Introducing HUMAINE: the LLM benchmark that puts real human experience first 🎯 21,352 human evaluators. 27 models. 22 demographic groups. 5 evaluation dimensions. In partnership with @huggingface. See insights below 🧵

Gemini 3 Pro hits a 69% trust score on HUMAINE, up from 2.5's 16%. CEO @Phelimb: "It's the consistency across a very wide range of different use cases [...] and a style that appeals across a wide range of different user types.” More on @VentureBeat ↓ https://t.co/L4dmSFhZFC

Prolific is now natively integrated with @trydialogueai 🙌 Run end-to-end research in one platform: → AI-assisted study design → Select from 200K+ participants → Run AI-moderated interviews → Get instant AI-generated insights Try it now: https://t.co/ZdVmYaYCMf

BNDS actively manages bonds & preferreds seeking stable returns. 📊

Excited to partner with @Prolific! Dialogue is now a Premier Marketplace Partner, offering seamless, self-serve access to Prolific’s vetted global participant network. Better research, faster decisions, real insights from real people. 🚀 👉 Read more: https://t.co/2VKjjECtTZ

🇬🇧 At the @UniversitiesUK Research & Innovation Conference, Dr. Simon Jones discussed digital transformation in research services, with insights from 35,000+ researchers using Prolific. He explored challenges and successful institutional practices. Great to sponsor another #UUK!

Joined a great panel at the @AI_AInstitute Generative AI Summit, also featuring @NatWestGroup, @BBC, and @PublicisMedia 🙌 We discussed successfully putting GenAI strategies into practice - one point being to incorporate humans-in-the-loop early. Thanks to all we met in London!

"Market dominance doesn’t equal best user experience." @Forbes highlights @GoogleDeepMind's Gemini models as the most satisfactory in the market according to @Prolific's HUMAINE leaderboard for human-aligned LLMs, past ChatGPT and more. See more ⬇️ https://t.co/YL6JMLER5x

On @MLStreetTalk, Prolific CEO @Phelimb notes that maintaining the human element in AI development processes involves building a direct connection between those collecting data and the participants providing it. 🎥 Full episode here → https://t.co/CV56OXoMJq

This Week Only ⏰ Get 50% off UnKibble: - 100% human-grade ingredients - No fillers or preservatives - Vet-developed, complete recipes - Picky-eater approved - 1,700 5-star reviews

We discussed: → What “good” human data looks like and how participant expertise shapes it → Behaviors we still can’t evaluate well with current rater pools → An ideal eval stack across sourcing, task design, QC, BPOs, and tooling And more. Thanks to all who joined us!

Last week we hosted an exclusive London dinner for leaders building the future of AI 🇬🇧 With experts from @AnthropicAI, @Salesforce, @awscloud and others, we explored how to align models with our intentions and design effective eval workflows. CEO @Phelimb opened the event.

AI at the Thanksgiving dinner? Here’s what the US public think 🦃 We ran a themed survey asking about AI in family traditions, part of which we used to demo rapid human data collection via Prolific at @DeepLearningAI's #AIDev25. @ana_in_sf talks through results. Happy holidays!

Leading human-aligned models right now: → Gemini-3-Pro, @GoogleDeepMind → Gemini-2.5-Pro, @GoogleDeepMind → DeepSeek-V3-0324, @deepseek_ai → Magistral-Medium-2506, @MistralAI Follow on @huggingface 📊 https://t.co/x1wLUxWuE0

🔝 Gemini 3 Pro by @GoogleDeepMind has surpassed ALL frontier models on the human-centered HUMAINE benchmark for LLMs. The model scores 19.74 (+0.49 over 2.5 Pro) with a 81.9% probability of ranking #1 after repeated evaluation. It leads in 4 of 5 evaluation dimensions.

Huge props to all organizers, sponsors, and partners. Check out how to build, manage, and scale AI data annotation and evaluation tasks with Prolific’s AI Task Builder here ⬇️ https://t.co/ENwUMxLcIU

We had live product demos of the Prolific API, HUMAINE benchmark, and an RLHF example via AI Task Builder. A packed booth and swag cleared out. Enjoyed chats with @Amazon, @Google, @MistralAI, and more integrating human data into their AI workflows. And great seeing @AndrewYNg!

EXW vs. FOB vs. DDP shouldn’t slow a shipment down. Download the Incoterms 2020 cheat sheet and get clarity in 2 minutes. → Click for free download

Thank you #AIDev25 x NYC 🗽 It was a pleasure sponsoring the @DeepLearningAI conference in the big apple this month. 3,000+ leading developers, builders, and researchers connecting over AI innovation.

According to Prolific’s new “Humaine” study, users’ favorite is no longer ChatGPT but Gemini 2.5 Pro. Top 5: Gemini 2.5 Pro, DeepSeek v3, Mistral “Magistral Medium”, Grok 4 and Grok 3. In the AI race, it’s less about raw benchmarks and more about being human-friendly.

Scaling human eval for emotional AI shouldn’t mean sacrificing quality. One AI leader used Prolific to source 7,200+ multilingual evaluators and collect ~100k submissions in 3 months, with cultural-nuance screening and real-time QC. Full story → https://t.co/334qfzGXip

What do we do about AI contamination in survey research? Some thoughts on going forward: 1) @YouGov and @Prolific are working to ensure high quality responses. (Disclosure: I have no personal financial relationship with either firm, but have used both to collect data.) Others

A conference for serious Christian men and their families. Join pastors, elders, seminarians, and churchmen for three days of preaching, worship, and fellowship around “The Church: The Bride of Christ.” Meals, a new-release book, merch, and all sessions included.

⚡️ @ana_in_sf is on a roll! At our second hosted SF AI meetup, @InflectionAI went "Beyond the Benchmark," digging into how human insight shapes post-training, alignment, evals, and the next wave of emotionally aware models.

When AI becomes less deterministic, how do we measure “goodness” if we’ve never agreed on what “good” means? Prolific's Enzo Blindow and Sara Saab joined @MLStreetTalk to explore why true alignment starts with understanding human values.