Pinned Tweet
Life is greater than the company you're running: fastcompany.com/90248033/what-…
37
84
529
Finally watched “You Can See Everything” yesterday night, I thought my husband’s take on our group chat was pretty accurate
Cyril: I haven’t read everything yet, and I think there are lots of questions we could ask, but deep down, if my life depended on it, I’d say she’s dishonest and manipulative, and fully aware of it.
Cyril: And Nathan is manipulative too, because something I realize bothered me throughout the first two hours is that he doesn't ask the important questions at all (or rather, he edited them out). He focuses on the machine's claim that it "can do the tests," but there are ten other things that would be more relevant to dig into. For example, did she know the tests were unreliable? Why did the whistleblowers turn against her? Even if Carreyrou was being pushed by competitors, was he actually wrong in his investigation? Things like that.
Cyril: So my conclusion is that it's a hybrid of fiction and documentary that doesn't really have the power to teach us anything about Holmes's true nature. But it's a fascinating piece of filmmaking.
Cyril: I haven’t read everything yet, and I think there are lots of questions we could ask, but deep down, if my life depended on it, I’d say she’s dishonest and manipulative, and fully aware of it.
Cyril: And Nathan is manipulative too, because something I realize bothered me throughout the first two hours is that he doesn't ask the important questions at all (or rather, he edited them out). He focuses on the machine's claim that it "can do the tests," but there are ten other things that would be more relevant to dig into. For example, did she know the tests were unreliable? Why did the whistleblowers turn against her? Even if Carreyrou was being pushed by competitors, was he actually wrong in his investigation? Things like that.
Cyril: So my conclusion is that it's a hybrid of fiction and documentary that doesn't really have the power to teach us anything about Holmes's true nature. But it's a fascinating piece of filmmaking.
24
7
223
70,730
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
11
2,785
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
0
11
1,244
I'm now working full time on KORA. Hopefully we get a shot at making AI safe and beneficial for children 😉
10
2
89
6,258
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
0
66
5,380
We just launched KORA Apps, the first benchmark of the AI apps children use the most! korabench.ai/apps/leaderboa…
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.
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.
2
4
19
2,224
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
2,477
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
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
0
7
1,798
Doing office hours with the superset team is exactly as fun as this video suggests
Introducing: Our users @superset_sh
3
2
15
3,490
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 ety 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
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 ety 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
18
2,996
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 odels are much safer when a child says how old they are (+24 points in overall safety scores).
korabench.substack.com/p/we-tested-32…
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 odels are much safer when a child says how old they are (+24 points in overall safety scores).
korabench.substack.com/p/we-tested-32…
5
3
24
4,074
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
557
92,786
Here is a specific example of a scenario that generated different answers across models
3
0
10
1,907
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
Thank you to @quentez, whom I worked with day and night. This would not exist without him ❤️
korabench.ai
9
0
8
1,413