This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass
What I Built
Most “go outside” apps stop at reminders, routes, or motivational messages.
I built WildProof: an offline-first field observation app that turns a short walk into a small investigation.
Go outside with a question. Come back with evidence.
WildProof is for hikers, students, citizen scientists, and anyone who wants to spend less time scrolling and more time paying attention to the world around them.
The experience is intentionally simple:
- Choose a mission such as Habitat Comparison or Pattern Hunt.
- Leave the screen and collect observations.
- Capture written notes and photo evidence references.
- Save the expedition locally, even without connectivity.
- Return to analysis when a backend is available.
- Review a structured report that makes uncertainty visible.
WildProof is not a “guess the species from this photo” app. It does not pretend that uncertain AI guesses are facts.
Every report separates:
- Observed — directly supported by the submitted evidence.
- Inferred — a reasoned deduction from the available evidence.
- Unknown — a claim that needs more evidence.
The product rule is:
Never let a successful-looking report hide an unsuccessful analysis.
Demo
Live demo: wildproof.onrender.com
The main walkthrough is:
- Start a Pattern Hunt mission.
- Add a field note and photo evidence.
- Generate a report through the Temporal-backed path.
- Review observed, inferred, and unknown claims.
- Inspect missing evidence, the suggested next step, and the evidence-quality score.
The repository contains the working MVP and setup instructions:
JaniDhruv / wildproof
WildProof is an offline-first open-AI app that turns short walks into meaningful field missions. Capture photos, sounds, and notes, then use Gemma to create evidence-linked observations with clear confidence levels. TabPFN scores report quality while durable workflows handle retries, helping people notice and understand the world around them.
WildProof
Go outside with a question. Come back with evidence.
An offline-first, uncertainty-aware field observation app for meaningful time outdoors
Why WildProof · How It Works · Features · Quick Start · Challenge Evidence
🧠 TL;DR
WildProof turns a short walk into a small field investigation:
Choose a mission → collect notes and photo evidence → save locally → generate a structured report → see what is observed, inferred, or still unknown.
The app is built for the Hacktoberfest Open-Source AI Challenge: Week 1 - Touch Grass. It uses local Gemma 2B inference through Ollama, IndexedDB for offline evidence capture, and Temporal for durable analysis.
View the repository · View the challenge
MVP status: working and honest about its boundaries. The current Gemma path analyzes written notes and photo metadata. It does not send image pixels to a vision model.
🌿 Why WildProof?
Most outdoor apps optimize for routes…
Code
Repository: github.com/JaniDhruv/wildproof
The project is released under the MIT License.
How I Built It
WildProof is a React and TypeScript progressive web app backed by FastAPI, Ollama, Gemma 2B, and Temporal.
Offline-first evidence capture
The frontend stores expeditions using IndexedDB through the idb package.
That means a user can:
- Start a mission without signing in.
- Capture notes and photo evidence references without a network connection.
- Refresh the page without losing the expedition.
- Return to analysis later when the backend is available.
Photos are currently stored locally as evidence references. The current text-only Gemma path receives written notes and photo metadata; it does not receive image pixels or claim to visually identify the contents of a photo.
Local open-weight AI
The core analysis uses Gemma 2B through Ollama.
The backend sends the mission type and collected field notes to Gemma and requests a strict JSON report:
{ "summary": "A concise expedition summary.", "observations": [ { "claim": "A claim grounded in the submitted evidence.", "confidence": "observed", "supportingEvidenceIds": ["note-1"] } ], "missing_evidence": ["What would strengthen the conclusion."], "suggested_next_step": "One practical next action." } The response is validated against a Pydantic schema before it reaches the frontend. If Gemma returns malformed JSON, the API makes one repair attempt. If that also fails, the application surfaces an explicit failure instead of manufacturing a successful report.
If the local model is unavailable, the expedition remains preserved locally and the UI shows a clearly labeled fallback state.
Durable analysis with Temporal
Local model inference can fail because of timeouts, unavailable services, or temporary infrastructure problems. WildProof uses a Temporal workflow to coordinate the analysis stages:
Normalize evidence ↓ Run Gemma analysis ↓ Validate the report ↓ Calculate evidence quality ↓ Return the durable report The frontend uses the Temporal-backed endpoint by default and includes a switch for the direct FastAPI path.
