• 1 Post
  • 599 Comments
Joined 3 years ago
cake
Cake day: July 18th, 2023

help-circle



  • Yeah, that’s fair. I haven’t jumped into the whole agentic side of things as I find LLMs consistently fail at lower level stuff.

    Everyone says it’s great at prototyping or writing documents, etc, but I think that’s just cause people have low standards. When coding I find that it quickly messes things up or lacks good quality control (which you only notice if you’re familiar with the domain). For writing it’s fine, but the tone and language always feels off and certainly doesn’t sound like me.

    Either way, I would suggest playing around with them to see how they fit into how you do things. I think we’re starting to see things finally slow down on new implementations, and they aren’t going away, so it may be a good time to see if all the fuss is worth it to you.




  • The underlying issues, in my opinion, regarding LLMs is their indeterministic nature. Even zeroing out the temperature (randomness of outputs), you can get significantly different results between two almost identical texts.

    However, building out an ecosystem supporting new technology is a fairly common progression. If you compare it to the internet things like browser caches, CDNs (content delivery networks), code minifiers, etc. are all ways to help combat latency (a fundamental problem for the internet).

    As for the effectiveness of these solutions, RAGs do help a lot when generating text against a select corpus. Its what allows the linked sources in things like ChatGPT and Googles AI results. It’s also what a lot of companies are using for searching their support pages/etc. It’s maybe not quite as good as speaking to a person, but is faster.

    Similarly, the reasoning models and managing the models “context” both have shown demonstrable improvements for models in benchmarking.

    I’m not sure I personally believe this makes LLMs a replacement for humans in most situations, but it at least demonstrates forward progress for GenAI.


  • I think you may be mixing a couple of things together, but I’ll take a crack at this.

    When you get an Ai generated response from a search engine, this is usually a modified RAG (retrieval augmented generation) approach. How this works is that the content from web pages are already pre-processed into embeddings (numerical representations of the text). When you perform a search, your search text is turned into an embedding and compared (numerical similarity) to the websites to get the most related content for your search. That means that the LLM only parses and processes a very small subset of the returned websites to generate its response.

    Another element you might be asking about is how can these agentic AI systems handle larger tasks (things like OpenClaw). That is a bit more complicated and dependent on the systems design, but basically boils down to two things. The first is the “reasoning models” first break concepts into smaller tasks meaning the LLM only has to worry about a subset of a larger task. Secondly, a lot of these systems will periodically merge all past context into a compressed state that the LLM can handle (basically summaries of summaries) or add them to a database for future/faster reference.

    At the end of the day, your understanding of the limits of LLM are correct, all the progress we’ve really seen with LLMs (over the past couple of years) has been the creation of systems to work around their limitations. The base technology isn’t getting much better, but the support around it is.






  • I feel like on part no one ever mentions on things like this are, how do you enforce any jurisdiction on a satellite and what it’s doing.

    The main crazy thing about a satellite data enter is you can’t confiscate it and therefore you can’t control it. Hell once it’s up there the only thing any government might be able to do is find the owner and force them to crash it (if possible).

    It in a sense sounds a bit like the wild west of the original internet. Admittedly Musk being at the forefront of it all sounds terrible, but I think there is something fascinating about an information hub that could be completely independent of any country.