tweetindex
ES

Vals AI ✓

@ValsAI · San Francisco, CA · joined 07 Mar 2024

Public LLM Evaluation // https://t.co/rNS39rhVQ9 @8vc @BloombergBeta @pearvc @a16z @HRTVentures @nextladder

21 047Followers
275Following
1 943Posts total
1.4MViews on collected posts

Últimas publicaciones

@ValsAI Share the save file ! 1.2K views · 18 likes · 0 reposts · 0 replies Open on X →
@ValsAI > Navier-Stokes: 88 hours > Factorio: 165 hours (I’m aware this is not a legit comparison) 6.9K views · 258 likes · 5 reposts · 5 replies Open on X →
@ValsAI Were blueprints allowed? If so, this isn't that impressive 3K views · 25 likes · 0 reposts · 0 replies Open on X →
GPT-6 Astra has beaten Factorio: Space Age after over 165 hours in-game time and 2 days wall-clock time. Space Age has six planets and takes a human about 10-20x as long compared to the standard Factorio. https://t.co/kEJ1UajdC5
236.8K views · 2.2K likes · 113 reposts · 64 replies Open on X →
Watch it live here: https://t.co/2P8yU3eA4n 18.5K views · 48 likes · 3 reposts · 1 replies Open on X →
@ValsAI The machine specs are cracking me up, 96 core CPU and RTX 5090 for a model that can play at like 1 FPS max lmao 6.3K views · 124 likes · 2 reposts · 3 replies Open on X →
This was only using standard computer use, no specialized tools, hooks, or pauses 18.7K views · 229 likes · 0 reposts · 2 replies Open on X →
Astra has officially made it to the nether fortress in our long-horizon Minecraft computer use eval. Something no AI has done in history. It is now in the final stretches of beating the game in real time. https://t.co/TtApCW4gLM
552.2K views · 1.6K likes · 89 reposts · 44 replies Open on X →
GPT 6 Astra has smashed the record on our Code Migration benchmark, #1 at 68% accuracy (+10 points over second place). It's also 2-4x faster than the comparable models. https://t.co/8nIMNiYpRs 17.5K views · 366 likes · 27 reposts · 23 replies Open on X →
OpenAI’s GPT 6 Astra has effectively saturated SRE-Bench, a cybersecurity benchmark testing whether models can reverse engineer binaries. We’re sharing more information, along with a call for contributions to extend the benchmark: https://t.co/K13uyPgPOM 6.5K views · 141 likes · 5 reposts · 3 replies Open on X →
Gov. Shapiro just signed an execute order establishing stringent AI data center regulations, focusing on energy, water and community burdens. But measurements of the environmental footprint of AI are incomplete outside the context of how the technology is used. Our new https://t. 2K views · 10 likes · 2 reposts · 1 replies Open on X →
GLM 5.3 Flash (codenamed ox-alpha) is #8 among open-weight models on the Vals Index - 6 spots behind GLM 5.3, but costs roughly 18x less than GLM 5.3. https://t.co/PrjtH1kb1q 3.2K views · 56 likes · 1 reposts · 4 replies Open on X →
@ValsAI how many unsolved ciphers did fable 5.1 attempt before this one yielded? hard to judge the result without that denominator. 7.7K views · 52 likes · 0 reposts · 4 replies Open on X →
Out came: O GOD UPHOLD KING CHARLS THE SECOND AND MAKE HIM THE SUPREME RULER OF THIS LAND Congrats @AnthropicAI More in the blog: https://t.co/K1is9xFdr6 13.7K views · 385 likes · 15 reposts · 4 replies Open on X →
The cipher was Sir Thomas Urquhart’s Cyphral Distich, published in 1653. It contains two lines of 32 numbers each. It’s been attempted by numerous organizations and people over the last three centuries. https://t.co/ejJKp9FWlV 13.6K views · 162 likes · 6 reposts · 1 replies Open on X →
Past humans tried methods like frequency analysis, substitution, and homophonic substitution, and none of these approaches worked. It seems they were missing one crucial hint. The cipher has 32 numbers per line. Immediately before it are Urquhart’s 32 Proquiritations. Fable 14.2K views · 147 likes · 9 reposts · 1 replies Open on X →
Using Fable 5.1, we’ve elicited a decoding of a cipher that has been unsolved for 373 year, and listed as #28 on Klaus Schmeh’s (the most-published cryptology author in the world) “The Top 50 unsolved encrypted messages.” The solution? Almost embarrassingly simple in hindsight. 187K views · 1.5K likes · 129 reposts · 44 replies Open on X →
@ValsAI @a16z @8vc @pearvc @BloombergBeta @HRTVentures @nextladder huge congrats to the team!! 2.4K views · 26 likes · 0 reposts · 2 replies Open on X →
Today we're announcing our $40M Series A at a $400M valuation, led by @a16z , with participation from existing investors @8vc, @pearvc, and @BloombergBeta and new investors @HRTVentures and @nextladder. Alongside the fundraise, three more announcements: - Vals Smith: is now ht 234.5K views · 364 likes · 43 reposts · 77 replies Open on X →
See our full blog post! https://t.co/qWN6HIhUPm 2.7K views · 10 likes · 0 reposts · 1 replies Open on X →
We are hiring! https://t.co/HoGFDU7arR 2K views · 7 likes · 0 reposts · 1 replies Open on X →

Frente a cuentas del mismo tamaño

21 publicaciones de los últimos 90 días, junto al rango de 10K–100K seguidores. llega a mucha gente, pero pocos de esos espectadores reaccionan.

Visualizaciones medianas7 742esta cuenta924mediana de 10K–100K
Alcance, %36.78%esta cuenta3.62%mediana de 10K–100K
Interacción, %1.11%esta cuenta1.52%mediana de 10K–100K
MétricaEsta cuentaMediana de 10K–100KProporción
Visualizaciones medianas por publicación7 7429248.38×
Alcance (visualizaciones ÷ seguidores)36.78%3.62%10.2×
Tasa de interacción1.11%1.52%0.73×

Otras cuentas de este rango →   Comparar con otra cuenta →   Cómo se construyen estas referencias →

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

13.7K1 Sep
7.7K
3.2K3 Sep
2K
6.5K
17.5K4 Sep
552.2K10 Sep
18.7K
6.3K11 Sep
18.5K
236.8K17 Sep
3K18 Sep
6.9K
1.2K

Last 14 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

2.96%1 Sep
0.72%
1.93%3 Sep
0.71%
2.32%
2.41%4 Sep
0.33%10 Sep
1.24%
2.07%11 Sep
0.28%
1.03%17 Sep
0.82%18 Sep
3.87%
1.52%

Reactions — likes, reposts, replies and quotes — divided by views. Median for 10K–100K accounts is 1.52%.

What the audience does

Likes77.1%7 770 in total
Reposts4.5%449 in total
Replies2.8%285 in total
Quotes2.0%201 in total
Bookmarks13.7%1 377 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.

Cuentas similares