This seems a lot like fishing. Cast a wide net with claude to find and solve an 'unsolved' problem. Given this, it is not enough to verify the problem and the solution but also the history of the problem and if it really existed or has simply been collectively hallucinated.
This is impressive as it is optimizing the effort on the low, but not too low hanging fruit.
"In late 2020s, while the whole world was focussed on AI, automation and resultant economy four major mathematical study branches were discovered by human researchers which took AI a long time to catch up with"
The libraries are there for avoiding repetition. It is useful on its own without other benefits like implicit/explicit boundaries, readability by humans etc. If all lego(base unit software) pieces were unique shaped it might fit your requirements more efficiently but the cost of building those unique shaped legos explodes with the size of the lego piece required.
LLMs compress the known shapes well and fit them to solve for a problem but they are still not good enough to build from scratch a large new lego piece which fits a full problem perfectly. And such a large lego piece might not be the most efficient solution either and might be difficult to prove so.
> the cost of building those unique shaped legos explodes with the size of the lego piece required.
The cost of plastic injection molding is almost entirely due to the cost of creating the steel mold. My argument is: with LLMs we are entering a world which makes it cost effective to build many more things from scratch, which is akin to going from building things out of pre-fabricated lego pieces to 3D printing (agreeably not cost effective for everything, but for many things).
It is based on Anthropic Uptimes. If anthropic wanted 99.999 they will have to acquire 10 times more GPUs/infra to match the traditional free resources of 99.999 services.
Agree. Just pay attention to the follow up questions a learner is asking to see the progress. If the follow up is just "continue", "go on", "next" or a non-sequitur then it is smell of a stall. If it is challenging or filling a gap in the answer then it is progress. So production from the learner is the only signal of worth here not the quality of LLM response, the time spent or the ability of the learner to reproduce the facts given by the LLM.
With human devs, errors become recovery instructions.
400 Bad Request is fine for a client developer who reads it once at design time and fixes the code forever. it's dead weight for an agent that must self-correct from the string alone. "Expected ISO-8601, got 03/04/2025" is now a functional part of the interface.
Not all agents are developers who can code their own interface.
Google improved chrome by reading code: Google built an agent harness using Gemini to scan Chrome's codebase, trained on a knowledge base of prior CVEs and the entire Git history, with a "critic" agent consuming developer-supplied SECURITY.md files.
In my experience, I find it to be exceptionally good at exploring and fixing the edge cases. Of course the output is not human maintainable for these fixes and needs to be heavily tests controlled, refactored or just accepted as being agent-maintained going forward.
Can you please give some examples of the best tools/businesses which are being built like this? Genuinely curious. I know the vibe tech is really good but I don't know of any upstarts using it, everyone cool is building/distributing the vibe tech. There are some games/copycats but nothing production grade in my radar.
This is impressive as it is optimizing the effort on the low, but not too low hanging fruit.
reply