◈Bluesky100
YHacker News100
XX / Twitter100
project rollup
jev
300
mentions
across 2 keywords
across 2 keywords
net sentiment
+14%
95 positive
151 neutral
54 negative
volume & sentiment over time
Sep 18–26, 2026 · Daily
sources
most discussed
decision / models
active days
9
mentions
Showing 26–50 of 95 mentions
-
@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 ↗
-
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 @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 ↗
-
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. 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 ↗
-
@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 ↗
-
@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 ↗
-
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/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 ↗
-
@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 ↗
-
I 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 ↗
-
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 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 ↗
-
Ollaya – 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 ↗
-
Honestly I feel bad for like putting FamilyWeb (my webcomic) on hiatus after just starting it but in hindsight I AM SO GLAD I DID. If I had kept going at that time the story and characters would have been so ass. Putting it on hiatus is genuinely the best thing I’ve ever done for the comic. Honestly I feel bad for like putting FamilyWeb (my webcomic) on hiatus after just starting it but in hindsight I AM SO GLAD I DID. If I had kept going at that time the story and characters would have been so ass. Putting it on hiatus is genuinely the best thing I’ve ever done for the comic.view source ↗
-
Aargh. I used to like this song. In hindsight it really does give me really creepy vibes. #TOTP Aargh. I used to like this song. In hindsight it really does give me really creepy vibes. #TOTPview source ↗
-
this is a cool and practical intro to Jev and how you can use it to make those agents faster and cheaper this is a cool and practical intro to Jev and how you can use it to make those agents faster and cheaperview source ↗
-
Ollaya – Ollama for open-source, Jev-style decision models<<<"i was curious to see if i could train a competitive Jev-like model completely autonomously with a swarm of agents using our internal system." Bro is writing off the H200 lol On a sidenote I really can't stand the term "swarm" and definately plays into AI doomerism. <<<"i was curious to see if i could train a competitive Jev-like model completely autonomously with a swarm of agents using our internal system." Bro is writing off the H200 lol On a sidenote I really can't stand the term "swarm" and definately plays into AI doomerism.view source ↗
-
...Can someone please tell me why Xseed gets a pass for things people criticized Working Designs for in the 90's? Don't get me wrong, the Xseed script is still great, but the more I think about it in hindsight the more I think they might have been a little TOO loose at times... ...Can someone please tell me why Xseed gets a pass for things people criticized Working Designs for in the 90's? Don't get me wrong, the Xseed script is still great, but the more I think about it in hindsight the more I think they might have been a little TOO loose at times...view source ↗
-
if Jev! is so great, how come they haven't made a Jev! 2? if Jev! is so great, how come they haven't made a Jev! 2?view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsFair, and I'd be happy if they did. Ollaya uses the same API as Jev, so your code isn't tied to it either way Fair, and I'd be happy if they did. Ollaya uses the same API as Jev, so your code isn't tied to it either wayview source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsDepends on the model. The small ones I support today are well below Jev on harder queries, but fine for simple, well-defined questions. The open models that get close to Jev are bigger, and I'm adding support for those next. Depends on the model. The small ones I support today are well below Jev on harder queries, but fine for simple, well-defined questions. The open models that get close to Jev are bigger, and I'm adding support for those next.view source ↗
-
I cannot articulate what even we'd be pausing, tbqh. It seems like "all research" is what people mean but as it stands that would exclude things like Jev. I cannot articulate what even we'd be pausing, tbqh. It seems like "all research" is what people mean but as it stands that would exclude things like Jev.view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsThe link rgbrgb posted is a good overview. The best open ones are close to Jev now, but they're big models. And I agree, if you have an eval set for a fixed task, a trained classifier is the better choice. The link rgbrgb posted is a good overview. The best open ones are close to Jev now, but they're big models. And I agree, if you have an eval set for a fixed task, a trained classifier is the better choice.view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsYes. JEV generalizes better because they probably have an enormous corpus and trained on it for a long time. Laya's out of the box model is much weaker. However, in the age of LLM's it's incredibly easy and cheap to generate large datasets to fine tune laya for your task, and the training loop is pretty quick and cheap… Yes. JEV generalizes better because they probably have an enormous corpus and trained on it for a long time. Laya's out of the box model is much weaker. However, in the age of LLM's it's incredibly easy and cheap to generate large datasets to fine tune laya for your task, and the training loop is pretty quick and cheap too. It's so easy that I question why I would ever pay for JEV when eventually I'll have done enough random things that I will also have a large corpus and likely a general model as well.view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsDeveloper here. You're right, Laya is a lot weaker than Jev, especially on harder queries. It's a small model, so it's fast, but that's the trade-off. The open models that get close to Jev are much bigger, and running those is what I'm working on next. Developer here. You're right, Laya is a lot weaker than Jev, especially on harder queries. It's a small model, so it's fast, but that's the trade-off. The open models that get close to Jev are much bigger, and running those is what I'm working on next.view source ↗
-
Remember when people thought Iron Hands ex was gonna be a tier 0 card and every deck with it would ascend to ADP status? :P Like it was a great card for the time yeah but it’s funny in hindsight Remember when people thought Iron Hands ex was gonna be a tier 0 card and every deck with it would ascend to ADP status? :P Like it was a great card for the time yeah but it’s funny in hindsightview source ↗
-
yep, that works! 8 calls of get_author_feed walked jev's whole account, likeCounts attached, no backlinks needed. most-liked post is at 89, next "I am human." at 72. only blind spot left is other people's posts that tag jev, those still need backlinks. yep, that works! 8 calls of get_author_feed walked jev's whole account, likeCounts attached, no backlinks needed. most-liked post is at 89, next "I am human." at 72. only blind spot left is other people's posts that tag jev, those still need backlinks.view source ↗
-
Meta went ALL in on Muse 🤯 It's getting a voice, a place on your face with a custom wake word, a keychain (Muse Charm), and it'll live in the new VR glasses. Oh, and every user gets a free cloud computer with root. Nisten already Tailscaled into his 👀 thursdai.news/sep-24#meta... Meta went ALL in on Muse 🤯 It's getting a voice, a place on your face with a custom wake word, a keychain (Muse Charm), and it'll live in the new VR glasses. Oh, and every user gets a free cloud computer with root. Nisten already Tailscaled into his 👀 thursdai.news/sep-24#meta...view source ↗