◈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 51–75 of 95 mentions
-
Is Jev AI worth the hype? See it set up in Python, tested on a real example, and given an honest verdict. youtu.be/pmnq5e5Xp4s Is Jev AI worth the hype? See it set up in Python, tested on a real example, and given an honest verdict. youtu.be/pmnq5e5Xp4sview source ↗
-
Ollaya – 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 ↗
-
Drex: Open jev-like claims win on decision indexview source ↗
-
Ollaya – 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 ↗
-
Jevmem – 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 ↗
-
Guess who can't eat 365 bananas a year and is back on that potassium again -- it's this girl 👏👏👏😤 You know in hindsight it's wild how many doctors have recommended I eat a banana a day when it's like $12 for this entire bottle 🫠💦 Guess who can't eat 365 bananas a year and is back on that potassium again -- it's this girl 👏👏👏😤 You know in hindsight it's wild how many doctors have recommended I eat a banana a day when it's like $12 for this entire bottle 🫠💦view source ↗
-
Weiwei Ye, Hangchen Liu, Renhe Jiang NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees https://arxiv.org/abs/2609.28587 Weiwei Ye, Hangchen Liu, Renhe Jiang NumericJev: Jev-like LLM Numerical Decoding with Multiway Decision Trees https://arxiv.org/abs/2609.28587view source ↗
-
I mostly do, too, but then I think about some of the weird stereotypes in the Potter books and whether or not the bigotry was something always under the surface or if we're reading more into it now with the hindsight of who she's become. Either way it sucks. Loved HP and JKR growing up. It's sad. I mostly do, too, but then I think about some of the weird stereotypes in the Potter books and whether or not the bigotry was something always under the surface or if we're reading more into it now with the hindsight of who she's become. Either way it sucks. Loved HP and JKR growing up. It's sad.view source ↗
-
Jev 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 ↗
-
Speedball was locked out for like five years wasn’t he?! Absurd in hindsight Speedball was locked out for like five years wasn’t he?! Absurd in hindsightview source ↗
-
An ounce of prevention???? NAH FAM WE TAKE A POUND OF CURE CUZ MERICUHHH I know theres problems everywhere but it feels like the US is particularly regressive now after so much progress was appearing to happen (im hindsight it was just obama years optimism clouding reality lmao). An ounce of prevention???? NAH FAM WE TAKE A POUND OF CURE CUZ MERICUHHH I know theres problems everywhere but it feels like the US is particularly regressive now after so much progress was appearing to happen (im hindsight it was just obama years optimism clouding reality lmao).view source ↗
-
lol. this makes the sudden increase in speed of features and the VERY sudden accelerated release of 2Ship feel.... like very obvious red flags in hindsight lol. lol. this makes the sudden increase in speed of features and the VERY sudden accelerated release of 2Ship feel.... like very obvious red flags in hindsight lol.view source ↗
-
Jevmem – 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 ↗
-
Show 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 ↗
-
We'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 ↗
-
right? like in hindsight, they really needed the HoTS2.0 era (quests, xp globes, etc) but every time i play league i just, kinda feel like it’s crunchier, less cooperative hots. i only play aram mayhem because it came close to scratching the itch with the long team fights, map variety, scaling. right? like in hindsight, they really needed the HoTS2.0 era (quests, xp globes, etc) but every time i play league i just, kinda feel like it’s crunchier, less cooperative hots. i only play aram mayhem because it came close to scratching the itch with the long team fights, map variety, scaling.view source ↗
-
A solid 50% of the genre being based on, in hindsight, kind of silly and often just straight-up racist fears that Japan was going to achieve permanent economic giga-chad status and mog America forever has also given it some wonky DNA IMO A solid 50% of the genre being based on, in hindsight, kind of silly and often just straight-up racist fears that Japan was going to achieve permanent economic giga-chad status and mog America forever has also given it some wonky DNA IMOview source ↗
-
Like most things, draft picking is a whole lot easier in hindsight. But dang that's a big miss Like most things, draft picking is a whole lot easier in hindsight. But dang that's a big missview source ↗
-
Wire obviously the superior show. But the general observation is fascinating. Was it, in hindsight, bad that the most zeitgeisty show of the 90s - the X Files - (which I loved) essentially pushed the message ‘conspiracy theories are real and the government is lying to you’? Wire obviously the superior show. But the general observation is fascinating. Was it, in hindsight, bad that the most zeitgeisty show of the 90s - the X Files - (which I loved) essentially pushed the message ‘conspiracy theories are real and the government is lying to you’?view source ↗
-
The great pity is that even at the time many understood this about the very process they were in. Having clear sight turned out to be about as useful as having hindsight. The great pity is that even at the time many understood this about the very process they were in. Having clear sight turned out to be about as useful as having hindsight.view source ↗
-
Jev 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 ↗
-
Jev 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 ↗
-
Solitaire Alone TogetherHello! Great job on the project! After seeing your blog, I actually decided to go to that 30th Anniversary after party! I didn't even know about Rhizome. They are such a cool group! Man I was NOT dressed as well as everyone else there and had no idea what I was doing but it was still fun ha ha! In hindsight, I guess it… Hello! Great job on the project! After seeing your blog, I actually decided to go to that 30th Anniversary after party! I didn't even know about Rhizome. They are such a cool group! Man I was NOT dressed as well as everyone else there and had no idea what I was doing but it was still fun ha ha! In hindsight, I guess it was everyone coming back from that benefit dinner? Was your exhibit supposed to be there? I didn't see it on either floor.view source ↗
-
Where's the Beef?: The lab-grown-meat revolution that wasn'tWouldn't you be able to do this with ordinary processed meat today? I remember as a kid, we once ate some kind of filled chicken nugget thing, which would have been pulped chicken glued back together into a pouch. I thought it was pretty tasty, but in hindsight its probably good that I only got to eat it a couple times… Wouldn't you be able to do this with ordinary processed meat today? I remember as a kid, we once ate some kind of filled chicken nugget thing, which would have been pulped chicken glued back together into a pouch. I thought it was pretty tasty, but in hindsight its probably good that I only got to eat it a couple times, because typing it out now it sounds disgusting and super unhealthy.view source ↗
-
Radicle: Disclosure of Vulnerability in the Network ProtocolAs someone who joined the project at the beginning of the year, I can assure you that the team cares a lot. Hindsight is always 20/20. We will work hard to regain the trust of the community. As someone who joined the project at the beginning of the year, I can assure you that the team cares a lot. Hindsight is always 20/20. We will work hard to regain the trust of the community.view source ↗