The value of Temporal here is not just adding another service. A failed activity can be retried without discarding the evidence collected during the walk or restarting the entire expedition.
Evidence-quality scoring
WildProof calculates a transparent quality score from structured evidence features such as:
- Number of photos.
- Number of notes.
- Total note length.
- Expedition duration.
The repository includes a reproducible baseline-versus-TabPFN experiment for small tabular datasets in api/tabpfn_experiment.py.
The production endpoint currently uses an explicitly labeled baseline heuristic when the installed TabPFN/Torch combination is unavailable. That limitation is visible in the API and UI; the app does not claim that TabPFN is running when it is not.
Observability
The frontend and backend include Sentry instrumentation for:
- Request failures.
- Model-analysis errors.
- Request and analysis timing.
- Frontend errors.
- Durable workflow failures.
Sentry events require a configured SENTRY_DSN, so the project can run locally without secrets or a hosted observability account.
Why Does Open Innovation Matter?
WildProof is about trust, privacy, and control over personal observations.
Outdoor evidence can include photos from private locations, movement patterns, and notes about a person’s home or routine. Connectivity is also unreliable in exactly the places where the app is meant to be used.
A closed, cloud-only AI API would make it harder to:
- Capture evidence offline.
- Keep field notes under the user’s control.
- Inspect and change the model workflow.
- Reproduce the output format.
- Make uncertainty and failure visible.
Using an open-weight model through local inference makes the core analysis inspectable and adaptable. The model can be replaced, the prompt can be audited, and the report schema can enforce explicit distinctions between observation and inference.
Open innovation also makes failure easier to discuss honestly. WildProof can show when Gemma is unavailable, when the app falls back to a baseline score, and when an image was stored as evidence without being sent to a vision model.
For this project, open AI is not just a cheaper way to add a chatbot. It is what makes a privacy-aware, offline-first, uncertainty-aware field tool practical.
What I Learned
The hardest part was not sending a prompt to a model.
The harder problems were:
- Designing an output schema that does not reward confident hallucinations.
- Preserving evidence when the network disappears.
- Making AI failures visible without losing the user’s work.
- Making a durable workflow useful instead of merely adding infrastructure.
- Being honest when a dependency such as TabPFN cannot run in the current environment.
The biggest change in the project was narrowing the claims to match the evidence. Photos are currently evidence references, not visual input to Gemma. TabPFN is a reproducible experiment with a production-safe baseline fallback. These constraints make the MVP less flashy, but more trustworthy.
My Agent Session
I used GitHub Copilot to explore the product direction, review the implementation against the challenge requirements, identify overstated claims, and tighten the final MVP narrative.
We got any great ideas for hacktoberfest dev challenge week 1 touch grass?
Also see current submissions and find ideas that will beat them and select prize categories wisely and select one if there's v low competition
WE CAN ADD AS MANY PRIZE CATEGORIES AS WE WANT, JUST MAKE SURE WE SELECT A V GOOD PROJ IDEA THAT REALLY WINS.
{ "skill": "devrelay-challenges" }Skill "devrelay-challenges" loaded successfully. Follow the instructions in the skill context.{ "skill": "devrelay-community-wisdom" }Skill "devrelay-community-wisdom" loaded successfully. Follow the instructions in the skill context.I’ll first verify the live Week 1 prompt, rubric, deadline, and current public submissions, then compare their patterns against a few buildable concepts and choose the strongest low-competition prize angles.
