Tweet Tester: Preview & Score a Post Before You Send It

Post on X

Views: 238,461
Likes: 1,380
Reposts: 65

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

Reported by the author

Per post: ~1s, $0.0004Every post gets 61 questions in ~1s for $0.0004x.com
Accuracy: 2 in 3picks the viral post 2 in 3 timesx.com

Tweet Tester is a free SuperX tool that takes a draft X post and scores it from 0 to 100 before you publish. Type a post in and it drops into a simulated feed between invented posts, so you can see how it reads. The panel beside it returns the score, estimates for likes, replies and reposts, and short lists of what helped and what hurt.

Hallam’s launch post says each draft gets 61 Jev questions in about a second, for $0.0004, and that the scoring was fitted on 9,481 real posts from 207 creators. The page says the tester works out what a normal post from an account your size tends to do and reads the draft against that, so a 70 means clearly better than your usual post. Hallam reports it picks the viral post 2 in 3 times and never rewards reply bait.

The intended workflow is short: write a draft, check the score, rewrite, and stop once the score peaks. The tool is free and needs no signup.

Open on Web

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