2,282 karma · joined July 29, 2014
About infinite on boring tasks I might not do and keep putting off.
I started learning infra via AWS CDK (TypeScript). And by osmosis learned a lot about cloud native application architecture. Which changed my way of creating web apps entirely and rejuvenated my love for software. Still going strong 5 years later. Now with much stronger focus on platform engineering and not working on features much.
But one flaw (IMO) that it can’t export artifacts and import into other steps without breaking the cache.
Eg if you provide monorepo as input, and then on some step narrow your build to one specific dir, then even when files change outside of that dir then caching still is invalidated.
Which makes it extremely verbose and maintenance nightmare to keep multiple narrow inputs and keep all those paths up to date.
Once AI can write proper compelling converting copy then I’ll change my mind.
Is it about pulverizing software artifacts into token statistics?
What remains is not "code", but code-shaped matter?
Really? I derive a ton of value from it. For me it’s a phenomenal advancement and not a failure at all.
I want just services.
Indeed, during pandemic data field sort of matured. Modern data stack emerged. No one knew what they were doing and it was extremely over hired for.
In addition, I highly doubt LLMs have a significant effect on data teams as their main jobs aren’t writing code.
LLMs are still very unreliable at converting language to SQL. I believe the best benchmark was merely at around 70%. Who in their right mind can trust this level of accuracy?
My suspicion to this day is that these schools were both a spy front and long-game propaganda, where they were teaching how to make news more western-aligned.
Why would BBC want to teach their methods in Russia? How do they benefit from that? How does Soros benefit from that?
MCP is just an API with docs.
The problem isn’t MCP itself. It’s that each MCP “server” has to expose every tool and docs which consumes context.
I think the tools should use progressive reveal and only give a short summary like the skill does. Then agent can get full API of the tool on request.
Right now loading GitHub MCP takes something like 50k tokens.
I also have 2008 mazda3. Great reliable car. Also no connectivity whatsoever.