Jev scored 3,282 X posts for what drives growth (X)

Post on X

Views: 87,849
Likes: 748
Reposts: 34

Read from X on 24 Sep 2026. Counts change daily.

Reported by the author

Total cost: $0.12824,252,330 tokens $0.1282 for the full 8m 34s run!x.com
Run time: 8m 34s4,252,330 tokens $0.1282 for the full 8m 34s run!x.com
How-to lift: 150 vs 44 likesHow-to posts got 150 median likes vs the average median of 44.x.com

Ian Nuttall ran his own archive of 3,282 X posts, spanning 100 million views, through Jev to find out what actually drives growth. Each post got 8 questions covering its topic, hook, tone, and whether it teaches the reader something. That is a batch classification job: Jev answers each question with a category or rating rather than writing anything.

The full run processed 4,252,330 tokens in 8 minutes 34 seconds for $0.1282, so scoring one post cost a fraction of a cent. The pattern that fell out: how-to posts got 150 median likes, against an average median of 44. AI and coding topics carried a 1.9x multiplier over the baseline, while SEO, despite showing up often in his recent posts, sat right at the 1.0x baseline, which he called surprising. He summarized the winning combination as an AI or coding topic that teaches something, written in a provocative voice.

Open on X

View the post on X

Use casesComposite scoring

jev-trader

Makes one AI trade decision every Monad block on the Kuru MON-USDC market using Jev. The public deployment runs in dry-run mode with a mock model.

jarrodwattsOpen

2.2k starsLoop, mock model p50 100 msDecision window ~300 ms/block

ProjectConfidence-gated actions+1

Introducing System One Models and Jev (Hacker News launch thread)

The 1,978-point, 513-comment launch thread. The top comment calls the speed comparison misleading, since Jev only returns structured output, and disputes the cannot-hallucinate claim because a valid type can still hold a wrong value. Others note ordinary LLMs can already be forced into structured output.

albelfioOpen

DiscussionIntent and model routing+3

DSPy: programming, not prompting, language models

Declares typed input/output Signatures for LLM modules and optimizes the underlying prompts and weights against a metric. Its Signature abstraction is the closest widely-used open equivalent of Jev's typed-question interface. Star count is GitHub's rounded display figure.

stanfordnlp38k starsOpen

AlternativeStructured extraction+3

newsjack

Open source skills that read a morning's news feed with Jev and tell a list of brands which stories to act on. In a demo run it read 384 headlines and matched them to 15 brands in 24.9 seconds for $0.19, against 4 of 384 for $0.77 on Claude Opus 5 over the same feed.

Elvis (@elvissun)Open

851 starsCost $0.19vs Opus/headline ~390x cheaper

ProjectComposite scoring

decider: one-pass typed decisions with calibrated probabilities (Qwen3.5-2B)

Open reproduction of the System One model class, fine-tuned from Qwen3.5-2B-Base, returning a probability distribution per typed question in a single forward pass. Serves TypeSafe's POST /v1/systemone wire format so TypeSafe SDKs work unchanged by repointing TYPESAFE_BASE_URL.

Mapika348 starsOpen

AlternativeIntent and model routing+3

pg-jev

PostgreSQL extension that lets you filter, rank and classify rows with plain-language conditions, such as WHERE jev(tickets, 'the customer is angry'). Adds jev_prob, jev_choice and jev_score functions that compose with joins, GROUP BY and ORDER BY, with no index or embeddings. Published on PGXN.

realZachiOpen

329 stars2k rows, cold ~3.5s, $0.0122k rows, cached ~50ms

ProjectSupport inbox triage+1

Menu