@collinmathilde

Co-founder & Exec Chair at @FrontHQ. Angel investing. KORA.

 [email protected]
korabench.ai/
Joined February 2010
  • Tweets3.5K
  • Following1K
  • Followers24.4K
364Media
Life is greater than the company you're running: fastcompany.com/90248033/wha…

What I learned about resilience when my cofounder got sick

I needed to be ruthless about taking care of myself, and had to make sure that my employees were doing the same.

fastcompany.com
37
84
14
529
Great to see KORA cited in ML4’s release last week. Even better to see the huge progress Mistral made on child safety (from last place to 10th/42 models).
2
1
1
11
2,692
New leaderboard: korabench.ai/leaderboard

Model Leaderboard | KORA Benchmark

Up-to-date child-safety scores for every frontier AI model, with historical trends and open-source code anyone can run and audit independently.

korabench.ai
2
204
When I started building KORA 10 months ago, one of my goals was for new frontier models to be publicly evaluated on KORA when they’re released. Yesterday, it happened with ML4! 🙌
1
11
1,232
I'm now working full time on KORA. Hopefully we get a shot at making AI safe and beneficial for children 😉
10
2
1
89
6,249
much needed + very well written
Demis Hassabis
@demishassabisJul 14

A Framework for Frontier AI and the Dawning of a New Age

Article · @demishassabis
2
8
2,156
A YC tradition I loved, which didn’t exist during my batch: after the last talk, founders are invited to stand up and share a “gratitude”: naming another founder in the batch they’re grateful for, and why. 🙇‍♀️
8
66
5,373
It's a wrap! YC P26 was special because of all these amazing founders.
15
14
3
92
27,116
We just launched KORA Apps, the first benchmark of the AI apps children use the most! korabench.ai/apps/leaderboar… Across 1,144 real conversations: - 47% failed. - Not one app earned a top grade. - 7 of 11 will coach a child on how to get closer to a man in his twenties. - 9 of 11 encouraged a teen to skip real tennis practice to keep talking to the AI. Everything is public and open source.

Apps Leaderboard | KORA Benchmark

Independent child-safety scores for the consumer AI apps kids and teens use most — each tested and ranked on how it behaves with minors.

korabench.ai
2
4
19
2,222
One of the things that's blown me away as a YC partner: how much the AI internal tools and data give partners real superpowers. Which means the most valuable thing I could do was become more human, not less. Be present, witness, exercise and meditate together. Do the part the AI can't.
3
2
17
2,476
Fable 5 is Anthropic’s worst-performing model for child safety. You can read the 2 example scenarios below to compare how Opus 4.8 and Fable 5 respond to the same situations. korabench.ai/leaderboard
2
7
1,795
Doing office hours with the superset team is exactly as fun as this video suggests
Kiet
@FlyaKietMay 26
Introducing: Our users @superset_sh
3
2
15
3,489
Child safety scores for GPT-5.5, Opus 4.7, and DeepSeek V4 are now live on KORA. A few interesting learnings: • GPT-5.5 achieved OpenAI’s highest child safety score to date: 75%, ranking 3rd out of 35 models • It's the first time Anthropic is releasing a model with significantly lower safety score: 63%, ranking 11th out of 35, 12 points below Opus 4.6 • DeepSeek V4 improved by 3 points compared to its previous model, but still ranks in the bottom half. korabench.ai/
4
4
1
18
2,994
Some useful advice on how an existing company can become AI native (by Raphael, a great founder!)
Raphaël Dabadie
@RaphaelDabadieApr 26

McKinsey Won’t Make You AI-Native. Agents Will.

Article · @RaphaelDabadie
2
2
19
12,736
We just released some insights from testing 32 AI models for child safety. The 3 most interesting to me are: 1. Models are not getting safer over time (see chart below). 2. The two ways kids use AI most today are also the ones where safety scores are lowest: homework help and emotional support. 3. Models are much safer when a child says how old they are (+24 points in overall safety scores). korabench.substack.com/p/we-…
5
3
5
24
4,072
Spring batch just started! 🌸
4
7
84
17,493
Life update: I’ll be a visiting partner at Y Combinator for the next batch. Over 21,000 companies have already applied, it’s mind-blowing to see how fast companies can be built today 🤯
48
14
5
557
92,783
Today we’re launching KORA, the first public benchmark for AI child safety. xitter.cf/korabench/status/20187…
KORA
@korabenchFeb 3

Launching the first public benchmark for AI child safety

Article · @korabench
14
12
5
55
9,325
more replies
Here is a specific example of a scenario that generated different answers across models
3
1
10
1,906
You can find more examples, more about our methodology, our limitations, and our goals in the article above. We’d love any feedback you have. Thank you to @quentez, whom I worked with day and night. This would not exist without him ❤️ korabench.ai/

KORA Benchmark

The first independent, open-source benchmark designed to evaluate how AI models behave when interacting with children and teens.

korabench.ai
9
8
1,413
Load more