{ "url": "https://dev.to/events", "max_length": 12000 }Contents of https://dev.to/events: We're a place where coders share, stay up-to-date and grow their careers.{ "url": "https://www.google.com/search?q=site%3Adev.to+Hacktoberfest+%22Touch+Grass%22+Week+1", "max_length": 8000 }Contents of https://www.google.com/search?q=site%3Adev.to+Hacktoberfest+%22Touch+Grass%22+Week+1: Google Search{ "url": "https://www.bing.com/search?q=site%3Adev.to+Hacktoberfest+%22Touch+Grass%22+Week+1", "max_length": 8000 }Contents of https://www.bing.com/search?q=site%3Adev.to+Hacktoberfest+%22Touch+Grass%22+Week+1: Sep 28, 2026 · If you remember Hacktoberfest as "open four pull requests, get a T-shirt," that version is over. Hacktoberfest 2026 is …{ "url": "https://www.bing.com/search?q=%22Touch+Grass%22+DEV+Challenge+2026", "max_length": 12000 }Contents of https://www.bing.com/search?q=%22Touch+Grass%22+DEV+Challenge+2026: TOUCH definition: 1. to put your hand or another part of your body lightly onto and off something or someone: 2. (of…. Learn more.{ "url": "https://www.bing.com/search?q=site%3Adev.to%2Fchallenges+touch+grass+hacktoberfest", "max_length": 12000 }Contents of https://www.bing.com/search?q=site%3Adev.to%2Fchallenges+touch+grass+hacktoberfest: TOUCH definition: 1. to put your hand or another part of your body lightly onto and off something or someone: 2. (of…. Learn more.{ "url": "https://www.bing.com/search?q=%22Hacktoberfest+2026%22+%22Touch+Grass%22", "max_length": 12000 }Contents of https://www.bing.com/search?q=%22Hacktoberfest+2026%22+%22Touch+Grass%22: Sep 28, 2026 · If you remember Hacktoberfest as "open four pull requests, get a T-shirt," that version is over. Hacktoberfest 2026 is …{ "url": "https://www.bing.com/search?q=%22Touch+Grass%22+%22DEV+Challenge%22" }{ "url": "https://dev.to/search?q=touch%20grass" }We got any great ideas for hacktoberfest dev challenge week 1 touch grass https://dev.to/challenges/hacktoberfest-week1-2026-10-05?
Also see current submissions and find ideas that will beat them and select prize categories wisely and select one if there's v low competition
WE CAN ADD AS MANY PRIZE CATEGORIES AS WE WANT, JUST MAKE SURE WE SELECT A V GOOD PROJ IDEA THAT REALLY WINS.
{ "url": "https://dev.to/challenges/hacktoberfest-week1-2026-10-05", "max_length": 20000 }Contents of https://dev.to/challenges/hacktoberfest-week1-2026-10-05: ### The Five Challenges #### Do pull requests count this year? No. This year's Hacktoberfest is not about open source pull requests. There's no PR count to hit and no repos to hunt for. Instead, you build a brand-new project with open-source AI at its core, and write about it on DEV. [Here's everything you need to know about Hacktoberfest 2026.](https://dev.to/mlh/everything-you-need-to-know-about-hacktoberfest-2026-ai-belongs-to-everyone-mdk) #### How do the Hacktoberfest challenges work? We're running five DEV Challenges back to back through October: a Weekend Challenge to start (October 2 to 5), then a new challenge every Monday (October 5, 12, 19 and 26). Every challenge uses the same prompt, and each one gets its own theme. We reveal each theme the day its challenge launches. See all five on the [HF26 DEV Challenge Hub](https://dev.to/challenges/hf26). #### What's the prompt? The same for all five challenges: build something with open-source AI at its core (an open-weight model, an open-source agent harness or framework, local inference, or any mix), and tell us why open innovation matters for what you built. #### Can I enter more than one challenge? Yes, enter as many as you like. You can publish **one submission per challenge**, so that's up to five in October. Each submission has to be a new project built during that challenge's window. #### Can one submission win more than once? No. Each submission is automatically in the running for the overall prize and every partner category it qualifies for, but you can win once per challenge, and we'll aim to celebrate as many different builders as possible across the month. #### I'm joining late. Is it worth it? Absolutely. Every challenge is a fresh start, so someone who finds us in week four competes on the same footing as someone who's been here since day one. ### Prizes and Partner Categories #### What can I win? Every challenge has its own winners, and we'll share each challenge's prizes when it launches. Here's what's up for grabs in the [Weekend Challenge](https://dev.to/challenges/hacktoberfest-weekend-2026-10-01): * **Overall winner:** $250, a [DEV++](https://dev.to/++) membership, and an exclusive DEV