what are some of the vagaries of how that use case depends on the agent aka harness? i’ve only been focused on sort of how to make models reliable for my math / cs / engineering and arts and crafts work loads, but RP is an important category for some folks. like are the fails of the various models different from more technical yet creative work loads?

eg im working on rigorizing a proof that a fun algorithm of mine is not only the first provably efficient algorithm for a particular problem, but its also the fastest in practice. ive found that for the sort of stuff i need to assume the model will get confused in the out of training distribution stuff from my personal library of ideas, so they will at best be a confused secretary intern mashup

it’s pleasant

> it’s pleasant

for whom?

its definitely good at admitting when it doesnt understand stuff. which is a rare treat with these models.

omg, ive wanted a precision computer controlled flexure motion system for yearssssss. i may also just really love tiny tools and devices.

So that's existed for a long time in the form of OpenFlexure. The microscope is a pretty easy / fun build.

fuck anthropic. their so called anti distillation stuff has made more recent models impossible to use. when i can see reasoning i can cut off a bad inference and prevent comprehension issues. also reified reasoning really helps make using models outside of their training distribution much easier. and it alsk lets me prevent task substituting by again preventing that reasoning from being accepted. this bs makes it much hard for me to build cool shit. :(

Of course the little detail that you are paying for those reasoning tokens that you can't see never gets mentioned, so now they can rip you off and you'll never know the difference.

yeah, and if the resoonse is off the rails you cant catch it earlier and reduce the cost. i genuinely think this shoukd be illegal

Opus 5.5 is the best model I’ve ever used. It is certainly not “impossible” to use. The numbers back it up too. If you don’t like a product or the people selling it, don’t use it. The sense of entitlement in this post is remarkable. If you have principles, stand on them. You are not entitled to anything more here.

recent claude models smear away personal taste when its in a continuum of vocal opinions and not corrected frequently. this drift is a cross domain transfer of the stupid political neutrality when facts are “contended” publicly. it results in some nauseating opinions about current us government wrt culpability for dead children. you can replicate this yourself, just ask any >= 4.8 model about moral culpability of wh for usaid termination consequences.

also my setups for making models reliable requires reified jointly inspectable deduction traces. its also fristrating because aside from context limits ive gotten incredible work out of claude 4.5 in the past, despite its context limits being a serious bottleneck. but those reliability things interact terrible with all the safety filter bs.

to be clear this is a customer/consumer rights issue. and the real safety issue. if they are so concerned about unsafe distillation, make it easier to fucking do alignment respecting distillation. no amount of any distillation benefits any fucking paying user whatsoever. its literally a tragedy of firewalling a compilation of public commons because you raided all the book stores and libraries first

edit: im also on the market atm so if anyone wants some smart ocd focused on actual interactive agent reliability, while all my black box tooling isnt public, aside from my lack of public marketing im hard to beat

I'd love to read your writing on this.

which part? theres a few different axes and im way overdue to make some writing public

i am also working on some commercial ideas around reliability, but im not 100 percent certain that theres a market for a truely good third party harness

> actual interactive agent reliability

That's the bit that jumped out as really interesting. I've been fighting this for some time now and I'm super interested in what your take is on this.

how are you doing cheaper than alternatives pricing? i assume some sort of snapshotting and sleep, wake on network thing?

I answered this in detail in another comment above, but really the basics are skip the hyperscalers and place the pods more efficiently based on available resources.

this 1000x. a lot of details in context compaction, editing, reverting ux, etc are all really centered on keeping the load and cost of subscription users as small as possible. its no always that nor is it necessarily correct, but its a huge driver of how those subscriptions and first party apps are designed

the cpu usage will be so absurd the devices would be trashed or batteries run down like instantly.

IoT devices don't have batteries. CPU usage on hacked devices may not be reliable.

Probably time to rely on the touch test. Although, alarmingly, my ISP-provided cable modem is consistently hot to the touch, and darned if I can figure out how to get any insight into why.

It's a simple matter in Linux to limit the CPU usage of a process. Would slow things down, but not completely stop them

Can't wait until this botnet working at 0.005 tokens per second kills humanity in a billion years

the gc ai site indicates all official contact is going to have the official domains in the email. hn hiring threads are not for external recruiters to make use of. additionally its super not cool to do false representation. job stuff is stressful enough as is

i dont even use cpp and my immediate response was oh shit this is a big deal