Pinging @stevenbyrnes : do you agree with me that instead of mapping those protoAGIs to a queue of instructions it would be best to have the AGI be made from a bunch of brain strcture with according prompts? For example "amygdala" would be in charge of returning an int between 0 and 100 indicating feat level. A "hypoccampus" would be in charge of storing and retrieving memories etc. I guess the thalamus would be consciousness and the cortex would process some abstract queries.
We could also use active inference and bayesian updating to model current theories of consciousness. Even use it to model schizophrenia by changing the number of past messages some strctures can access (i.e. modeling long range connection issues) etc.
To me that sounds way easier to inspect and align than pure black boxes as you can throttle the speed and manually change values like make sure the AGI does not feel threatened etc.
Is anyone aware of similar work? I've created a diagram of the brain structures and its roles in a few minutes with chatgpt and it seems super easy.
This reminds me of an idea : I think it would be great to hold a bi-monthly competition where people try to do something as incredible as possible in just 30 minutes using LLMs or other AIs. The winner being decided by a select few.
To reduce my sleep inertia I've created an app for my 25$ micropython smart watch (Pinetime from Pine64). Here's the link: https://github.com/thiswillbeyourgithub/sleep_tracker_pinetime_wasp-os
Aside from the motion tracking, it's able to vibrate very faintly at T minus 10 minutes, 7, 5, 2, 2, 1, 0.5 minute from waking up. Then vibrates gradually to wake me up gently.
It also automatically tells you when you should set your wake up time to optimize sleep cycle.
I think it works very well but I'm very biased.
Hi,
I had a question the other day and figured I'll post it here. Do we have any idea what would happen if we used the steering vector of the input itself?
For example : Take sentenceA, pass it through the LLM, store its embedding, take once again sentenceA, pass it through the LLM while adding the embedding.
As is, this would simply double the length of the hidden vector, but I'm wondering what would happen if we took played instead with the embedding say after the 5th token of sentenceA and add it at the 3rd token.
Similarly, would anything interesting happen with substraction? with adding a random orthogonal vector?
Thanks
Personnaly I come (and organize) meetups to make my brain sweat and actively avoid activities that leave me unchanged (I won't change much during a play while I grow a lot after each confrontation or discussion). But to each their own of course!
FWIW I tend to see a good part of ADHD medication's effect as changing the trade off between exploration and exploitation. ADHD being an excess of eploration, the meds nudging towards excess of exploitation. If you struggle with a perceived excess of exploration, you might ask yourself if you are helped by taking those medication or if you might fit the diagnostic criteria.
Related : Taking too much of those psychostimulants gives usually an extreme type of exploitation often called "tunnel vision", which can be detrimental as it feels like being a robot doing something on repeat.
Also : branched thinking is not only related to ADHD but also to people with unusually large IQ. So let me just stress that YMMV
Also2 : another interesting thread about ADHD the other day : https://www.lesswrong.com/posts/zi6Qq5jeWat8xFodq/what-works-for-adhd-and-or-related-things
edit: I can make the prompt more or less compressed easily, just ask. The present example is "pretty compressed" but I can make a more verbose one
Not really what you're asking but :
I'm coincidentally working on the side on a DIY summarizer to manage my inputs. I summarized a bit of the beginning of part 1. If you think it has any value I can run the whole thing :
note that '- ---' indicate the switch to a new chunk of text by the llm
This is formatted as a logseq / obsidian markdown format.
