1kpapers, AI research papers classified by Jev

Post on X

Views: 285,638
Likes: 1,985
Reposts: 141

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

Reported by the author

Cost: $0.08The classifications cost $0.08 on @typesafeaix.com
Latency: 256 ms median256ms median end-to-end latency per paperx.com

1kpapers is a site for browsing about 1,000 AI research papers from 2025 and 2026 by topic, lab and citations. Hassan (nutlope) ran the papers through a two-step pipeline: DeepSeek V4 Flash summarized each paper, then Jev got the title, the summary and 24 possible topics and classified the paper into one of them. The summaries cost $3.99 on Together, and the Jev classification pass cost $0.08 in total, with a 256 millisecond median end-to-end latency per paper.

Hassan presents the split as where things are heading: different models for different parts of the workflow, instead of one model for everything. At the time of the post Hassan was still running evals on the Jev classifications before replacing the site’s current ones.

Open on Web

View the post on X

PrimitivesChoice

Jev Ultrafast (Browser Use)

Browser Use's fast browser agent where Jev picks the operation and the DOM element in a single request; a small LLM is only invoked to write text when typing is required. Demoed on a Google Flights search.

browser-useOpen

19k starsFlight search 7.1 s

ProjectTyped tool dispatch+2

openjev

Attempt to run a Jev-style System One decision model locally on a single RTX 3090. Companion site at openjev.com. The repository was renamed to TheoLeeCJ/SemIf on GitHub, and the old openjev URL now redirects to it.

TheoLeeCJOpen

4.1k starsJSON vs direct 5.21x slowerPeak throughput 20.03 dec/s

Project

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

jevlike

Open reimplementation that trains a small model to choose among a changing list of text options, emitting one probability per option in a single forward pass. Ships Doom, chess and Wikispeedia demos.

vinnylarouge1.3k starsOpen

Project

Ran Jev against an existing classifier eval that previously used Gemini 2.5 Flash Lite

Vercel CTO reports Jev saturated an existing classifier eval that had used Gemini 2.5 Flash Lite and ran about 6x faster. Original post; TypeSafe's quote-tweet is a separate item.

Malte Ubl (@cramforce)Open

220k viewsSpeed vs Gemini 6x faster

ProjectHierarchical classification+1

Agent Desktop

Rust desktop automation that reads apps through the OS accessibility tree instead of pixels. Its jev-desktop skill takes a plain-language goal and has Jev pick one operation and one target element per turn, so the 150-element tree never enters the agent's context.

lahfirOpen

1.6k starsToken reduction 78-96%

ProjectTyped tool dispatch+1

Menu