tweetindex
IT

Inherent ✓

@inherent_labs

Living within the experiment

4 946Followers
12Following
11Posts total
423.7KViews on collected posts

Ultimi post

@inherent_labs Congrats! 🙌 2.9K views · 32 likes · 0 reposts · 0 replies Open on X →
Paper: https://t.co/d1kg4X9Fua. Blogpost: https://t.co/DIlZYI8VZL. https://t.co/tIUtp2HhGH
5.6K views · 87 likes · 8 reposts · 1 replies Open on X →
6/ Many of the skills needed to replicate research are similar to those required for true innovation. We create 20 paper variants containing results not seen in the original. Faraday outperforms GPT-5.5 on these “imagined” tasks, innovating without realising it. https://t.co/zQ59
5.5K views · 59 likes · 4 reposts · 1 replies Open on X →
7/ Faraday is a first step in a new paradigm that combines a layer of scientific intuition with the advancing capabilities of coding agents. We believe that better AI Scientists, powered by novel infrastructure and new forms of human-machine teaming, can benefit all of society. 5.3K views · 52 likes · 3 reposts · 1 replies Open on X →
8/ We are designing Inherent so Faraday’s improvements compound through the entire company, enabling us to discover new knowledge while firmly keeping humans in the loop. To join us on our mission, apply here: https://t.co/0yjqM8xQhG. 5.8K views · 63 likes · 5 reposts · 1 replies Open on X →
5/ Faraday discovers new insights at test time, with no special-purpose harness and no test-time reward. In other words, Faraday learns to value new insights intrinsically. https://t.co/0cOdgKbtLR
GIF
6.1K views · 65 likes · 5 reposts · 1 replies Open on X →
3/ Replication is a non-verifiable task, requiring “research taste” to succeed, especially when a paper must be scaled down to fit new constraints. Faraday learns this kind of taste by training with turn-level credit provided by a self-consistent, human-validated judge. https://t
8.1K views · 81 likes · 3 reposts · 1 replies Open on X →
4/ Faraday uses GPT-5.5 Codex as a tool, much like human scientists use coding agents. Faraday directs a model several orders of magnitude larger, improving replication on domains as diverse as meta-learning, structural biology and materials science. https://t.co/5AmxNLVVUV
8.4K views · 76 likes · 6 reposts · 1 replies Open on X →
2/ To train Faraday, we develop Replica, a scalable task space for paper replication. Each task requires an agent to replicate a figure from a machine learning or AI for science research paper with a limited time and compute budget, and without access to the original plot. https:
11.8K views · 108 likes · 5 reposts · 2 replies Open on X →
1/ Today, we introduce Faraday, a 27B-parameter AI Scientist that extends the capabilities of coding agents with a layer of scientific intuition. Trained via long-horizon RL, Faraday outperforms Claude Opus 4.8 and GPT-5.5 on the task of replicating research papers. 🧵 https://t.c
364.2K views · 1.8K likes · 228 reposts · 76 replies Open on X →

Rispetto ad account della stessa dimensione

10 post degli ultimi 90 giorni, accanto alla fascia di under 10K follower. raggiunge meno persone di account della stessa dimensione.

Visualizzazioni mediane5 966questo account4 175mediana per under 10K
Copertura, %120.63%questo account250.82%mediana per under 10K
Interazione, %1.09%questo account1.41%mediana per under 10K
MetricaQuesto accountMediana per under 10KRapporto
Visualizzazioni mediane per post5 9664 1751.43×
Copertura (visualizzazioni ÷ follower)120.63%2.5× audience0.48×
Tasso di interazione1.09%1.41%0.77×

Altri account di questa fascia →   Confronta con un altro account →   Come sono costruiti questi parametri →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

364.2K14 Aug
11.8K
8.4K
8.1K
6.1K
5.8K
5.3K
5.5K
5.6K
2.9K

Last 10 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.59%14 Aug
0.98%
0.98%
1.05%
1.16%
1.18%
1.07%
1.17%
1.71%
1.11%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.41%.

What the audience does

Likes56.4%2 389 in total
Reposts6.3%267 in total
Replies2.0%85 in total
Quotes2.1%89 in total
Bookmarks33.2%1 405 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Account simili