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

help-circle





  • I agree with you, it’s a decent open world game but a pretty mediocre Zelda game. I had hoped TOTK might improve upon the direction they chose to take the series, but it kinda doubles down on all the weaker points of BOTW (uninspired “dungeons”, more one-time use resources, etc.).

    I think my biggest gripe with TOTK and Echoes of Wisdom is that you can solve 90% of the “puzzles” with one or two techniques. There isn’t a lot of critical thinking needed when you can use things like the rocket to just skip most of the puzzle and similarly I think I solved a majority of the puzzles in Echoes of Time using the bed echo.


  • That’s a fair call out. My comment about systemic issues was to address the fact that it’s somewhat unfair to compare apples and oranges. So when I said the economy was doing well under Biden, I meant in regards to the current systems in place in the US.

    That being said, the economy is generally measured in how productive the country is. If the economy is doing good, then generally we have lots of people producing lots of things. That doesn’t mean we’re producing the right things though, as that comes down more to policy and public sentiment/behavior.










  • 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.