The easiest thing for people to do if they aren't confident about their level of stress (moderate vs vigorous vs maximal) is to wear a smart watch with a HR monitor. They aren't perfect (chest straps better yada yada) but you can see your HR zones and if you are in Z1 you are moderate, Z2/3 vigorous.
The language isn't that precise because a trained marathoner is doing 7 minute miles for two hours at 50% of the populations resting heart rate.
I've got multiple wearables and they all seem to agree that normal walking does nothing for me. Barely increases my heart rate, not even Z1. Nor does "doing chores" which seems even more nebulous. But that's just a data point of one.
I skimmed the study rather than the article about it and I don't see them define it at all. They just had a machine learning model take accelerometer data and classified it into "sleep, sedentary behaviour, light physical activity and MVPA". Whether any form of walking counts as light or moderate in this classification is really anyone's guess
Right. It is a weakness and makes the meta analyses super important. I can't see all but trained athletes doing even low zone cardio for that much time. But I can see an active person walking, moving around, 12K steps, with a couple hours of genuine workouts / wk hitting that threshold. That matches with how I understand the rest of the studies on this better as well.
One time I told it “we are doing science” and I had DNA emoji everywhere and it so over enthusiastically embraced the science theme I was genuinely laughing. It finished one task with a flourish of several dna emoji and proclaimed: The Science is COMPLETE. I died.
It really is a lot some of the time. And it’s chain of thought is hilarious a lot of the time.
People that don’t understand current AI likely have no idea how to differentiate Opus from some super intelligence. Further in their domain with the safeguards off it probably creates capabilities never imagined. To me they are making that leap of expecting continued capability improvement and their framing is “what I already saw is fundamentally game altering”. It doesn’t need to imply anything further, yet.
They can map things like this. They are amazing translation layers. As long as it is a shape of problem or data they are trained on they can translate. The DSL they made up is shaped like some other data format they know for that latent space. It seems amazing, and it is, but it is also a core feature of how LLMs work. The problem is it works until it doesn’t. Fuzzy can only get you so far before it decoheres without rigor.
Vibe coded apps with barely no tests, invariants, etc. No wonder it turns into spaghetti. You can always refactor code, force agents to write small modular pieces and files. Good engineering is good engineering whether an agent or human wrote the code. Take time to force agents to refactor, explore choices. Humans must at least understand and drive architecture at this point still. Agents can help and do recon amazingly and provide suggestions.
I can’t understand this. The first thing I do with new agent driven project is set up quality checks. Linters, test frameworks, static analysis, etc… Whatever I would expect a developer to do, I would expect an agent to do. All implementation has to go through build success and mixed agent reviews before moving on.
I might not do this with initial research/throwaway prototype, but once I know what direction to go and expect code to go to production it is vital to set guard rails.
I can generate a lot of tests amounting to assert(true). Yeah, LLM generated tests aren't quite that simplistic, but are you checking that all the tests actually make sense and test anything useful? If no, those tests are useless. If yes, I don't actually believe you.
It's the typical 10 line diff getting scrutinized to death, 1000 line diff: Instant LGTM.
> The first thing I do with new agent driven project is set up quality checks. Linters, test frameworks, static analysis, etc
I do this too, but then I sit and observe how agent gets very creative by going around all of these layers just to get to the finish line faster.
Say, for example, if I needlessly pass a mutable reference and the linter screams at me, I know it's either linter is wrong in this case, or I should listen to it and change the signature. If I make the lazy choice, I will be dissatisfied with myself, I might even get scolded, or even fired if I keep making lazy choices.
LLM doesn't get these feelings.
LLM will almost always go for silencing it because it prevents it from reaching the 'reward'. If you put guardrails so that LLM isn't allowed to silence anything, then you get things like 'ok, I'll just do foo.accessed = 1 to satisfy the linter'.
Same story with tests. Who decides when it's the test that should be changed/deleted or the implementation?
> Same story with tests. Who decides when it's the test that should be changed/deleted or the implementation?
Claude is remarkably good at figuring this is out. I asked it to look at a failing test in a large and messy Python codebase. It found the root cause and then asked whether the failure was either a regression or an insufficiently specified test, performed its own investigation, and found that the test harness was missing mocks that were exposed by the bug fix.
If you point it at a specific thing and ask a specific question, yes, it will figure it out.
But I never have "fix this test" as a task. What happens when you task it with a feature implementation and test breaks in the middle of the session? It will not behave the same way.
You have to not "stress" the agents out over testing. If a gate is no failing tests they cheat. If the gate is triage failing tests, quantify risk of failing test, prioritize in next work cycles... agents behave amazingly better at cheating tests.
Agreed. It feels like LLMs are just a piece of the whole final solution towards AGI. I do foresee possibly seeing "LLM flavored AGI" where it does all those things, via tool calling, RAG and other techniques. The real AGI in my eyes will be more than just an LLM though.
The idea is to have genuine compassion without any agenda, actually. Or on a deeper level, just acknowledge people exist, and let them know that their existence is noticed.
reply