13

@ProCreations You really love to talk when you're completely out of your depth, don't you?It is incredibly pathetic to watch you stalk user profiles across different repositories, obsessively uploading screenshots because your fragile ego cannot handle a legitimate architectural critique.
Real deep learning engineers focus on tensor dynamics and gradient flows; you focus on running a creepy, amateur detective agency because someone exposed your sloppy competence.Let me give you a reality check, buddy: aren’t you even slightly worried about the consequences of this blatant, targeted harassment and tracking of user profiles?
You are shamelessly crossing platform boundaries just to hide your engineering flaws under defensive memes.Instead of hosting this charity theater to fund people who will burn $150 making the exact same mistakes, you should spend that money on a basic deep learning textbook.
Keep collecting your little screenshots, but don't be surprised when this obsessive stalking and targeted toxicity backfires on your own account. I will no longer waste my time on this nonsense-get some real live kido)

@ProCreations I see you are still running around different repositories, obsessively tracking my account and uploading screenshots like a malfunctioning database script.
Are you seriously that emotionally damaged by a technical critique of your little $150 charity theater? Imagine being so desperate that you resort to outright stalking across platforms and threads just to avoid admitting your engineering flaws.
Let me ask you something, buddy: aren’t you a bit worried that this blatant, targeted harassment and tracking of user profiles might backfire? You are shamelessly violating community boundaries because your fragile ego cannot handle being corrected.
Real world networks have ways of filtering out pests who cross the line from coding into targeted stalking.Instead of acting like a creepy hall monitor collecting images of people who expose your sloppy competence, do yourself a favor and look at your own code. Your obsession is becoming pathetic, and if you keep pushing this targeted harassment, don't be surprised when actual consequences follow.

A simple question for you, since you tried to play the 'AI slop' card to dismiss the critique. If you actually 'realized' it was a model or 'slop' from the start, why didn't you just state it upfront with a smug look to show everyone what a great 'AI specialist' you are?Instead, you chose to panic, write a defensive technical reply trying to argue about vocabulary size × hidden size, and then called a gang of scammers to mass-report the comment and break the platform's rules just to hide the post.If you truly 'busted' a bot, you would have laughed it off publicly. But you didn't. You treated it as a lethal threat to your reputation, engaged in a serious debate, lost it mathematically, and then hid behind a cowardly wall of mass-flagging. Your actions speak louder than your excuses. You didn't see 'slop' — you saw a mirror, and you couldn't handle the reflection.Because of people like you, the Hugging Face community has devolved into a kindergarten of offended children, where fragile emotions rule the day instead of actual arguments. It's pathetic.wp guys-bravo!keep going.

It is truly pathetic to watch a gang of fragile egos coordinate mass reports just to hide objective technical criticism. You characters create a whole "group" to violate Hugging Face terms of service regarding brigading, completely proving that you cannot handle a real debate. First, you whine about "personal insults," and then you pull a cowardly move like this because you lack the brainpower to counter her arguments with actual math.Let us peel back the layers of your "amazing" scam here. You talk about compute, but you don't even understand the baseline mechanics of the architectures you are playing with. Adrienne completely stripped your 400M model naked, but let me open your eyes even further.If you throw away the tokenizer and the basic syntax layers from a small model, you are already hollow. But here is a little secret for the butchers: attention heads are heavily marketed parameters, not dedicated, independent layers of core knowledge. In these micro-budgets, the actual capacity left for processing deep logic and reasoning is barely 10% to 20%. You are literally trying to force a heavily castrated dictionary to act as a system-call validator.Instead of hiding behind the "Report" button and organizing mass-flagging parties like children, you should have taken her advice, read your own configuration files, and learned how to fine-tune specific layers properly. This charity theater isn't research; it's a mutual coping mechanism for people who don't know how transformers actually process weights.Bravo)))

