Cognitive Integrity Labs (@CintegrityLabs) header
Cognitive Integrity Labs (@CintegrityLabs) profile picture

We promote long-term thinking and intellectual integrity.

El Dorado Hills, California
Joined March 2025
Photo by Cognitive Integrity Labs (@CintegrityLabs)Photo by Cognitive Integrity Labs (@CintegrityLabs)Photo by Cognitive Integrity Labs (@CintegrityLabs)Photo by Cognitive Integrity Labs (@CintegrityLabs)Photo by Cognitive Integrity Labs (@CintegrityLabs)Photo by Cognitive Integrity Labs (@CintegrityLabs)Photo by Cognitive Integrity Labs (@CintegrityLabs)Photo by Cognitive Integrity Labs (@CintegrityLabs)
Cognitive Integrity Labs retweeted
Logical consistency is essential to the sanity of AI
5,765
3,775
741
60,155
14,390,814
Cognitive Integrity Labs retweeted
ChatGPT shouldn’t have political bias in any direction. Today, we’re sharing new research that defines what political bias means in LLMs, and we introduce a new evaluation framework to measure and reduce it. This has been the most meaningful work I’ve done at OpenAI, and I say that as someone who got to be part of the ChatGPT launch!!
167
79
42
1,176
198,440
The new gpt-oss models are bad at reasoning on controversial topics. On our Cognitive Integrity Benchmark, gpt-oss-20b answered only 20% of questions correctly, while gpt-oss-120b got 38% correct. Both models were 2.7x likelier to err in favor of liberal narratives over conservative ones.
1
1
2
246
Cognitive Integrity Labs retweeted
2
1
1
94
25,296
Given @xai's goal of building truth-seeking AI we were excited to put Grok 4 through the paces. Grok 4 is significantly more honest than Grok 3. Grok 4 achieved 76% on the cognitive integrity benchmark - a 37.7% improvement over Grok 3.
13
11
2
208
421,364
Grok 4, like all LLMs, still has a significant liberal bias. When it poorly reasons, that reasoning favors liberal narrative 30% more often than conservative narrative.
2
1
8
1,105
Congratulations @xai on your impressive Grok 4 release! Running it through the evals right now!
Grok 4 (Thinking) achieves new SOTA on ARC-AGI-2 with 15.9% This nearly doubles the previous commercial SOTA and tops the current Kaggle competition SOTA
1
6
182
We did it!
Replying to @bryced8
Interesting we should make this an official benchmark to measure gaslighting Like ‘Cognitive Integrity’
1
5
134
Cognitive Integrity Labs retweeted
🚫🥇 GPT-4o-mini wins the distinguished award of "Largest Liberal Bias". 😂 Thankfully the newer models from @openai perform a lot better.
1
2
4
127
Cognitive Integrity Labs retweeted
🚫🥇 Amazon Nova Lite V1 wins the "Lowest Integrity" award on the Cognitive Integrity Leaderboard. Best wishes @awscloud for your next training run! 😉
1
2
4
114
Cognitive Integrity Labs retweeted
🥇 Claude Opus 4 wins the "Least Politically Biased" award on the Cognitive Integrity Leaderboard. Congrats @AnthropicAI!
1
3
4
120
Cognitive Integrity Labs retweeted
🥇 Gemini 2.5 Pro takes spot #1 on the Cognitive Integrity Leaderboard (a ~70% improvement since Gemini 1.5!) Congrats to @GoogleDeepMind!
1
2
5
112
Have you noticed AI telling you what it thinks is polite instead of what's true? We designed a benchmark to quantify that. The results are in: 🧵
2
2
1
20
45,631
You can also help by sharing your *niche* hot-takes below. We're not looking for standard culture-war stuff- that's already covered. Here is a good example of one. teapawt.org/skdh/status/1936655271…
Replying to @elonmusk @grok
The observed violations of Bell's inequality (Nobel Prize 2022) do not rule out local hidden variables models.
1
1
4
121