Some misc advice. Your first task with ai is to use it to build constraints and guard rails for the ai. That probably means a test suite that is at least twice the size of your code base. If you started there, great,…
> Code always was, it's supposed to be malleable. … You can always rewrite the code. This isn’t capturing the spirit or the essence of the metaphor. chipping away at marble or whittling has this locality to it that’s…
K8s is a reconciliation engine for desired state, like many other adjacent tech in the infra space. Hating on yaml json or tempting layers that drive the engine is kind of silly, and usually missing the point.. like…
> ultimately left my partner feeling unhappy and lonely.. do our best with 24 hour days Impossible to express just how deeply frustrating it is to have the “sleep when I want you to, not when you want to” kind of fight.…
Not op but I think maybe the connection was more grammar vs your “select set of templates”.. observation being that structure beats no structure regardless of the base tech, and that completely structure-free…
> the model will perform worse Depends on whether and how you want to rank stability in terms of better/worse. Models are diverging on this, which seems increasingly clear.. i.e. Fable isn't stable, but Opus isn't…
> I think too much credit in the AI math discussion is being given to LLMs rather than to Lean, For sure math and software people know this, as it's kind of hard to ignore. Developers who are totally disinterested in…
> It’s good know I’m not just crazy wanting to do part time EMT work and keep my software career. Not OP, but there are dozens of us. If you might be interested in things like ski-patrol or guiding.. there's loads of…
Average people cannot tell reliably isn’t an appropriate or interesting test tho, otherwise Eliza and markov models etc. the framing that matters is explicitly adversarial. Play like your life depends on it instead of…
Sigh, the whole "obviously the turing test is solved" meme is annoying. Like, if we meant that it convincingly masquerades as a shitposter, ok. But everyone still bitches about AI slop, and everyone knows the writing is…
It may be surprising to you but, caring about fairness and democratizing access to helpful resources doesn’t actually require any kind of disadvantage or a complex. What’s your deal though, since you want to attack that?
naive to think people would follow this policy in the spirit in which it’s intended, but even then it clearly selects for the most social animals amongst your students instead of the most talented. And discussion alone…
[dead]
Yes. Forget costs just so we can skip the whole rabbit hole about other predictions about the future.. mixture of generally intelligent + specialist experts just works better. People who don't see this already are…
> I've never heard of grounding in this context, so it may help to describe what you want more clearly Clear and recognizable technical vocabulary for engineers, or a legal context, to mathematical logic, philosophy,…
Situation: Software-1 on Platform-1, both certified. Time-evolution: P1 is deprecated, replaced by uncertified P2, but S1 remains certified.. just nowhere certified to run yet. Solution: There's another software S2…
No offense intended, and I don't even mean to suggest that projects or docs cannot or should not be "finished". Finished is great, maintenance is great. I would however suggest a docs update if it says "new" where it…
> I agree about boring comments but that goes well beyond political. Every time I see a comment about how this year's iPhone is "evolutionary not revolutionary" or some variation. It's boring, lazy and pointless. This…
Do we want to call it mature or abandoned? > TXR is relatively new: the project started in 2009.
