◈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 1–25 of 40 mentions
-
Ollaya – Ollama for open-source, Jev-style decision modelsI've been following jevbench twice a day for the past week and that's been a lot of fun. Latest update: Rank System Score Public / sealed accuracy Evidence 1 decider-4b v2 64.13 83.5% / 34.7% Evaluator-run, offline 2 Jev 1.13 63.29 86.6% / 36.7% Evaluator-run API 3 JevK5 v0.2 62.04 85.3% / 33.1% Evaluator-run 4 Cygnet … I've been following jevbench twice a day for the past week and that's been a lot of fun. Latest update: Rank System Score Public / sealed accuracy Evidence 1 decider-4b v2 64.13 83.5% / 34.7% Evaluator-run, offline 2 Jev 1.13 63.29 86.6% / 36.7% Evaluator-run API 3 JevK5 v0.2 62.04 85.3% / 33.1% Evaluator-run 4 Cygnet 12B 61.76 87.9% / 33.8% Evaluator-run, offline 5 Hopper 59.43 82.3% / 34.1% Evaluator-run 28 Kev 4B 36.14 66.2% / 22.4% Evaluator-run 41 Laya 421M 30.25 58.4% / 30.8% Evaluator-runview source ↗
-
Jev BenchmarksThere are comming more and more Jev alternatives. Is there anywhere a benchmarklist of these jev competitors? There are comming more and more Jev alternatives. Is there anywhere a benchmarklist of these jev competitors?view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsJev does it more efficiently because it doesn't use an LLM https://typesafe.ai/blog/introducing-system-one-models-and-j... Jev does it more efficiently because it doesn't use an LLM https://typesafe.ai/blog/introducing-system-one-models-and-j...view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelstext classification is equivalente to decision. This is exactly the same thing Jev does. text classification is equivalente to decision. This is exactly the same thing Jev does.view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsI am fairly confident if Jev-style decision models are seen as prominent (which, they seem to be), Ollama will support them. Surprised the team hasn't implemented this already. I am fairly confident if Jev-style decision models are seen as prominent (which, they seem to be), Ollama will support them. Surprised the team hasn't implemented this already.view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsAre there many models that are comparable to Jev for generic decision making? Smarter move if you have an eval set is to just train a classifier and call it a day. Are there many models that are comparable to Jev for generic decision making? Smarter move if you have an eval set is to just train a classifier and call it a day.view source ↗
-
Ollaya – Ollama for open-source, Jev-style decision modelsview source ↗
-
Jev for Input Validationview source ↗
-
Jevmem – automatic project memory for Claude Code, built on JevI really don't undertstand the jev-hype. Just start a cheap chinese agent in a context where it has only one tool, and JSON-schema constrain that toolcall to the response shape you want. Prompt the agent to make only one tool call and not speak. Done. I really don't undertstand the jev-hype. Just start a cheap chinese agent in a context where it has only one tool, and JSON-schema constrain that toolcall to the response shape you want. Prompt the agent to make only one tool call and not speak. Done.view source ↗
-
Jev in Weather Forecastingview source ↗
-
Jev vs. Kev: open-source Jev alternative tested side by sideview source ↗
-
What Jev will do to data engineeringview source ↗
-
Jevmem – automatic project memory for Claude Code, built on JevAh, well that makes a bit more sense. Admittedly I haven’t really looked into Jev and thought it was an open decision model rather than a proprietary product from TypeSafe. Ah, well that makes a bit more sense. Admittedly I haven’t really looked into Jev and thought it was an open decision model rather than a proprietary product from TypeSafe.view source ↗
-
Jevmem – automatic project memory for Claude Code, built on JevTypeSafe AI are the providers for Jev. This complaint is like saying it’s a red flag that Claude Code sends lots of information to somewhere called Anthropic. TypeSafe AI are the providers for Jev. This complaint is like saying it’s a red flag that Claude Code sends lots of information to somewhere called Anthropic.view source ↗
-
Jevmem – automatic project memory for Claude Code, built on JevCurious how this compares to my own tool, https://deciduous.dev I will have to give it a run-through today. I haven't used Jev yet so this should be interesting. I'd be interested to see if any Deciduous users have opinions, too. Curious how this compares to my own tool, https://deciduous.dev I will have to give it a run-through today. I haven't used Jev yet so this should be interesting. I'd be interested to see if any Deciduous users have opinions, too.view source ↗
-
Jevmem – automatic project memory for Claude Code, built on Jevjevmem watches Claude Code, Cursor & Codex chats and keeps a JEVMEM.md in your repo up to date. After each message, Jev (TypeSafe) decides whether anything is worth remembering — a decision, a bug, a change of mind — and writes the keepers to that file. Reversed decisions get marked superseded. Install: npm i -g jevmem… jevmem watches Claude Code, Cursor & Codex chats and keeps a JEVMEM.md in your repo up to date. After each message, Jev (TypeSafe) decides whether anything is worth remembering — a decision, a bug, a change of mind — and writes the keepers to that file. Reversed decisions get marked superseded. Install: npm i -g jevmem (needs a TypeSafe API key) Held-out check on 66 messages (23 Sep 2026) vs six frontier LLMs: save/skip 98.5% (tied with Astra); save+correct kind 95.5% (Astra 98.5%, Opus 97.0%); changes of mind 5/5; median 0.30s via Jev API (~0.6s end-to-end) vs 2.8–4.3s for the LLMs; cost $0.000127/decision. Single run by me — treat 1–2 message swings as noise. Limits: early v0.4; fully automatic only in Claude Code today (Cursor/Codex via agent/MCP); messages go to the TypeSafe API with secrets stripped; if the API is down it skips.view source ↗
-
Jevmem – automatic project memory for Claude Code, built on Jevview source ↗
-
Small questions, measurable gains with Jev – CraftCXview source ↗
-
Jev and Reasonersview source ↗
-
Show HN: Jev Plays Pokémon RedJev can't come up with original text, but I did consider giving it a list of hilarious names. Jev can't come up with original text, but I did consider giving it a list of hilarious names.view source ↗
-
Jev Is Built for Tinkerersview source ↗
-
ReAnchor, a Jev Optimizer in DSPyview source ↗
-
A Jevlike using an escalation model to route between a classifier and an LLMview source ↗
-
Benchmarking Jev, Laya, and five open models under three stressesview source ↗
-
My Take on Jevview source ↗