We should discuss cache performance if we haven't already. That 33k tokens may be a cache hit (I am not certain it's automatically a cache hit) but after the first call, it should certainly be a cache hit. Cache hit tokens are billed at 1/10th the price of cache misses. This is quite opaque, but it's necessary when you're asking "is the system prompt worth its stay" if you can save 33k tokens worth of dynamic discovery across the next few turns, the break-even point is quick and if the system prompt makes task performance increase and/or makes the system more autonomous so that it can string together more cache hits in a row, it becomes way way better. On a personal note, I think of things as aa function of 'supervised time to desired result' and 'cost'. because I find it harder to reason about tokens. I do think they could introduce a "minimal" mode (something like this is probably doable with the Claude agent SDK today)
HN user
eigenblake
I write on https://empath.substack.com/
Other solutions get a lot right, but I don't know if I will ever use something other than LaTeX. Nothing gets math typesetting feeling so right. The justification and bin packing feels right. I might be esoteric for it. Maybe I care too much about things looking excellent. Maybe Claude is just good enough at debugging anything I'm facing. But I'm not interested in anything realtime/live if it means giving up on output quality. Overleaf has a live preview mode right there. I think a lot of the "problems with latex" are actually just problems with people developing packages in isolation in a decentralized manner. I don't care for LaTeX the language, or its implementation, but I do care for the output a whole lot, in a way that not the font alone or any approximation can reach. Maybe it's just inside baseball and people don't care about advanced typography. If I'm working on a piece of research that will carry my name on it, waiting for that compile is worth it. I still remember Scholarly Markdown. I might genuinely one day implement some other transpiler so I can always do my last pass in LaTeX. As long as your thing emits some decent IR, I'm happy.
Really reminds me that there's nothing in principle stopping us from storing parse trees and exposing them via something git like so we can avoid even needing to format, let alone also needing to resolve a whole category of merge conflicts based on that formatting. I mean a format is just a theme over your data -- I mean code.
I put Bad Apple in an MCP App two weeks ago https://youtu.be/YFF5H886slQ
Alternative Title: Claude Code puts words in my mouth (Self Prompt Injection)
I originally thought that this was just misunderstanding attribution in discussions. This does seem to be a harness bug. Or at least an ontology bug. In my work with LLM frameworks, it was always odd that tool call results are sometimes marked in the convo as coming from the "User", I think that could be fundamentally what's enabling this bug to happen. Neither the LLM nor the harness should be able to claim something came from the user.
This is command injection. I don't know enough to see if cryptography is part of the right answer but it might be. A hash of the user message, signed, public key private key, harness is coded to only allow signed messages issue instructions. Yes, that might be overkill, but thinking about the types of things agent harnesses are used for... I think the safety argument starts to speak for itself... This has never happened to me using CC though, for what it's worth.
Biggest limitation I see in this paper: the framing. Any time you have a lot of proprietary knowledge or you've just sorted out the right solution when it's not readily available from the model's parametric knowledge, that's when you should add a skill. Wrap it in a CLI that's easy to inspect. You don't need to store the whole help text of the skill either. The model can inspect it and its subcommands.
Reality doesn't force us to choose between skill or no skill, reality often doesn't give us a choice. You can either make a skill for your company's proprietary system or your model has to figure it out from scratch every time by searching wikis or reading code. If you use it right, skills are a compression mechanism. Instead of the process meaning your model needs to get all of theses files dynamically, it can simply statically run.
To steel-man the paper. It is worth looking at whether you should try to code something up first or try a skill first. And it may well be valid to say try first and if you can't work it out in 5 mins, install a skill. But there's a meta point of skills as software (where you deduplicate the effort of solving regressions).
For a reductio ad absurdum, If self-generated skills with no additional context _didn't_ eventually level off in performance, then we could reach AGI by making one big skill that keeps growing and solving harder and harder tasks, including improving the capability of its own skill-builder skill, all without embedding any signals from the environment or needing to interface with the real world at all.
I have been considering what it would be like to give each function name a specific color and a color for each variable's type followed by a color derived from the hash of the symbol name and keywords would each be their specific type. And essentially printing a matrix of this, essentially transforming your code into a printable matrix "low-lod" or "mipmap" form. This could be implemented like the VSCode minimap but I the right move here is to implement it as a hook that can modify the output of your agent. That way you can look at the structure of the code without reading the names in particular.
bd35a7f69b28c97fb3ebe489a4fba26a5f423522276d5ff5b5a8bb6441806ad2
How did they leak it, jailbreak? Was this confirmed? I am checking for the situation where the true instructions are not what is being reported here. The language model could have "hallucinated" its own system prompt instructions, leaving no guarantee that this is the real deal.
What's so special about this? Homo sapiens have been doing this for hundreds of thousands of years /s
This appears to be an observational result, so I'm genuinely perplexed by the reception here. I genuinely thought this comment shows a healthy amount of curiosity and asking important questions. Asking "what control group did this study use?" is usually well-received here.
Doctors aren't machines, they're humans. I have not yet read the full paper, only the article, but I already see something really big and important to look out for. When I read the full thing, the question I'll be asking is "what's the likelihood that the self-esteem of doctors was directly intervened on by the exam taking process itself." How do you control for the loss in confidence that learning of your test performance gives you? How are we certain that learning your score on the board exam doesn't make you more conservative (or riskier) with how you treat patients as a psychological effect?
We could probably fine-tune a tiny convolutional neutral net image classifier and just hold on the last good frames for longer to cover the frames with clear trolling and nsfw images.
I'm surprised no one has mentioned atomic Linux distros yet in this thread. The really hard thing here is that people aren't all talking about the same things. My experience on Arch isn't my experience on Pop. Things on Pop are amazing on my MSI rebuilt PC with Nvidia GPU. I don't even know if I really need to upgrade to NixOS except to satiate my curiosity.
Absolutely yes, but not me personally. The keywords to search for are Plover, Stenotype https://youtu.be/jRFKZGWrmrM
creative work that presents itself as journalism or nonfiction but introduces fictional elements with the intention of upsetting, disturbing, or confusing the audience.
A good time to mention the SCP wiki and some types of analog horror. It was this kind of thing that led me to discover "hard science fiction" which is distinct but related to the previous two.
What I don't see represented in this conversation is the idea that you can just write for personal satisfaction, or examine something you're personally interested in. Not everyone needs to have 10k+ monthly active readers. Not everything needs to be a rat race. Why don't we see blogging like exercise? Sure you'll have your body builders, but some people just go on walks, and no one is doing anything "wrong" they just have different goals.