> I don't know if his solution (""We should all go insane building interlocking evaluation and optimization pipelines, instead.") would be the long-term solution. TFA could explain this one part better I think. The…
Regardless of whether the target result(s) are ultimately correct, isn't it almost guaranteed that supporting infrastructure for surreals-in-lean is a real contribution? Is it a goal to make those polished/reusable, or…
Outcome reward vs process reward models. The second is obviously better.. like getting partial credit on a physics test for wrong answers but correct method. Research is gradually hybridizing them but historically we…
IMHO the best and most relevant part of fossil these days is the ticket system, which is in every single way almost completely ideal for coding agents. Some features are: single-binary, in-repo, CLI or web UI, and…
> We are witnessing a general threat to intellectual work, with misalignment between the outcome of the use of AI and its initial purpose. In many fields and activities, years of training have traditionally served not…
Some misc advice. Your first task with ai is to use it to build constraints and guard rails for the ai. That probably means a test suite that is at least twice the size of your code base. If you started there, great,…
> Code always was, it's supposed to be malleable. … You can always rewrite the code. This isn’t capturing the spirit or the essence of the metaphor. chipping away at marble or whittling has this locality to it that’s…
K8s is a reconciliation engine for desired state, like many other adjacent tech in the infra space. Hating on yaml json or tempting layers that drive the engine is kind of silly, and usually missing the point.. like…
> ultimately left my partner feeling unhappy and lonely.. do our best with 24 hour days Impossible to express just how deeply frustrating it is to have the “sleep when I want you to, not when you want to” kind of fight.…
Not op but I think maybe the connection was more grammar vs your “select set of templates”.. observation being that structure beats no structure regardless of the base tech, and that completely structure-free…
> the model will perform worse Depends on whether and how you want to rank stability in terms of better/worse. Models are diverging on this, which seems increasingly clear.. i.e. Fable isn't stable, but Opus isn't…
> I think too much credit in the AI math discussion is being given to LLMs rather than to Lean, For sure math and software people know this, as it's kind of hard to ignore. Developers who are totally disinterested in…
> It’s good know I’m not just crazy wanting to do part time EMT work and keep my software career. Not OP, but there are dozens of us. If you might be interested in things like ski-patrol or guiding.. there's loads of…
Average people cannot tell reliably isn’t an appropriate or interesting test tho, otherwise Eliza and markov models etc. the framing that matters is explicitly adversarial. Play like your life depends on it instead of…
Sigh, the whole "obviously the turing test is solved" meme is annoying. Like, if we meant that it convincingly masquerades as a shitposter, ok. But everyone still bitches about AI slop, and everyone knows the writing is…
It may be surprising to you but, caring about fairness and democratizing access to helpful resources doesn’t actually require any kind of disadvantage or a complex. What’s your deal though, since you want to attack that?
naive to think people would follow this policy in the spirit in which it’s intended, but even then it clearly selects for the most social animals amongst your students instead of the most talented. And discussion alone…
[dead]
Yes. Forget costs just so we can skip the whole rabbit hole about other predictions about the future.. mixture of generally intelligent + specialist experts just works better. People who don't see this already are…
> I've never heard of grounding in this context, so it may help to describe what you want more clearly Clear and recognizable technical vocabulary for engineers, or a legal context, to mathematical logic, philosophy,…
Situation: Software-1 on Platform-1, both certified. Time-evolution: P1 is deprecated, replaced by uncertified P2, but S1 remains certified.. just nowhere certified to run yet. Solution: There's another software S2…
No offense intended, and I don't even mean to suggest that projects or docs cannot or should not be "finished". Finished is great, maintenance is great. I would however suggest a docs update if it says "new" where it…
> I agree about boring comments but that goes well beyond political. Every time I see a comment about how this year's iPhone is "evolutionary not revolutionary" or some variation. It's boring, lazy and pointless. This…
Do we want to call it mature or abandoned? > TXR is relatively new: the project started in 2009.
> I don't know if his solution (""We should all go insane building interlocking evaluation and optimization pipelines, instead.") would be the long-term solution. TFA could explain this one part better I think. The…
Regardless of whether the target result(s) are ultimately correct, isn't it almost guaranteed that supporting infrastructure for surreals-in-lean is a real contribution? Is it a goal to make those polished/reusable, or…
Outcome reward vs process reward models. The second is obviously better.. like getting partial credit on a physics test for wrong answers but correct method. Research is gradually hybridizing them but historically we…
[dead]
IMHO the best and most relevant part of fossil these days is the ticket system, which is in every single way almost completely ideal for coding agents. Some features are: single-binary, in-repo, CLI or web UI, and…
> We are witnessing a general threat to intellectual work, with misalignment between the outcome of the use of AI and its initial purpose. In many fields and activities, years of training have traditionally served not…