yesnoerror

I built a new AI for @yesnoerror and have been using it for the past few weeks. It has been giving me unique insight into the latest AI research, alpha that I don't see anyone else getting right now. Excited to share it with you tomorrow. If you hold $YNE you will be able to use it.

Just got DMed some good news regarding the $YNE bridge to @base! @baseapp and @coinbase here we come 🚀

$YNE is going to connect to every DeSci project

$YNE is coming to @base! Thank you to our (mystery) partner for providing complete white glove service at no cost to @yesnoerror. Will share who they are once we are live!

$YNE IS COMING TO @COINBASE

I just saw someone who was very high up at @IBM (working on AI) sign up for early access to @yesnoerror. Amazing to see how many interesting people want this AI product. The beta list includes people from @AnthropicAI @Google @Meta @MIT @Yale @CarnegieMellon @xai @GroqInc and more. I started this project at the end of 2024 after seeing an inspiring post from @pmarca. Billionaires like @pmarca @chamath @reidhoffman @jackclarkSF started following the project. It has evolved a lot over time. And now here we are. Not only is the @yesnoerror AI agent itself really valuable, but I am about to be able to do some very fun things with the $YNE token once our bridge to @base is complete. Why is it exciting to bridge to @base? - Because the founder @jessepollak chats with me whenever I want to. - Because I have a telegram chat with the @base team and they proactively reach out to me asking if I need anything. - Because @yesnoerror and $YNE has real utility and the @base and @ethereum community value that. - Because there is a lot of innovation on @base with teams like @zora @flaunchgg and @farcaster_xyz! So many amazing flywheels we can create for the $YNE ecosystem and token. Onwards!

This will truly be the promised land. One brand (@yesnoerror), one main token ( $YNE), many sub brands and sub tokens that can be created by anyone, and everyone building in the $YNE ecosystem can build their own projects and a % all accrues back to $YNE holders. $YNE becomes a tokenized network for anyone building token based projects for research, science, or public good.

I was thinking that once we get to base we should start making some other mini apps under $YNE that accrue value back to the main $YNE token - thoughts? And that way we could have all sorts of apps, learning apps, games, we could have a whole network of apps/tokens under the $YNE umbrella. And $YNE holders benefit from all of it. We could even then get $YNE community members to make their own $YNE apps that accrue back to the main $YNE token. CC: @flaunchgg @base I feel like this could an awesome way for @yesnoerror to use your tech!

So cool to check @yesnoerror every day to see what new @arxiv AI research papers are being talked about the most today. And then amazing to instantly have AI analysis of each paper that breaks it down so that it is easier to understand. It is very fun and rewarding to build a product that is purely focused on helping to democratize knowledge, especially in the #1 most cutting edge industry today (AI). More key features to come which I haven't seen anyone create before that will make consuming this type of (sometimes) dense content easier and more efficient. I have already been able to yes @yesnoerror to do some research of my own on new ways to optimize the agentic features we are building into @octaneai for brands like @jonesroadbeauty and @iliabeauty. Thank you to everyone who has helped shape this AI agent so far, including @jackclarkSF (@AnthropicAI), @deedydas (@MenloVentures), and many more.

Ok, I love this feature I just added to @yesnoerror! You can now toggle the @arxiv paper titles between technical, simple, and ELI5 (explain it like I'm 5). This makes new research papers much more accessible to the average person because it isn't gating the information behind technical speak. See the three versions here.

And we are off to the races! So fun to check @yesnoerror every day to see the day's trending AI research papers. Let me know if you want to try it out. 1) @arxiv published the new papers that were submitted last Friday 2) @yesnoerror is auto indexing them 3) @yesnoerror is analyzing them with AI 4) @yesnoerror is tracking their engagement on @x to see which ones are being talked about the most This paper just jumped to the top of the trending list: "A diffusion-based generative model for financial time series via geometric Brownian motion" What is it? A score-based diffusion model that uses geometric Brownian motion to inject price-proportional noise when generating synthetic financial time series. Explain it like I'm 5 Teaching computers to add noise that grows with stock prices lets them create fake market charts that look and behave much more like real ones, including big crashes and bumpy volatility. Excited to see the race continue to unfold throughout the day! // identifying alpha // $yne

I am currently implementing feedback from @yesnoerror beta testers at @Google @AnthropicAI @MIT @Yale and @CarnegieMellon. Feedback is very positive and people have great suggestions ❤️

I want an easy way to keep up with the HUNDREDS of new AI research that comes out on @arxiv every single day. So I've been building something to help myself. Introducing @yesnoerror. I would love to share it with you! ❤️ I have not published a paper myself, I didn't go to college, but I love AI and I love frontier technologies where people are trying things nobody has ever tried before. I feel lucky to be where I am in life, but I want to learn and push myself even more. If you, like me, wish you could read and understand more about the latest developments in this amazing industry, you might also love this. I have been building this in private beta and updating it in real time as I get feedback from researchers and leaders at @AnthropicAI @MIT @Yale @CarnegieMellon and more. If you would like to be an early tester, please let me know 🧪🔬 The more feedback I get, the better we can make this, and the better we make this, the more informed and inspired a larger group of people can be.

