◈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 1–17 of 17 mentions
-
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 ↗
-
Y Hacker News 1w positive decision / modelsOllaya – 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 ↗
-
Y Hacker News 1w positive decision / modelsOllaya – 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 ↗
-
Y Hacker News 1w positive decision / modelsOllaya – 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 ↗
-
Y Hacker News 1w positive decision / modelsOllaya – 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 ↗
-
Y Hacker News 1w positive decision / modelsOllaya – 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 ↗
-
Y Hacker News 1w positive decision / modelsOllaya – 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 ↗
-
Y Hacker News 1w positive decision / modelsOllaya – Ollama for open-source, Jev-style decision modelsSounds good on latency but how is its actual decision quality vs. Jev? Sounds good on latency but how is its actual decision quality vs. Jev?view source ↗
-
Y Hacker News 1w ▲ 1 positive decision / modelsDrex: Open jev-like claims win on decision indexview source ↗
-
Y Hacker News 1w positive decision / modelsOllaya – Ollama for open-source, Jev-style decision modelsthere's this thing with a bunch of similar models https://huggingface.co/spaces/multimodalart/jev-decision-ind... top open one is trained by perplexity cto for $3k, kinda cool https://x.com/denisyarats/status/2102252088067850507 there's this thing with a bunch of similar models https://huggingface.co/spaces/multimodalart/jev-decision-ind... top open one is trained by perplexity cto for $3k, kinda cool https://x.com/denisyarats/status/2102252088067850507view source ↗
-
Y Hacker News 1w positive modelsJevmem – automatic project memory for Claude Code, built on JevThe people that run local jev like models do sth similar. Train a seperate nn adapter on top of qwen 4b so it has balanced probabilities whatever that means and apparently it works quite well. Side note: conspiracy theorists say that jev is a qwen model fine tuned but who know if true The people that run local jev like models do sth similar. Train a seperate nn adapter on top of qwen 4b so it has balanced probabilities whatever that means and apparently it works quite well. Side note: conspiracy theorists say that jev is a qwen model fine tuned but who know if trueview source ↗
-
Y Hacker News 1w positive decision / modelsJev in Weather ForecastingWeather apps have been notoriously pretty bad when it comes to predicting the vector rain will take on a radar. Dark Sky (bought by Apple) tried to do this with machine learning and was objectively the best for decades. However, given Jev's fast speed + cheap costs, hooked in Jev as the decision maker for forecasting r… Weather apps have been notoriously pretty bad when it comes to predicting the vector rain will take on a radar. Dark Sky (bought by Apple) tried to do this with machine learning and was objectively the best for decades. However, given Jev's fast speed + cheap costs, hooked in Jev as the decision maker for forecasting rain. The resulting lift is meaningful. Made an app on the App Store + published a bit of the work. If there's anyone smart out there, feel free to build on top of it and Jev is just an awesome model to play around with...definitely unlocks use cases that even GPT Luna was too expensive / not rigid enough for.view source ↗
-
Y Hacker News 1w positive modelsJevmem – automatic project memory for Claude Code, built on JevThe AI language really stands out, too. "What is automatic and what depends on the agent". A human might write, "jevmen watches your coding session with Claude Code or Codex and picks just the right moment to remember important things that you decided along the way. There are some differences in how jevmem works, depen… The AI language really stands out, too. "What is automatic and what depends on the agent". A human might write, "jevmen watches your coding session with Claude Code or Codex and picks just the right moment to remember important things that you decided along the way. There are some differences in how jevmem works, depending on which coding harness you are using. The table below summarizes these differences:" I don't know why the models were generally trained to be so brief, but it's definitely not the way anyone I know actually writes. A second pass is always a good idea to clean this stuff up. And, thankfully, the models are all pretty good at that.view source ↗
-
Y Hacker News 1w ▲ 31 positive open-source / alternativeShow HN: Doom or Bloom, map your AI worldviewMap your AI worldview by answering a few questions, and see how you compare with others. only takes a few minutes && free & open source && private by default && powered by Jev I think this is a really important question for everyone to be asking themselves, and my hope is that this lil project helps to move our convers… Map your AI worldview by answering a few questions, and see how you compare with others. only takes a few minutes && free & open source && private by default && powered by Jev I think this is a really important question for everyone to be asking themselves, and my hope is that this lil project helps to move our conversations around AI futures in a more balanced, productive direction.view source ↗
-
Y Hacker News 1w positiveWe're Gonna Need More MathematiciansHe is right. We will need more expert verifiers, thanks to the eventual Jevon's Paradox. He is right. We will need more expert verifiers, thanks to the eventual Jevon's Paradox.view source ↗
-
Y Hacker News 1w positive modelsJev Is Built for TinkerersAuthor here, and I'll declare my bias so I'm upfront. I am co-founder of Ably, a realtime infrastructure company, so I wanted Jev to be a low-latency story. Two weeks ago I built Jev Pong and thought it was. Then I tried to find a use our customers would ship and couldn't, so I sorted the whole first week of Jev posts … Author here, and I'll declare my bias so I'm upfront. I am co-founder of Ably, a realtime infrastructure company, so I wanted Jev to be a low-latency story. Two weeks ago I built Jev Pong and thought it was. Then I tried to find a use our customers would ship and couldn't, so I sorted the whole first week of Jev posts instead of guessing. The data is on a separate page linked from the piece (see https://mattheworiordan.github.io/jev-landscape/ and https://github.com/mattheworiordan/jev-landscape/ , which scanned ~6k posts and looked at the data from two public gateways and twenty rapidly emerging rivals). The short version. Adoption is very real (a quarter of Vercel's AI Gateway requests, 2% of its tokens), but the 100x claim is against frontier models. In practie, Jev is more like 7x and 5x against small models you'd have likely used. So my conclusion is Jev is a great model, unblocks things you could not do before when you're in builder mode, but when you move into production and definitely do things at scale, you're unlikely to be on Jev. We have solutions already for the things Jev does, just with some friction.view source ↗
-
Y Hacker News 1w positive decision / modelsJev Based Code Review> Like the classifiers we were building 15 years ago with random forrests and logistic regressions I think no one mentioned here, but the obvious difference is that Jev can spit out decisions directly from natural language input. None of these ML models could do that, and other than a full-fledged LLM (which is optimiz… > Like the classifiers we were building 15 years ago with random forrests and logistic regressions I think no one mentioned here, but the obvious difference is that Jev can spit out decisions directly from natural language input. None of these ML models could do that, and other than a full-fledged LLM (which is optimized for conversation and agentic tasks) or some classical NLP models (which underperform compared to LLMs, AFAIK), there is nothing right now that rivals Jev-like models. Of course it's not perfect, but seems like the right step forward for quick classification/decision tasks based on natural language.view source ↗