- Carl Shulman (Pt 1) - Intelligence Explosion, Primate Evolution, Robot Doublings, & Alignment - https://youtube.com/watch?v=_kRg-ZP1vQc
summarization_date:: 28/06/2023
token_cost:: 12057
dollar_cost:: 0.01911
summary_reading_length:: 4.505
doc_reading_length:: 120.5025
author:: Dwarkesh Patel
- Carl Shulman: highly regarded intellectual known for ideas on intelligence explosion and its impacts
- Advisor to Open Philanthropy project
- Research associate at Future of Humanity Institute at Oxford
- Feedback loops and dynamics when approaching human-level intelligence involve:
- Development of new computer chips, software, and training runs
- Concept of input-output curves important in understanding increasing difficulty of improving AI
- Productivity of computing has increased significantly over the years, but investment and labor required for advancements have also increased
- In a world where AI is doing the work, doubling computing performance translates to a doubling or better of effective labor supply
- Doubling labor force can result in several doublings of compute, accelerating AI development
- Bloom paper mentioned:
- 35% increase in transistor density
- 7% increase per year in number of researchers required to sustain that pace
- ---
- The bloom paper mentioned:
- 35% increase in transistor density
- 7% increase per year in the number of researchers required to sustain that pace
- There is a question of whether AI can be seen as a population of researchers that grows with compute itself.
- Compute is a good proxy for the number of AI researchers because:
- If you have an AI worker that can substitute for a human, having twice as many computers allows for running two separate instances and getting more gains.
- Improvements in hardware and software technology contribute to the progress of AI.
- The work involved in designing new hardware and software is done by people, but computer time is not the primary cost.
- The number of people working on AI research is in the low tens of thousands, with companies like Nvidia, TSMC, and DeepMind having significant numbers of employees.
- The capabilities of AI are doubling on a shorter time scale than the number of people required to develop them.
- ---
- The capabilities of AI are doubling faster than the number of people needed to develop them.
- Hardware efficiency has historically doubled 4-5 times per doubling of human inputs, but this rate has slowed down as Moore's Law nears its end.
- On the software side, the doubling time for workers driving software advances is several years, while the doubling time for effective compute from algorithmic progress is faster.
- Epoch, a group that collects datasets relevant to forecasting AI progress, found the following doubling times:
- Hardware efficiency doubles in about 2 years.
- Budget growth doubles in about 6 months.
- Algorithmic progress doubles in less than 1 year.
- The growth of effective compute for training big AIs is drastic, with estimates that GPT-4 cost around 50 million dollars to train.
- Effective compute can increase through greater investment, better models, or cheaper training chips.
- Software progress is measured by the reduction in compute needed to achieve the same benchmark as before.
- The feedback loop between AI and compute can help with hardware design and chip improvements.
- Automating chip design work could lead to faster improvements, but it is less important for the intelligence explosion.
- ---
- Improving chip design through AI automation is less important for the intelligence explosion because it only applies to future chips.
- Faster improvements can be achieved through AI automation.
- The most disruptive and important aspect of AI automation is on the software side.
- Improvements can be immediately applied to existing GPUs.
- The question is when AI will contribute significantly to AI progress and software development.
- This contribution could be equivalent to having additional researchers.
- The magnitude of AI's contribution is crucial.
- It should boost effective productivity by 50-100% or more.
- AI can automate certain tasks in the AI research process.
- This allows for more frequent and cost-effective completion of these tasks.
- The goal is to have AI that can significantly enhance performance.
- This is even with its weaknesses, rather than achieving human-level AI with no weaknesses.
- Existing fabs can produce tens of millions of advanced GPUs per year.
- If they run AI software as efficient as humans, with extended work hours and education, it can greatly surpass human capabilities.
- ---
- The education level of AI models surpasses that of humans and focuses on specific tasks.
- Tens of millions of GPUs, each equivalent to the work of the best humans, contribute to significant discoveries and technological advancements.
- Human-level AI is currently experiencing an intelligence explosion, starting from a weaker state.
- The feedback loop for AI researchers begins when they surpass small productivity increases and reach a level equivalent to or close to human researchers.
- AI systems can compensate for their weaknesses by deploying multiple less intelligent AIs to match the capabilities of a human worker.
- AI can be applied to tasks such as voting algorithms, deep search, and designing synthetic training data, which would be impractical for humans.
- As AI becomes more advanced, it can generate its own data and identify valuable skills to practice.
- For instance, AlphaZero generated its own data through self-play and followed a curriculum to always compete against an opponent of equal skill.
That would most certainly cause a bad trip at night. As taking uppers to stay awake for long will also increase anxiety, which will not be helped by the residual hallucinations from the earlier hallucinogenic.