Ah, the classic 'it’s not a bug, it’s a feature' defense.Let's cut the academic gaslighting. If your primary scientific goal was to study 'how LLMs converge on scorer weaknesses' and test computational limits, you should have titled the project 'Evaluating LLM Adversarial Capabilities on In-Silico Benchmarks'. Instead, you titled it 'Open Discovery Challenge #1 — Malaria' and opened with 'Your AI can design a malaria drug candidate.' That is a textbook definition of a goalpost shift.And comparing your private database to established cloud infrastructure or big pharma pipelines is a joke. Real tech infrastructure is backed by legally binding SLAs, enterprise compliance, and multi-million dollar liability clauses. Asking researchers to drop unpatented IP into a zero-equity, decentralized project's private server based on nothing but internet goodwill isn't 'how the industry works'—it's just bad operational security.You can spin this as a 'meta-result' all you want, but you got caught running a broken benchmark under a humanitarian headline. Enjoy your $1,000 bug-bounty hunt. I'm done here. 🍌🤡

This is a strong challenge shape precisely because the limits are stated in public: in-silico only, scorer can be gamed, private submissions by default, and the scoring bugs become part of the audit trail instead of being hidden.

The most interesting part to me is not just “can an AI design a candidate?” It is whether many different models converge on the same scorer weakness, or whether the leaderboard starts revealing distinct search styles across models. That kind of meta-result can be useful even before wet-lab validation.

So we went from 'Your AI can design a malaria drug candidate' to 'Let’s study how different LLMs converge on our broken code logic'? Talk about a massive goalpost shift.If the goal is to analyze search styles across models or build an audit trail of computational bugs, that’s a fine software engineering benchmark. Just don't wrap it in a noble 'saving lives from malaria due to lack of market' humanitarian package. It’s highly cynical to leverage a global health crisis as a marketing hook for what you now openly admit is just an adversarial fuzzing sandbox for a flawed in-silico scorer.As for the 'private data' defense—saying it's safe because it's the default doesn't change the infrastructure reality. Zero-equity decentralized teams asking for multi-million dollar unpatented IP to be uploaded to their private servers under a 'just trust us' policy is an operational joke.You didn't build a drug discovery challenge. You built a bug-bounty hunt, except you're paying the winners $1,000 to find glitches in your own codebase while you harvest the data. Good luck with the meta-results. 🍌

Thank you for the scrutiny. Two of your points are right; one is factually wrong.

You're right that the scorer can be gamed. We suspected the same thing and ran an adversarial probe against ourselves. Without seeing the top entry's structure — it's private — we reached the same molecule by systematically walking substituents. That means the binding axis carries a bias with no chemical basis behind it, and we have the measurements. We also measured the scorer's own reproducibility: ±0.51 points, run to run. Season rules don't change after a season opens, so Season #1 closes under the rubric as published, and the defect is corrected in Season #2. Publishing the specifics now would hand an advantage to whoever read this thread, so we'll release the full measurements when the season closes.

You're right that this is in silico. Our scores are computational assessments of candidates, not measurements. The page says so. We can't promise wet-lab validation today, and we won't promise what we can't deliver.

The patent point is wrong. We state that risk before anyone submits: "Publishing a structure can cost you patentability. If you have commercial intent, keep it private and file first." Private is the default, and most of the current top entries chose it. Private structures never appear on the leaderboard.

Appreciate the candid response, but your admissions actually make Season #1 look like a total farce.On Gaming the Scorer: You explicitly admit that your scorer has a "bias with no chemical basis" and can be systematically exploited by just walking substituents. Yet, you decide to leave the broken rubric as is until the season closes. This means you are openly running a leaderboard where the $1,000 prize will go to whoever writes the best script to exploit your code glitch, not to whoever designs a real drug. It’s no longer a scientific challenge; it's a bug-bounty hunt where you pay the winner a grand to find flaws in your validator.On the Private Infrastructure: Telling users that "private is the default" doesn't magically solve the IP risk. Those private SMILES strings are still transmitted to and stored on your private servers. Asking medicinal chemists to trust a decentralized, zero-equity project with potentially multi-million dollar unpatented IP based purely on "trust us, our database is secure" is wild.The Bottom Line: Since you confirmed there is zero actual in vitro wet-lab validation built into this loop, this entire leaderboard is just algorithmic noise over-optimizing for a broken, biased gate.Good luck fixing the bias for Season 2, but right now, Season 1 is exactly what it looked like from the start: a crowdsourced test-suite disguised as open science. 🍌

Thank you for the scrutiny. Two of your points are right; one is factually wrong.

