One question, do you have plans for any other forms of sandboxing that are a little more "lightweight"?
Also how do you add more agent types, do you support just ACP?
614 karma · joined October 31, 2016
Socials: - github.com/ydennisy - linkedin.com/in/dennisyurkevich - x.com/ydennisy_
Interests: AI/ML, Data Science, DevOps, Entrepreneurship, Programming, Startups, Web Development
---
One question, do you have plans for any other forms of sandboxing that are a little more "lightweight"?
Also how do you add more agent types, do you support just ACP?
My personal view here has shifts quite often, yes software is getting easier to build at an alarming rate, but designing good software is not (yet), and new novel software is not in the training set so should remain hard to build, forever (?)
To address the main comment, yes lots of apps are just wrappers, and I feel this is not sustainable, we will not need all these specialised apps since AI is such a general interface to computing.
It reminds me of GEPA & Textgrad.
Would love to hear if anyone has worked on anything of this sort in practice.
It is not obvious to me that one credible citation is better than having appeared many times in the training data.
Also knowledge releases of models are too slow to be depended on for marketing in my view. It is the search / retrieval of LLMs for which one can optimise.
A final point would be that none of this changes the point made, which is that there too much noise due to too many products being shipped.
I would love to know how big your sample is, in what way the tools fail, what features are missing etc.
Also could think of it a little like a “Wikipedia of flashcards”.
Would you be interested in working on something like this?
Surely these sorts of problems must be worked upon from a mathematical standpoint.
Will have a think about how this can extended to other types of uses.
I have personally been trying to replace all tools/MCPs with a single “write code” tool which is a bit harder to get to work reliably in large projects.
My guess is it’s a top level folder which shows the cross module deps.
On your homepage there is a mention that Tern “writes its own tools”, could you give an example on how this works?
I would love to hear what people’s takes on the market dynamics are, especially if any of the YC founders working in this space see this!
What sort of market dynamics do people predict here, winner takes all? Especially when this is integrated into the platforms of distribution.
Also having AI write notes is really missing the point of writing notes in my opinion.
I also agree with comments on this thread stating that problem solving should be the focus and not the code.
However my view is that our ability to solve problems which require a specific type of deep thought will diminish over time as we allow for AI to do more of this type of thinking.
Purely asking for a feature is not “problem solving”.
However I do personally really dislike that everyone is either marketing themselves or has truly pivoted to AI agents…
This seems like a great platform to run any type of tasks.
The author makes valid points but they are vacuous and do not provide concrete alternatives.
Many engineering articles disappoint me in this way, I get hyped by all the “don’t dos”, but the “do dos” never come.
However I am personally looking for a product exactly like this! I really want LLMs to make beautiful UI for me.