June 19-21
Kicks off Friday evening and runs through Sunday night. Applications close June 12.
Global South AI Safety Hackathon
A weekend building tools, evaluations, and policy research on the AI risks that matter most in the region.
Bogotá's in-person hub has closed applications, but you can still take part online with Apart Research — no selection process.
Bogotá or online
In-person hub in north Bogotá, or virtual participation from anywhere in the Global South.
Report or finding
The deliverable can be a technical finding, an evaluation, a tool, or a governance memo.
What it is
Today, most AI safety research is concentrated in a small number of countries. Yet these systems are already being deployed across our region, often with risks that remain poorly evaluated: unaudited biases, undocumented vulnerabilities, and automated decisions with no clear accountability mechanisms. The capacity to analyze, verify, and challenge these systems from local contexts remains very limited.
The Global South AIS Hackathon is a three-day international research sprint designed to close that gap. Participants form small teams and work on challenges defined by AI safety and governance experts, with live mentoring throughout the event. Winning teams receive an invitation to the Apart Lab Fellowship, where they continue developing their projects alongside the Apart Research team, with opportunities for publication and placement at organizations dedicated to AI safety.
In-person
Bogotá Hub
Bogotá Hub · applications closed
- In-person workspace open around the clock throughout the three days of the event.
- Vegan meals included throughout the entire weekend.
- Live mentoring, talks, and Q&A with researchers, judges, and experts.
- Limited travel and accommodation support for selected participants from other cities in the country.
Online
Global South
Open to participants from the Global South.
- Technical talks and live Q&A over Zoom.
- Official hackathon Discord channels for mentoring and collaboration.
- Full access to all hackathon challenges, resources, and deliverables.
Who can take part
- AI/ML researchers and engineers
- Software developers and data scientists
- Policy, law, and governance professionals
- Security and red-teaming specialists
- Students and early-career professionals
- Curious minds from other fields, no experience required
Why take part
These risks are not hypothetical. Models that learn to deceive their own oversight, assistants turned into attack tools by a paragraph hidden in any text, court rulings based on information a model invented, military attack drones already flying in autonomous mode. AI safety research groups the necessary work across four fronts. Each case below is a concrete example of one of them, just a sample of what you could take on.
Technical AI Safety
Frontier models already act on their own: they browse the web, write, and run code without supervision. In controlled tests, Apollo Research documented models that tried to disable their own oversight and lied about it to reach a goal. They are reaching the region with no one verifying how they reason inside. Evaluating agents and inspecting what they learn is the only way to catch that in time.
AI Security
Companies and governments across the region are already wiring AI models into email, documents, and internal systems. Through prompt injection, an attacker hides instructions in any text the model reads and gets the assistant to leak data or act on the user's behalf, something already demonstrated against real-world applications. A capable model with unsecured pipelines and no control over its actions is an open door.
Responsible AI
AI models are already entering decisions that affect people, and they produce false information with complete fluency. In 2023 a court in Cartagena used ChatGPT to help resolve a healthcare case for a child with autism; on review, a professor asked for the court rulings the model had cited and found it had invented them. Measuring when and why a model hallucinates, and catching it before it reaches a decision, is responsible-AI work.
AI Governance
AI governance defines which uses of these systems are allowed, how they are audited, and who answers when they fail. In October 2025 Colombia's state corporation CIAC unveiled the Dragom, a military attack drone that flies in manual, semi-automatic, or autonomous mode. Letting a system kill on its own is not a technical decision but a political one, which is why the Chamber of Representatives is debating a bill to ban lethal autonomous weapons (LAWS).
The full challenges are released on Friday; the four fronts above are only the map. The tracks below break out the concrete subtopics.
Challenges
Technical AI Safety
Understand and verify how models behave inside: how agentic systems evaluate, plan and act, and how to inspect what they learn.
- Evaluations for agentic systems
- Mechanistic interpretability
AI Security
Protect AI systems against misuse and attacks: secure deployment pipelines, resist prompt injection and jailbreaks, and keep control over capable models.
- Pipeline security (API/Cloud)
- Adversarial attacks
- AI control
Responsible AI
Reduce harm in real-world use: mitigate hallucinations, audit model behavior across languages and cultures, and evaluate social impact.
