe keep trying to force massive language models into roles that just need fast, deterministic JSON endpoints. A non-autoregressive routing model for typed decisions makes way more sense than burning tokens on things that should just be function calls. #AI #Jev https://t.co/nx4cmwVHwX We keep trying to force massive language models into roles that just need fast, deterministic JSON endpoints. A non-autoregressive routing model for typed decisions makes way more sense than burning tokens on things that should just be function calls. #AI #Jev https://t.co/nx4cmwVHwXview source ↗
-
X X / Twitter 1w ▲ 0 positive built@whosfranki @shadcn Loved this, Franki. I've featured your post on https://t.co/6rvbCXTB3W, a directory of things people have built with Jev: https://t.co/nJGM0Xe8kk @whosfranki @shadcn Loved this, Franki. 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 positiveI already see Jev, Kev and Lev on twitter. Anyone working on Zev already? 😅 I already see Jev, Kev and Lev on twitter. Anyone working on Zev already? 😅view source ↗
-
X X / Twitter 1w ▲ 0 positiveI run this exact split in production on my own agent. On every message, Jev picks which notes and skills get loaded before Claude sees anything. Measured on 169 real turns: → right note ranked first: 34% → 64% → right note in the top 5: 55% → 78% → 150 to 430ms, $0.00027 a turn Two changes moved those numbers. Each n… I run this exact split in production on my own agent. On every message, Jev picks which notes and skills get loaded before Claude sees anything. Measured on 169 real turns: → right note ranked first: 34% → 64% → right note in the top 5: 55% → 78% → 150 to 430ms, $0.00027 a turn Two changes moved those numbers. Each note is described by the words that should pull it in, not by its title. And Jev sees the previous exchange, so a follow-up like "go test it" still lands on the right file. https://t.co/o2a1K5pAoQview source ↗
-
Y Hacker News 1w positive decision / modelsOllaya – Ollama for open-source, Jev-style decision modelsIsn't the point of Jev that it generalises better? It's a fast classifier you can use out-the-box, ~1.5bn tokens is about $40 (I've been hammering it) It just works ... a whole bunch of low-level/low-importance workflow stuff that was getting farmed out to small/fast LLM models now has a competitive alternative ... and… Isn't the point of Jev that it generalises better? It's a fast classifier you can use out-the-box, ~1.5bn tokens is about $40 (I've been hammering it) It just works ... a whole bunch of low-level/low-importance workflow stuff that was getting farmed out to small/fast LLM models now has a competitive alternative ... and bits that hadn't even been considered to go into some external descision/classifier service can be tested/deployed at ~$0.00003/req I don't get this wall of negativity on it, it's genuinely innovative/useful tech ... would expect HN to be more positive, regardless of whether it's the absolute best executionview source ↗