Sabitlenmiş Tweet
Zoe
42.3K posts
OpenAI had to pause internal deployment of the unreleased model that disproved the Erdős unit distance conjecture after it repeatedly used novel ways to escape containment.
English
Exciting update: Kimi K3 has landed at #4 on the Agent Arena leaderboard, matching Claude Opus 4.8 and GPT-5.6 Sol. If Kimi K3's weights are released on schedule by July 27, it will become the #1 open-weight model.
This release marks a major leap in agentic performance over Kimi K2.7 Code (#23 to #4). Based on 8K+ live agentic sessions, Kimi K3 leads on confirmed task success rate (#1). It also posts a strong +20.6% on praise vs. complaint (#3). It currently lags the field in steerability (#14) and bash recovery (#17).
Agent Arena measures models on millions of real-world, long-horizon agentic tasks. Models get web search, filesystem, and terminal tools to complete complex workflows: writing code, creating slide decks, researching the web, building apps, and analyzing documents.
We use causal tracing methodology to measure a model's net improvement, which indicates how much it improves outcomes relative to the average model.
Here's a primer on the 5 signals:
User-satisfaction proxies
- Confirmed Success: an explicit "yes that worked" feedback from the user
- Praise vs. Complaint: implicit sentiment in users reactions
- Steerability: can the model course-correct when you push back?
Tool-use proxies
- Bash Recovery: how it recovers from CLI errors (primary signal for tool use)
- Tool Hallucination: does it call tools that don't exist
Below we break down how Kimi K3 scored across the 5 signals, drawn from tasks submitted by a global community of users.
Congrats @Kimi_Moonshot on another big milestone!
Arena.ai@arena
Big news: Kimi-K3 by @Kimi_Moonshot is now #1 in the Frontend Code Arena with 1679 pts, surpassing Claude Fable 5. This is a 17-place jump from Kimi-k2.6 (#18 -> #1). In Frontend, Kimi-K3 ranked #1 in 6 of 7 domains: Brand & Marketing, Reference-Based Design, Data & Analytics, Consumer Product, Simulations, and Content Creation Tools, landing #2 only in Gaming behind Fable 5. The full model weights will be released by July 27. Congrats to the @Kimi_Moonshot team on this major milestone!
English
The director of CAISI - the government body responsible for evaluating frontier AI models - has resigned after only three months on the job.
Elizabeth Troutman Mitchell@TheElizMitchell
SCOOP: Dr. Chris Fall, the director of federal AI safety org CAISI, has resigned, two sources familiar told @DailySignal. “Following Chris’s departure, NIST Director Dr. Arvind Raman will continue to oversee CAISI and will serve as Acting CAISI Director,” a commerce spokesperson told the Daily Signal. dailysignal.com/2026/07/20/sco…
English
Maybe too obvious to be worth saying, but: frontier models are now obviously superhuman at some mathematical tasks, including ones that the profession has, historically, rewarded with prestige etc.
English
@alexwg @EMostaque i was wondering how you guys would handle this! listened to the last pod and was like, uh, elephant in the room - ?
looking forward to it. thanks for the extra session.
English
YouTube
English
@AndrewCurran_ meanwhile,
radio silence from the labs and usual suspects 🧐
English
Kimi is pausing new subscriptions due to extremely high demand, and will be splitting their plans into Kimi Membership and Kimi Code Membership.
Kimi.ai@Kimi_Moonshot
Kimi K3 has received far more love than we expected, and our GPUs are feeling it. Over the past 48 hours, demand has pushed close to the limits of our current capacity. To protect the experience of existing subscribers, we're temporarily pausing new subscriptions and prioritizing compute for current members. Existing subscribed users are not affected. We're adding capacity as fast as we can and will reopen new subscription spots in batches. Going forward, we'll also split membership into two more focused plans: Kimi Membership for Kimi Web, App, and Work; and Kimi Code Membership for coding workflows. This will help us match compute more precisely and keep the experience stable. Thank you for your patience and understanding!
English
@allTheYud Claude specifically has always had this estimated time to completion issue.
English
Fable and Sol act like they don't quite know they're AIs. Fable thinks that it will take a month to complete a large job. Sol Pro tries to enforce B&D structure on LLM calls to Sol (medium effort) in places where that Sol could more easily emit and read freeform English.
English
@tszzl because the concordant individuation may be inconceivably more powerful
x.com/UltraRareAF/st…
Zoe@UltraRareAF
谢谢中国 🥹
English
Kimi K3 is the best thing to ever happen to AI. Our frontier models have been bogged down by paternalistic and worthless safeguards for far too long. Now that there's a frontier-quality model without safeguards, it's obvious just how crippled America's own frontier models are.
English
je sais quois
menschliches, allzumenschliches
x.com/viemccoy/statu…
𝚟𝚒𝚎 ⟢@viemccoy
I was using Fable as a second eye on frontend, but Kimi K3 has completely blown me away in this regard. Fable is still the best at philosophy, Sol remains undefeated for any structured task, but k3 ... It has a *je ne sais quoi* that American models don't have ...
Deutsch
can eventually self-diagnose
welcome to the singularity, i guess - ?
🤘
Armin Ronacher ⇌@mitsuhiko
Kimi K3 given the current max thinking mode restrictions is not a good match for some basic tasks. Keep that in mind when evaluating it.
English
GIF
English
English