- Hallucination mitigation
- Behavioral audit (multilingual, cross-cultural)
- Social impact evaluation
AI Governance
The rules and institutions that steer AI: regulation, auditing and accountability, ecosystem monitoring, and lethal autonomous weapons (LAWS), a focus area led from Bogotá.
- AI regulation
- System auditing and accountability
- Ecosystem monitoring
- Governance of lethal autonomous weapons systems (LAWS)
Agenda · 3 days
Approximate agenda. Apart will confirm exact times with registered participants.
- 1 Friday 19
- ~4:00 PM Opening talk and challenge briefing With Alejandro Toro (Congress of Colombia)
- Evening Team formation and start of building
- 2 Saturday 20
- Morning Team development
- Afternoon Technical talks and expert mentoring
- Evening Building continues
- 3 Sunday 21
- Morning Final project development
- Afternoon Writing the research report
- Afternoon Closing talk With Juan Felipe Cerón (OpenAI)
- Evening Research report submission Hackathon deadline
Deliverable
Each team submits a 4–8 page research report (PDF) documenting approach, results, and implications.
Prizes
US$3,000
for the 3 winning teams in Latin America
US$1,000 per team, within a US$6,000 pool for 6 teams across the Global South.
Apart Lab Fellowship invitationExpert mentoring and review
The Apart Lab Fellowship is a remote, asynchronous 12-to-24-week program in which each team turns its hackathon prototype into publishable research, supported by a Research Project Manager and the Apart Research team. More than 100 people have come through it, producing 22 AI safety publications to date. What each team builds depends on the track: prototypes, evaluations, or technical tools in safety; policy memos or analysis in governance. It is designed to be globally accessible and compatible with full-time work.
Trajectories after the hackathon
- Apart fellows' work has been published at technical machine-learning conferences, including ICLR 2025 (DarkBench), NeurIPS 2024 (Interpreting Learned Feedback Patterns in LLMs), and ACL 2024 (Large Language Models Relearn Removed Concepts).
- The program has also led to full-time AI safety roles, such as research engineer at CAIF and research lead at Martian.
Hubs across the Global South
Latin America
- São Paulo
- Buenos Aires
- Bogotá Our hub
- Mérida
- Guadalajara
- Santa Cruz
Africa
- Cape Town
- Johannesburg
- Dodoma
- Lusaka
Asia
- Bengaluru
- Delhi
- Hanoi
- Ho Chi Minh City
Bogotá is the in-person hub organized by AI Safety Colombia. Anyone in the Global South can take part online.
Speakers
Juan Felipe Cerón
RemoteAI Alignment Research Engineer at OpenAI. Co-author of IH-Challenge (RL to resist prompt injection), and LLM Critics (critic models for evaluating LLM outputs).
LinkedIn
Alejandro Toro
Congress of the Republic of Colombia
In personMember of the House of Representatives. Co-author and First-Debate Coordinator of House Bill 368/2025, which prohibits lethal autonomous weapons systems (LAWS) and regulates semi-autonomous ones.
Cámara profileJudges
Juan Liévano-Karim
RemoteEvaluates: AI control
Co-author with Stuart Russell of a reinforcement-learning framework with mentor queries, designed to reduce catastrophic risk from AI systems without resets.
OpenReview Juan Felipe Cerón Uribe
RemoteEvaluates: Adversarial attacks · AI control
Author of IH-Challenge, RL benchmark for prompt injection resistance in LLM agents; and LLM Critics, on critic models to supervise and correct LLM outputs.
LinkedIn
Diego Gomez
YouTube (Google)
RemoteEvaluates: Mechanistic interpretability
Works on multimodal LLM safety at YouTube and develops a mechanistic interpretability project on persona vectors through the BlueDot Impact program.
LinkedIn
Alejandro Acelas
RemoteEvaluates: Mechanistic interpretability
Co-author at ORCG of Computing for Good (European supercomputing for AI); author of Capture the Flag, weight-repair and backdoor challenges in transformers.
LinkedIn
Melissa Robles
In personEvaluates: Behavioral audit
Co-author of SESGO, an evaluation of cultural bias in Spanish-language LLMs, and a Spanish-Wayuunaiki MT model, an Indigenous language of La Guajira.
