Judging by comments opencode seems popular. Why is it not in the top ranking coding agents on openrouter? HN's darling Pi is there, along with few others which I never heard about, but not opencode.
Maybe because of their rich provider ecosystem allowing you to use a whole bunch of subscriptions in it. I use OpenCode Go and OpenAI for almost everything, almost never touching OpenRouter.
Most head of states of countries that are not military dictatorship are civilian, i.e. they are not military, but if they rule over the military (such as the American president who is commander in chief of the military) does that count as being treated as a civilian for the purposes of wartime policy?
A similar role was played by Khamenei who was commander in chief of the Iranian armed forces.
Netanyahu is also a civilian and nevertheless the ICC issued an arrest warrant for his responsibilities for the behaviour of the IDF in the war in Gaza.
The formal definition used by the ICC is "civilian superior".
If you have the power to start a war, and you did start and aggressive war against other state, I'd say it's quite a stretch to be called a civilian. You're the one that deserves being taken down the most, as aggression is the highest crime, from which all other crimes follow.
"To initiate a war of aggression, therefore, is not only an international crime; it is the supreme international crime differing only from other war crimes in that it contains within itself the accumulated evil of the whole."
Recently a lean formalized proof of the Collatz conjecture had exploited bugs in the lean kernel. However, the kernel is fairly small so hopefully it'll be bullet proof soonish.
It should be noted that it wasn't a legitimate attempt at the collatz conjecture. Someone found a lean bug and created the proof to show it off. It wasn't an llm reward hacking (but this still is a concerning risk). Lean probably isn't the best kernel for adversarial proofs, but it probably has too much momentum at this point for anything else to take over.
Do I understand correctly, that they spent memory storing largish N hash values per server, so that request hash determines which server to send request to using closest higher value of all server hashes?
That in effect boils down to consistently selecting server S with probability P, where P is function of weight and total number of servers?
Surely there must be better way to select server with a given probability without storing a massive lookup table of hashes? Randevouz hashing of some sorts
Plus it's limited to 65k entries. Perhaps a btree where parent nodes sum the weights of child nodes would work well. Using the input hash scaled by total weight, a binary search lookup would compute the partial sums for comparison on the fly. Adding/removing a node would only update the ~8 parents when the btree order is 4. Eytzinger layout and struct-of-arrays could be used to improve cache locality during lookup. This does mean an add/remove could drastically change the overall mapping, perhaps that's why consistent hashing is used instead.
Do I understand correctly that in your harness models don't call tools and pass output of one to another via context, but instead code whole pipeline as small on-demand tools and see only final output?
> a sequential scan may push ~100GB of other data from memory (shared buffers or page cache).
Small note, if I remember correctly PostgreSQL allocates small buffer within shared_buffers for bulk reads. It is so that single sequential scan won't flush all of shared buffers content.
Similar mechanism exists for a pagecache implementation on Linux. It is divided into generations based on access patterns.
Is Huel ultra processed food too? They promote themselves as healthy meals and I am long time subscriber. I keep telling myself that even if it is not like cooking from raw ingredients, it is still far from a greasy junk food at kebab shops and McDonalds.
Hyper-ultra-processed, yes. But, as others point out in these comments, a food's degree of processing doesn't determine its health value, although those two things are correlated.
Personally, my instincts would favor Huel over fast food, too. I'd be very interested in any study that tested this rigorously. Huel is far from anything "raw," but so long as all the nutritional components are still in there, one has to wonder if it's just as healthy.
This is kind of the point. We simply don't have a sufficiently good understanding of food and nutrition to be able to say "smoosh these nutrients ands other food derivatives together and you get a healthy food".
UPFs is exactly the smooshing, and is generally done to maintain palatability whilst saving money, not even in an attempt to make a healthy food. Sure, Huel has a different goal, but I'm not sure the end result is any different. Just because it's not hyper palatable, it doesn't mean it's healthy.
Doesn't everyone do this now? It's hardly a new idea. Yet every time someone proposes the idea, people fawn over it and proclaim it the best thing ever.
Yes, you can inject tokens via a proxy. What else is new?
Who is doing it as first class feature with at least adequate UX?
I have skimmed alternatives offered in comments to this post (vibepod-cli, code-on-incus, opencode-docker, sandboxy, smolvm, amazing-sandbox) and none of them seem to do credentials injection at the proxy level.
reply