Wooo! Our first @yesnoerror review from an @arxiv paper author!

Waking up to see this new paper from @scale_AI charting on the @yesnoerror trending feed. Authors: @anisha_gunjal, @aytwang, Elaine Lau, @vaskar_n, @BingLiu1011, and @SeanHendryx "Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains" Simplified: Teaching computers with detailed check-lists instead of vague thumbs-up ratings lets them learn better answers in medicine and science questions and makes it clear why they got a reward. Key findings: • Implicitly aggregated rubric rewards boost medical benchmark score by 28 % relative to Likert baseline. • Matches or exceeds rewards based on expert reference answers despite using smaller judges. What can it be used for: • Fine-tuning clinical decision support chatbots with medical safety rubrics. • Training policy-analysis or legal-reasoning models where multiple subjective factors matter. Detailed summary: Rubrics as Rewards (RaR) is proposed as an interpretable alternative to opaque preference-based reward models when fine-tuning large language models (LLMs) with reinforcement learning. Instead of asking humans to rank whole answers, domain experts (or a strong LLM guided by expert references) write a prompt-specific checklist of 7–20 binary criteria that capture essential facts, reasoning steps, style and common pitfalls. Each criterion is tagged Essential, Important, Optional, or Pitfall and given a weight. During on-policy training the policy model (Qwen-2.5-7B in the paper) samples 16 candidate answers per prompt. A separate judge LLM (GPT-4o-mini or smaller) is prompted either to score each criterion separately (explicit aggregation) or to read the full rubric and output one holistic Likert rating 1–10 (implicit aggregation). The normalized score becomes the scalar reward and the policy is updated with the GRPO algorithm. The authors curate two 20 k-example training sets—RaR-Medical-20k and RaR-Science-20k—by combining existing medical and science reasoning corpora and generating synthetic rubrics with o3-mini or GPT-4o. Evaluation on HealthBench-1k (medical reasoning) and GPQA-Diamond (graduate-level physics/chemistry/biology) shows that RaR-Implicit yields up to a 28 % relative improvement over simple Likert-only rewards and matches or exceeds rewards computed by comparing to expert reference answers. Implicit aggregation consistently outperforms explicit, demonstrating that letting the judge decide how to combine criteria works better than fixed hand-tuned weights. Rubric supervision also helps smaller judge models. When asked to rate preferred versus perturbed answers, rubric-guided judges choose the preferred answer far more reliably than equally sized Likert-only judges, narrowing the gap between a 7 B evaluator and GPT-4o-mini. Ablations reveal that prompt-specific rubrics beat generic ones, multiple criteria beat essential-only lists, and access to an expert reference while drafting rubrics materially boosts downstream performance. Even human-written and high-quality synthetic rubrics perform on par, suggesting scalability. RaR generalises Reinforcement Learning with Verifiable Rewards (RLVR): when the rubric has just one correctness check, the framework collapses to RLVR’s exact-match reward. By exposing each aspect of quality explicitly, RaR is more transparent, auditable and potentially harder to reward-hack than neural reward models. The authors discuss extensions to real-world agentic tasks, dynamic curriculum via rubric weights, and formal robustness studies. -- Over 500,000 pages of research are published on @arXiv every month. Hidden within are breakthrough insights that could transform your work — but finding them is like searching for diamonds in an ocean of data. @yesnoerror cuts through the noise to surface the most impactful research for your projects, investments, and discoveries. // $yne

Ok! I am now tracking engagement on all new @arxiv papers on @x and ranking the top 50 most talked about papers. This is one type of signal to pay attention to, but imo the most interesting is still the feed of papers that are NOT trending on @x but instead have alpha that nobody is talking about. The hidden gems. Now that I have recent and trending completely automated, the next feed I am making is the alpha feed. Under the radar new papers that show signs of high alpha.

Ok, simple feature, but a good one. If @yesnoerror hasn't yet indexed the paper you want to look at (probably because it is an old one), then you can now add it yourself. Feature suggestion from @anmorgunov // onwards // $yne