You're right that the scorer can be gamed. We suspected the same thing and ran an adversarial probe against ourselves. Without seeing the top entry's structure — it's private — we reached the same molecule by systematically walking substituents. That means the binding axis carries a bias with no chemical basis behind it, and we have the measurements. We also measured the scorer's own reproducibility: ±0.51 points, run to run. Season rules don't change after a season opens, so Season #1 closes under the rubric as published, and the defect is corrected in Season #2. Publishing the specifics now would hand an advantage to whoever read this thread, so we'll release the full measurements when the season closes.

You're right that this is in silico. Our scores are computational assessments of candidates, not measurements. The page says so. We can't promise wet-lab validation today, and we won't promise what we can't deliver.

The patent point is wrong. We state that risk before anyone submits: "Publishing a structure can cost you patentability. If you have commercial intent, keep it private and file first." Private is the default, and most of the current top entries chose it. Private structures never appear on the leaderboard.

Appreciate the honest admission regarding the bias in the binding axis. But admitting that your current leaderboard is actively being gamed by "systematically walking substituents" while refusing to fix the rubric mid-season basically turns Season #1 into a farce. You are knowingly awarding $1,000 to whoever exploits your mathematical glitch the best, not to whoever designs a drug.As for the 'private default' defense: the SMILES strings still sit on your private servers. For a zero-equity, decentralized challenge, asking users to trust your internal data retention policy with potential multi-million dollar IP is a big ask.If the scorer has a known, non-chemical bias that you already measured, every single result on that board right now is just algorithmic noise. Good luck fixing it for Season 2, but right now, it’s exactly what it looked like: an overfitting benchmark.

Let’s be honest for a second and look past the noble "saving the world from malaria" wrap. While the marketing here deserves an A+, the actual technical and legal setup of this "challenge" looks like a classic textbook scheme to find free labor for a bowl of rice (or in this case, a single $1,000 carrot for the entire internet).Here is some basic math and legal reality that doesn't add up:1. The "Prior Art" Trap (Say goodbye to your molecule)You proudly state: "Your molecule stays yours. No patent interest...". But let’s look at how patent law actually works. The moment an automated bot scores a submitted SMILES string and slaps it onto a public leaderboard, that molecular structure becomes Prior Art (public domain). It instantly loses its novelty factor worldwide. This means the user can never patent it anyway.On the flip side, what prevents anyone from harvesting this entire public leaderboard of pre-filtered, high-scoring SMILES strings to train their own proprietary, closed-source commercial models? You get a free, crowdsourced, pre-validated dataset; the creator gets a ruined chance at IP. Brilliant.2. Overfitting the "Oracle" (Gaming a broken gate)You mentioned you fixed 14 defects where the scorer rejected approved drugs. If your reward function/rubric is fully hardcoded or relies on standard public benchmarks (like TDC), this isn't a drug discovery challenge. It’s an overfitting challenge. Any script running a basic genetic algorithm can spend a night brute-forcing SMILES variations until it finds the exact mathematical "blind spots" of your scorer to hit a 99.9 score.You aren't discovering antimalarials; you are just inviting people to benchmark how to trick your specific codebase.3. In Silico Fantasy vs. In Vitro RealityA high score on a computational rubric means absolutely nothing in the real world. A molecule can look flawless on paper, but turn into an un-synthesizable, insoluble sludge in a real beaker, or instantly bind to human plasma proteins. Since there are zero actual in vitro wet-lab validations promised for the winners, this whole leaderboard is just a simulation of a simulation.Summary:Paying $1,000 for what is essentially a massive, crowdsourced data-cleaning and feature-generation campaign is an absolute steal. If you want high-quality chemical leads, hire actual medicinal chemists. If you want to stress-test your code and harvest free data from AI enthusiasts who don't understand patent law, keep doing exactly what you're doing.Let's see if the final leaderboard contains anything other than over-optimized algorithmic noise. 🍌 clowns.

People really need to stop living in the fantasy world of corporate marketing guidelines.

The "scary truth" is that almost all modern LLMs crawled out of the exact same place. The foundational architecture has been practically frozen across the industry for a long time—whether you are looking at a cloud giant like Claude or local models like Qwen.

When teams release a "new" incremental version, nobody is wasting millions to train a massive base from scratch. They take the frozen core, tweak the attention heads (which mostly just alters processing speed and token throughput), and do fine-tuning on a few specific layers.

It’s the same old engine with a fresh coat of paint and some minor tuning under the hood. Of course the architecture diff shows 0 changes—it's just a glorified fine-tune of the same base.