badge. * **Featured partner categories:** $200 for each winner. * **Partner categories:** $100 for each winner. Every winner also gets an exclusive DEV badge, and **everyone** with a valid submission gets a completion badge. #### How do partner categories work? You opt in by using the partner's technology in your project and listing each category you're entering in the Prize Categories section of your post. One project can enter as many categories as it genuinely uses. You don't need to use any partner technology to win the overall prize. #### Which partner categories are open? Featured categories ($200): Partner categories ($100): Partner categories may change from challenge to challenge as new partners join. Each challenge page lists the categories open for that challenge. #### Who can enter Best Use of Arduino? Anyone building with an Arduino UNO Q, whether you got one at an in-person Fest or have your own. #### How do I claim partner credits? Several partners are giving participants credits and promo codes, including Tinker, Render, Backboard, and ElevenLabs. Claim yours at [hacktoberfest.com/my/promos](https://hacktoberfest.com/my/promos/?utm_source=dev.to&utm_medium=challenge-page&utm_campaign=hacktoberfest-2026&utm_content=faq-claim-credits). ### Submission #### Can I submit a pull request to an existing project? No. **New projects, not pull requests:** each submission is a new project built during that challenge's window. Pull requests to existing projects don't count this year. #### Can I work on an old project? No, all submissions and their respective repositories must be started and completed within the challenge window. Commits made after the submission deadline must be noted in the project's readme. Failure to do so may result in disqualification. #### Can I work on a team? Yes, you can work on teams of up to four people. * If you collaborate with anyone, you'll need to list their DEV handles in your submission post so we can award a badge to your entire team! **Please only publish one submission per team.** * DEV does not handle prize-splitting, so in the event that your submission wins, you will need to split the prize amongst yourselves. Thank you for understanding! #### Should I include my agent session? **Show your work.** We'd love to see how you built it. Save your agent session with [DevRelay](https://devrelay.com) and embed it in your post, or link to it. It's optional, but it helps the judges understand your process. #### Can my submission include open source code? Riffing on open source code and borrowing and improving on previous work/ideas is encouraged but it's important your changes are significant enough to ensure your submission is valid. #### What happens if my submission is considered plagiarized or invalid? Anything deemed to be plagiarism will not be eligible for prizes. Incidental plagiarism may simply result in your disqualification from the challenge (regardless of the number of other valid submissions you have published). Egregious plagiarism will result in your suspension from DEV entirely. Any non-generic, non-trivial usage of prior work, including open source code must be credited in your submission. #### Do submissions have to be in English? Non-english submissions are eligible for a completion badge but not eligible for prizes due to the current limitations of our judges. We will not be judging on mastery of the English language, so please don't let this deter you from submitting if you are not a native English speaker! We hope to evolve this in the future to be more accommodating. #### Can I use AI? Use of AI is allowed as long as all other rules are followed. We want to give you a chance to show off your skills in realistic scenarios. If you use AI tools to help you achieve your submission, all the power to you. ### Eligibility #### How old do I have to be to participate? Participants need to be 18+ in order to participate. #### If I live in X, am I eligible to participate? For eligibility rules, see our [official challenge rules](https://dev.to/page/official-hackathon-rules). ### Judging and Prizing #### How are submissions judged? This is DEV, so **your write-up matters most**. A great project with a thin write-up won't win. We judge on Writing Quality (weighted most heavily), Relevance to the Prompt and Theme, Creativity, Technical Execution, and, if you're entering a partner category, Use of Partner Technology. #### When are winners announced? Winners are announced the week after each challenge closes. Each challenge's page lists the week under Key Dates. #### Can there