It started after spending 15 years building AI for insurers, hospitals, data companies, and startups. Almost every system ended with "a human reviews the output". That person was usually a nurse, medical director, or certified coder. These are some of the hardest people to hire, and the same people automation was supposed to help.
The problem is that real claims do not have an answer key. You cannot reduce human review until you can measure when an agent is wrong.
Getting claims data is also difficult. It can take a year of data agreements, privacy reviews, and procurement. Even then, you may not know what the correct decision should have been. So we generate claims. Utilization and case mix come from published data. Claims are priced using real fee schedules and contract terms. Payers behave differently, like real payers do. We plant errors on purpose, so the correct answer exists before any model runs.
On top of that, we are building benchmarks for overreach, refusal, errors by record type, and detection time. We are also building small MCP tools that refuse when evidence is missing. Every number includes its source, date, and basis.
What I find interesting is how much of this sits between actuarial work and machine learning. Both are needed, but I do not see many people connecting them.
25 published refusals: https://hammer.ai/worlds/refusals/ .
Runs on rate and policy evidence https://hammer.ai/reimbursement-evidence/ and savings claims https://hammer.ai/savings-claims/ .
AgentPlugin is Apache-2.0: https://github.com/hmmrlabs/hammer-plugin
We are an early stage startup working on light weight containerization and virtualization open source technologies for constrained devices. We are looking for software developer with experience: Rust, C/C++, Embedded Systems, MbedOS, Arm, iOS and Android. Please contact holly ‘at’ hotg.ai
Please contact holly ‘at’ hotg.ai
We are an early stage startup working on light weight containerization and virtualization open source technologies for constrained devices. We are looking for software developer with experience: Rust, C/C++, Embedded Systems, MbedOS, Arm, iOS and Android.
Please contact holly ‘at’ hotg.ai
http://kirin.cs.washington.edu:8000/translate?request_str=fi...
Also looks like it isn’t forwarding http to https? Eitherway great work! This was a lot of fun to play with.
Hi all,I have been wanting to build some projects to understand 5g. I want to be able to network some devices and play around with the tech. I can’t seem to find any hardware kits for 5g. Most google shows is a Qualcomm site but I cannot buy it? Any hints?
I am the Sr. Data Scientist at Doc.ai and we are in the process of building a novel blockchain, ML and mobile experience for patients. Contact us at kartik 'at' doc.ai.
We are looking for someone to help drive our devops, discovery and maintenance.
Minimum Qualifications: - Experience deploying and maintaining a micro service architecture - Experience with kubernetes/docker/ecs - Experience with MySQL/PostgresSQL and Mongo - Familiarity with HiPPA - Familiarity with blockchain tech
Took a long break from hacking and staying indoors playing with yet another framework. I am much happier :) my depression is better and I have more balance :) Less likely to burn out.
This is a major concern because the exclusion zone (particularly the Red Forest) has 27 years of litter (leaves and other plant material) which is a fire hazard. A large fire could redistribute the radioactive material outside of the exclusion zone.
Hope that helps.