MegaHAL, Jason Hutchens and AI Ltd (NV?)

So I just read a very interesting chapter by Jason Hutchens in "Parsing the Turing Test", in which he talked a little about his work at AI Ltd (NV?) on mixing a reinforcement learning paradigm with some stochastic word frequency modeling to train an AI. I remember reading about that 10 years ago or so and was really interested to get an update. There was a tantilizing transcript of a HAL/Trainer dialogue where HAL (the computer) was effectively simulating a 15 month old's speech. A quick web search turned up that dialogue in an academic paper:

Treister-Goren, A., Hutchens, J.L.: Creating AI: A unique interplay between the development of learning algorithms and their education. In: Proceeding of the First International Workshop on Epigenetic Robotics (2001)

Trainer: where is daddy?
HAL: daddy gone
Trainer: daddy is at work
HAL: daddy work bye bye
Trainer: yes daddy has gone to work
HAL: daddy work bye bye bye bye
Trainer: do you want to go to the park?
HAL: yes bye bye
Trainer: ok we can go to the park
HAL: take car bye bye
Trainer: we will take the car because the park is far.
let’s pack some things in a bag
HAL: ball now park
Trainer: yes we should put the ball in the bag
HAL: ball now park mommy
Trainer: wait hal, we need to take something to eat
HAL: bananastory? night now
Trainer: we need to take something to eat
HAL: bananas
Trainer: ok we can take some bananas
HAL: monkeys eat bananas
Trainer: you’re so smart hal. do you want to take a
book?
HAL: juice mommy
Trainer: sure we will take some juice as well

Jason's chapter didn't have any references and there were a few points he made that I would have liked further details on, specifically:

"... findings which indicate that appropriate guidance may strongly influence ... aspects of the child's language development ... these findings have spawned evaluation and treatment programs in areas that border on the question of intelligence with developmental language data enabling the treatment of some developmentally delayed populations. It has also proven itself a valuable tool in treating schizophrenic thought disorder where clinicians often find themselves unable to capture the communicative problem of patients to assess their intelligence."

Anyhow the chapter ended on saying there was an exciting future ahead, but a quick web search revealed that Jason left the company in 2001, and I had a little trouble finding more about the company, although finally I found this website:

http://www.a-i.com/

Where I had a reasonable conversation with a chatbot that seemed more advanced than the 15-month old one, but the conversation was not disimilar to an original HAL or Eliza program. The website has lots more to explore including an iPhone app, and apparently the ability to train your own bot and make it public; but I couldn't immediately find what I was looking for, which was something about how the program of training infant AIs was progressing. I'd love to see more recent peer-reviewed papers on this stuff. Maybe I'll find it with a bit more looking.