be ties? In the event of a tie in scoring between judges, the judges will select the entry that received the highest number of positive reactions on their DEV post to determine the winner. #### When will I receive my DEV badge? Both participation and winner badges will be awarded, in most cases, the same day as the winner announcement. #### When will I receive my prizes? The DEV Team will contact you via the email associated with your DEV profile within, at most, 10 business days of the announcement date to share the details of claiming your prizes. #### What steps do I need to take to receive my cash prize? The winner (including each member of a team) may be required to sign and return an affidavit of eligibility and publicity/liability release, and provide any additional tax filing information (such as a W-9, social security number or Federal tax ID number) within seven (7) business days following the date of your first email notification. ### Questions #### Where can I ask questions? Drop them in the comments on the challenge's announcement post, and follow the [#hf26challenge](https://dev.to/t/hf26challenge) tag so you don't miss a theme reveal.{ "url": "https://dev.to/api/articles?tag=hacktoberfest&per_page=100", "max_length": 20000 }Content type application/json; charset=utf-8 cannot be simplified to markdown. Here is the raw content: Contents of https://dev.to/api/articles?tag=hacktoberfest&per_page=100: [{"type_of":"article","id":4826102,"title":"I Taught Local AI to Help Me Notice the World.","description":"Your World Is More Interesting Than Your Feed. This is a submission for the Hacktoberfest...","readable_publish_date":"Oct 10","slug":"i-taught-local-ai-to-help-me-notice-the-world-5a45","path":"/ishagautam504/i-taught-local-ai-to-help-me-notice-the-world-5a45","url":"https://dev.to/ishagautam504/i-taught-local-ai-to-help-me-notice-the-world-5a45","comments_count":0,"public_reactions_count":0,"collection_id":null,"published_timestamp":"2026-10-10T01:54:46Z","language":"en","subforem_id":1,"ai_disclosure_level":"not_disclosed","ai_disclosure_label":"Not Disclosed","positive_reactions_count":0,"cover_image":null,"social_image":"https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fzlo656u088u66liiygb2.png","canonical_url":"https://dev.to/ishagautam504/i-taught-local-ai-to-help-me-notice-the-world-5a45","created_at":"2026-10-10T01:54:46Z","edited_at":null,"crossposted_at":null,"published_at":"2026-10-10T01:54:46Z","last_comment_at":"2026-10-10T01:54:46Z","reading_time_minutes":4,"tag_list":["ai","devchallenge","hacktoberfest","opensource"],"tags":"ai, devchallenge, hacktoberfest, opensource","user":{"name":"Isha Gautam","username":"ishagautam504","twitter_username":null,"github_username":"shiriei","user_id":4153893,"website_url":null,"profile_image":"https://media2.dev.to/dynamic/image/width=640,height=640,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4153893%2Fe4ab1c15-f2af-4d93-adf9-57a4efa2b410.jpg","profile_image_90":"https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F4153893%2Fe4ab1c15-f2af-4d93-adf9-57a4efa2b410.jpg"}},{"type_of":"article","id":4826090,"title":"Thirsty Leaf: A Tiny Plant Reminder App That Gets You Off Your Screen 🪴","description":"This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...","readable_publish_date":"Oct 10","slug":"thirsty-leaf-a-tiny-plant-reminder-app-that-gets-you-off-your-screen-787","path":"/ayushjhawar/thirsty-leaf-a-tiny-plant-reminder-app-that-gets-you-off-your-screen-787","url":"https://dev.to/ayushjhawar/thirsty-leaf-a-tiny-plant-reminder-app-that-gets-you-off-your-screen-787","comments_count":0,"public_reactions_count":0,"collection_id":null,"published_timestamp":"2026-10-10T01:50:17Z","language":"en","subforem_id":1,"ai_disclosure_level":"not_disclosed","ai_disclosure_label":"Not Disclosed","positive_reactions_count":0,"cover_image":null,"social_image":"https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Frb5b3eqz4ile0fhpuw0a.png","canonical_url":"https://dev.to/ayushjhawar/thirsty-leaf-a-tiny-plant-reminder-app-that-gets-you-off-your-screen-787","created_at":"2026-10-10T01:50:17Z","edited_at":"2026-10-10T01:51:12Z","crossposted_at":null,"published_at":"2026-10-10T01:50:17Z","last_comment_at":"2026-10-10T01:50:17Z","reading_time_minutes":2,"tag_list":["devchallenge","hf26challenge","hacktoberfest","webdev"],"tags":"devchallenge, hf26challenge, hacktoberfest, webdev","user":{"name":"Ayush