Partnership with SDSU on Project HALO

Partnership letter from SDSU for Project HALO (Hyperband Adaptive Link, Omnidirectional)

One challenge in space applications is the sharing of information while in flight. That only works if each link carries an antenna capable of holding the connection channel to its peers. No such antenna exists today that meets all the requirements at once.

Conformal array antenna concept.

The requirements are demanding. It has to transmit in nearly every direction, because rockets or satellites spin and the geometry between vehicles changes constantly. It has to work across a wide range of radio frequencies, from S band up through Ka band. And it has to keep working through the sheath of ionized air, which normally blocks radio signals entirely.

Dreamscape's approach is to print flat antenna rings directly onto the curved skin of the missile and let software do the rest. Instead of building the beam direction, polarization, and frequency into the physical hardware, all of those become settings the radio can change in real time. If a jammer appears, the link moves to a different frequency or a different polarization. When the vehicle enters or travels in the atmosphere and the plasma sheath forms, the radio shifts to a higher frequency band that punches through it. This last point rests on measured flight data from NASA reentry experiments in the 1970s, not on speculation.

San Diego State University's Antenna and Microwave Laboratory, led by Dr. Satish Sharma, builds and measures a physical test piece in its anechoic chamber and compares the measurements against the computer models.

Partnership with Georgia Tech on Project SPEED DIAL

Letter of commitment from Georgia Tech.

Machines and AI can now design algorithms, and tools like Agda and Lean can be used for assistance with proofs (especially for maths related to Homotopy Type Theory). Over the past two years the evidence has accumulated steadily. Researchers have evolved Kalman filter variants that outperform the standard filter in conditions where its assumptions no longer hold. Others have discovered iterative methods for linear algebra rather than deriving them by hand. Meta solvers have been found that outrun conventional iteration on nonlinear partial differential equations. One system identified a way to multiply four by four complex matrices in forty eight scalar operations, improving on a benchmark that had stood since 1969.

Very little of this work has reached production use.

The common explanation is that the field is young and the tools need another development cycle. I believe that reading is mistaken. The tools function. What is absent is any reason for a practicing engineer to trust what comes out of them.

Consider the position of that engineer. You are responsible for a computational fluid dynamics workflow supporting a vehicle that must survive reentry. Someone presents you with a preconditioner that a search process produced overnight. Would you place it in the loop? Three conditions would have to be met first. You would need to read the method and understand its behavior. You would need to know where it fails, not merely that it performed well on the cases it was scored against. And you would need to see it measured against the method it replaces, using data the search process never encountered.

Each of those is a verification problem. None is a discovery problem.

That distinction determines what is worth building. If discovery is the difficult part, investment belongs in search. If verification is the difficult part, search becomes a component that can be replaced as the field advances, and the lasting assets lie elsewhere. They lie in the schema that converts an imprecise engineering complaint into a well posed search, the harness that evaluates a candidate honestly, the provenance record establishing where a piece of code originated, and the index that surfaces the right prior solution when a new problem arrives. Those outlast any particular search method. A platform committed to a single paradigm will be obsolete before it ships.

There is a more demanding version of this standard. The measure that matters is not whether a discovered algorithm runs quickly. It is whether someone who did not build the system can obtain a real improvement from it. That is a considerably higher bar, and it is the correct one, because a tool that only its author can operate is a research artifact rather than a capability.

The failure modes are specific and deserve to be named. A discovered solver can prove numerically unstable in a region no one sampled, and a speedup figure will never expose it. A search guided by a language model can reproduce a solution memorized during training and score it as novel. Background search has no natural stopping point and will consume a compute budget without necessarily producing anything admissible. Each of these requires a policy established before the first run rather than a caveat appended at the end.

None of this argues against automated discovery. It is an argument about sequencing. The discovery half is close to settled and growing cheaper. The trust half has barely been addressed, and it is what stands between a strong body of research and anything that reaches an engineer's desk. This is what we intend to do with Project SPEED DIAL.

Partnership with UCF on Project WITNESS

Letter of commitment from UCF.

If you are beginning to feel that we are inching closer to the apocalypse every passing day, like the Fallout game franchise, you aren't alone. This is why I have launched Project WITNESS. The idea is to develop hardened vans equipped with sensors to detect nuclear radiation in the form of gamma rays.

Radiation detection can require specialized hardware and CMOS sensor arrays, and in the past cloud chambers, bubble chambers, and various forms of vacuum tubes or gas tubes were used. One novel approach here I've proposed is that instead, gamma radiation should be detectable with what we already have off-the shelf with the cameras we use every day.

It turns out that when you have gamma rays, this can be detected in current CMOS cameras - and would be much cheaper. These are already in production and so this would simplify supply chains.

Two Sigma Systems has also endorsed this project. More news to come.

Endorsement from Two Sigma Systems