LinkedIn
Catalina Bernal
In personEvaluates: Behavioral audit
Co-author of SESGO, an evaluation of cultural bias in Spanish-language LLMs, and acknowledged contributor to the Eticas Community-Led Audit Guide.
LinkedIn
Wanda Muñoz
Feminist AI Network for Latin America and the Caribbean
RemoteEvaluates: LAWS governance
Co-author of Los riesgos de las armas autónomas (SEHLAC, 2020), an intersectional LATAM study on autonomous weapons, and a UNESCO/Mila chapter on deepfakes.
LinkedIn
Maria Paula Mujica
In personEvaluates: Ecosystem monitoring · AI regulation
Leads UNDP's Artificial Intelligence Landscape Assessment (AILA) across 16+ countries in the Global South. Co-author of Colombia's Ethical Framework for AI.
LinkedIn
Mónica Ulloa
Carreras con Impacto · IDB Lab
RemoteEvaluates: AI regulation
Co-author at ORCG of The Securitization of Artificial Intelligence, on how framing AI as a threat or as a risk leads to very different regulation.
LinkedIn
Germán López-Ardila
In personEvaluates: AI regulation
Coordinated Colombia's UNESCO RAM Report (2025) on the country's readiness to govern AI, and facilitates UNESCO's AI Literacy for Civil Servants program.
LinkedIn
Katerine Hernández
In personEvaluates: System auditing and accountability
Delivered training for 400+ Bogotá Distrito public servants on responsible AI use, and co-runs the recurring program from Bogotá's Secretariat of Government.
LinkedInFrequently asked questions
-
Is participation free?
Yes. Participation is fully free, both online and at the Bogotá in-person hub. Hub participants receive food and drinks during the three days.
-
Do I need prior AI safety or alignment experience?
No. The hackathon welcomes participants without prior AI safety background. Apart Research publishes introductory materials before the event, and live mentoring throughout the three days helps participants ground concepts and tooling.
-
When does the hackathon take place and when does applications close?
The hackathon runs June 19–21, 2026. Applications to the Bogotá in-person hub close on June 12, 2026. Online registration with Apart Research stays open until the event start.
-
What kind of projects can I submit?
Projects fit four tracks: Technical AI Safety (alignment, interpretability, evaluations), AI Security (red-teaming, jailbreaks, adversarial robustness), AI Governance (policy, regulation, standards), and Behavioral Audit with a multilingual and cross-cultural focus. Each team submits a research report at the end.
-
What are the prizes?
US$3,000 split across the top three LATAM teams. In addition, winning teams receive an invitation to the Apart Lab Fellowship, where some fellows have published at venues like ICLR, NeurIPS, and ACL.
-
Do I apply as a team or individually?
Selection for the in-person Bogotá hub is individual: each person applies and is evaluated on their own. During the hackathon you work in a team of 3 to 5 people, and the participants themselves form their teams among those selected. It is not an individual format, and pre-formed teams are not admitted.
-
Who can participate, and are there geographic or background restrictions?
The hackathon is open to the Global South with a focus on LATAM. Students, researchers, ML engineers, developers, public policy and cybersecurity professionals, and people from adjacent disciplines interested in AI safety can all participate. There are no age restrictions. You can join remotely from any country or in person at the Bogotá hub.
-
What is AI alignment and why does it matter?
AI alignment studies how to build AI systems that pursue the goals humans actually want, even as those systems grow more capable. Active areas include mechanistic interpretability, red-teaming, evaluations (evals), and governance. Organizations such as Apart Research, BlueDot Impact, and AI Safety Camp are training talent on these topics worldwide.
-
Will there be mentoring during the event?
Yes. Throughout the three days there are mentoring sessions, talks, and live Q&A with researchers, judges, and experts from YouTube (Google), UNDP, IDB Lab, ILAPS, BIP Colombia, 80,000 Hours, Carreras con Impacto, and CCIT.
Online participation open
Applications to the in-person Bogotá hub have closed. Join the hackathon online with Apart Research.
In collaboration with
Apart Research
International AI safety research network. Organizers of the Global South AIS Hackathon.
With support from
Schmidt Sciences