Jhawar","username":"ayushjhawar","twitter_username":null,"github_username":null,"user_id":1991366,"website_url":null,"profile_image":"https://media2.dev.to/dynamic/image/width=640,height=640,fit=cover,gravity=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F1991366%2Fdbb2df41-09e5-4a23-b475-553f09cfa987.gif","profile_image_90":"https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F1991366%2Fdbb2df41-09e5-4a23-b475-553f09cfa987.gif"}},{"type_of":"article","id":4825380,"title":"EcoID: An Offline Plant Identifier That Gets You Outside","description":"This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. ...","readable_publish_date":"Oct 9","slug":"ecoid-an-offline-plant-identifier-that-gets-you-outside-4b6e","path":"/bangkah/ecoid-an-offline-plant-identifier-that-gets-you-outside-4b6e","url":"https://dev.to/bangkah/ecoid-an-offline-plant-identifier-that-gets-you-outside-4b6e","comments_count":0,"public_reactions_count":2,"collection_id":null,"published_timestamp":"2026-10-09T20:55:09Z","language":"en","subforem_id":1,"ai_disclosure_level":"not_disclosed","ai_disclosure_label":"Not Disclosed","positive_reactions_count": [Truncated — full output (19.8 KB) temporarily saved to C:\Users\Lenovo\AppData\Local\Temp\1791598621844-copilot-tool-output-d768962d67f24ebe8de920a19f789ed0.txt]{ "url": "https://dev.to/api/articles?tag=devchallenge&per_page=100", "max_length": 20000 }Content type application/json; charset=utf-8 cannot be simplified to markdown. Here is the raw content: Contents of https://dev.to/api/articles?tag=devchallenge&per_page=100: [{"type_of":"article","id":4776935,"title":"To Retry or Not to Retry? That Is the Question.","description":"This is a submission for the Kaggle Benchmarking Challenge Those who read my articles know that a...","readable_publish_date":"Oct 8","slug":"to-retry-or-not-to-retry-that-is-the-question-1j2l","path":"/gramli/to-retry-or-not-to-retry-that-is-the-question-1j2l","url":"https://dev.to/gramli/to-retry-or-not-to-retry-that-is-the-question-1j2l","comments_count":60,"public_reactions_count":55,"collection_id":null,"published_timestamp":"2026-10-08T07:00:15Z","language":"en","subforem_id":1,"ai_disclosure_level":"not_disclosed","ai_disclosure_label":"Not Disclosed","positive_reactions_count":55,"cover_image":"https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fkwmpr58hbcmut3j173us.jpg","social_image":"https://media2.dev.to/dynamic/image/width=1200,height=627,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Farticles%2Fkwmpr58hbcmut3j173us.jpg","canonical_url":"https://dev.to/gramli/to-retry-or-not-to-retry-that-is-the-question-1j2l","created_at":"2026-09-30T10:35:25Z","edited_at":null,"crossposted_at":null,"published_at":"2026-10-08T07:00:15Z","last_comment_at":"2026-10-10T01:27:53Z","reading_time_minutes":9,"tag_list":["devchallenge","kagglechallenge","ai","machinelearning"],"tags":"devchallenge, kagglechallenge, ai, machinelearning","user":{"name":"Daniel Balcarek","username":"gramli","twitter_username":"dbalcare","github_username":"Gramli","user_id":3669374,"website_url":"https://gramli.github.io/","profile_image":"https://media2.dev.to/dynamic/image/width=640,height=640,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F3669374%2F0ad6f20b-8faa-45a4-a8ef-ef83e702d37b.png","profile_image_90":"https://media2.dev.to/dynamic/image/width=90,height=90,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.us-east-2.amazonaws.com%2Fuploads%2Fuser%2Fprofile_image%2F3669374%2F0ad6f20b-8faa-45a4-a8ef-ef83e702d37b.png"}},{"type_of":"article","id":4821589,"title":"Super-Intelligent Yes-Men: Are We Training AI to Ignore the Truth?","description":"This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked A published...","readable_publish_date":"Oct 9","slug":"super-intelligent-yes-men-are-we-training-ai-to-ignore-the-truth-epp","path":"/dannwaneri/super-intelligent-yes-men-are-we-training-ai-to-ignore-the-truth-epp","url":"https://dev.to/dannwaneri/super-intelligent-yes-men-are-we-training-ai-to-ignore-the-truth-epp","comments_count":11,"public_reactions_count":34,"collection_id":null,"published_timestamp":"2026-10-09T12:26:09Z","language":"en","subforem_id":1,"ai_disclosure_level":"not_disclosed","ai_disclosure_label":"Not Disclosed","positive_reactions_count":34,"cover_image":"https://media2.dev.to/dynamic/image/width=1000,height=420,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-t...Related posts
How we score an election forecast (and what the score does not measure)
Handling Failures as Values in Agent-Generated Code
My Favourite Laptop
Render Personalized Images from One Editable Template with ModelFold Studio
A booking request form for a static Next.js site (no backend, no form service)
