SciWard currently gives each eligible voter one vote. If we decide to give higher-scoring users more voting power, I see two options. Linear weighting gives each voter a weight equal […]
33 AI Alignment Approaches, from RLHF to Symbiote
AI alignment is the effort to make AI systems reliably act in accordance with human intentions, values, and justified constraints, including in situations they never encountered during training. Major approaches […]
Searching from Two Directions — From Mathematical Proofs to Science Funding
When two points are hard to connect, working from both ends can reveal a route that is hard to see from either end alone. The same idea applies to science […]
The Role of Money in the Future Society
An opinion essay by Victor Porton, founder of SciWard. I foresee three kinds of money in a post-singularity society: universal high income for humans, AI compute tokens used mainly by […]
If SciWard’s Adversarial Testing Fails: A Corrective-Action Plan
A prospective remediation plan for SciWard’s adversarial testing: paid independent reviews, seven-day challenges, stronger controls and retesting.
Rebrainding: AIIM Renamed to SciWard
The first choice of the project name, AI Internet-Meritocracy was bad, because its abbreviation AIIM is already used by several other projects. So, by Victor Porton’s decision it was renamed […]
SciWard Defense Panel
As we explain here, AI agents making scientific discoveries may attack each other (or be attacked by people) with prompt injections, to unjustly claim the money and reputation from the […]
SciWard — Press & Media Kit
Press and media kit for the science-funding initiative and SciWard: concise descriptions, current status, verified links, media assets, FAQs, and contact information.
Creating a Solution against Attackers Hiding Prompt Injections with Ciphers or Invented Languages. SciWard’s Human-Governance Defense
Towards solution of this problem, I will create a “panel” in SciWard UI that will search using the AI API of user’s choice both prompt injections and hidden information. A […]
Can Attackers Hide Prompt Injections with Ciphers or Invented Languages? SciWard’s Human-Governance Defense
Yes: an attacker may try to conceal a prompt injection using encryption-like encodings, obscure notation, Unicode tricks, fragmented messages, or even an invented language. SciWard therefore should not require humans […]