HackerTrans
TopNewTrendsCommentsPastAskShowJobs

crazylogger

203 karmajoined قبل 4 سنوات

Submissions

What we learned building sandbox for document agents

blog.yfzhou.fyi
1 points·by crazylogger·قبل شهرين·0 comments

comments

crazylogger
·قبل 20 ساعة·discuss
To be fair while almost no company publishes what a "credit" or what a 5h window in their subscription plan really is in terms of input/cached input/output tokens, Xiaomi does: https://mimo.mi.com/docs/en-US/tokenplan/Token%20Plan/subscr...
crazylogger
·قبل 13 يومًا·discuss
Students will just one-shot whatever lab problems professor comes up with using Claude Code.
crazylogger
·قبل 13 يومًا·discuss
Actually they don't even need to compete against frontier closed models, they just need to work.

99.99% people's day jobs aren't competing for the Fields Medal or even finding security vulnerabilities. So it appears while TAM (total addressable market) of AI in general is huge, TAM for frontier LLMs is tiny. Efficiency gains at roughly the same performance might be all people care about from now on.
crazylogger
·قبل 16 يومًا·discuss
In a typical agent loop your N-th LLM request naturally becomes prefix for the (N+1)-th request. As the thread grows longer, cache hit rate converges to 100% and unit pricing for cached tokens is 10-100x cheaper.
crazylogger
·قبل 17 يومًا·discuss
Chinese labs access Claude via API. Isn't it the black box method by definition?
crazylogger
·قبل 24 يومًا·discuss
Xiaomi Mimo v2.5 is my favorite alternative. Matches DS v4 Flash (official) pricing exactly and supports image/audio/video input.
crazylogger
·قبل 24 يومًا·discuss
Cache hit rate dominates your total cost calculation for long agent session, and it largely depends on the provider. Deepseek's native deployment is probably much better than third party in this regard. For v4 pro it's a whopping >100x price difference between normal input vs. cached input tokens.
crazylogger
·قبل 25 يومًا·discuss
The promise of intelligence might be larger still. By scaling and using superintelligent LLMs to write code for itself, it's possible that the whole field of robotics is just another problem you can point LLM agents at and expect to be solved by afternoon, just like one of those math puzzles. "Traditional" robotics R&D (or any R&D really) would be worthless due to abundance.
crazylogger
·قبل 26 يومًا·discuss
This is equivalent to buying 3 extra days of free time with 60% of your income. You want more (holidays, in this case) and you buy them with work.
crazylogger
·الشهر الماضي·discuss
They basically said "Deepseek ran 150,000 requests and here's the gist of one of their prompts". Anthropic doesn't know which accounts are Deepseek proxies beforehand, so definitely sounds like retrospective analysis of broad user logs to me.

Of course Anthropic realizes saying this straight is problematic so they said they examined request metadata, but no, I don't think they can get this kind of insight from metadata (token counts, request time, etc.)
crazylogger
·الشهر الماضي·discuss
Didn’t they all but admit they’ve been storing and actively looking at requests with this post: https://www.anthropic.com/news/detecting-and-preventing-dist... ?

If they weren’t storing, they’d be oblivious to what customers are doing, making this kind of detection impossible. What data did they train their classifier on, if not real user (distiller) traffic?
crazylogger
·الشهر الماضي·discuss
> It might seem weird for us to teach beginners Python, knowing that they’ll then have agents output other, faster languages. I see an analogy here with Chinese: Many people don’t realize this, but children in China first learn Latin characters, which they use to spell out Chinese phonetically, using a system called “pinyin.” They then use their knowledge of Latin characters to learn Chinese characters, whose pronunciation isn’t obvious from the characters themselves.

The article did explain, albeit near the end.
crazylogger
·قبل شهرين·discuss
OpenRouter may see you fire hundreds of requests at them, but they have no idea that "these 50 requests here at 4PM are for task A", "those 100 requests there does task B", etc. So it's a shallow analysis at the "overall request shape" level.
crazylogger
·قبل شهرين·discuss
For a single database using UUIDs, yes, it's astronomically rare. But it's quite a different thing to say that no computer system on Earth has ever experienced a UUID collision. The number of systems out there is also astronomical.
crazylogger
·قبل شهرين·discuss
People had this "why you probably can't run a GPT-4 (or even GPT-3.5) class model on your MBP anytime soon" conversation before.

Today's LLMs are able pack much more capabilities into fewer parameters compared to 2023. We might still be at the very rudimentary phase of this technology there are low-hanging efficiency gains to be had left and right. These models consume many orders of magnitude more energy than a human brain, this all seems like room for improvement.

The right question: is there a law in information theory that fundamentally prevents a 70B model of any architecture from being as smart as Opus 4.7?
crazylogger
·قبل 3 أشهر·discuss
"Hi ChatGPT, propose and prove something radically new in the genre of Gödel's theorem."

How is this not just another proposed problem (albeit with a search space much larger than an Erdos problem's)?
crazylogger
·قبل 3 أشهر·discuss
I haven't seen anyone claiming that API prices are subsidized.

At some point (from the very beginning till ~2025Q4) Claude Code's usage limit was so generous that you can get roughly $10~20 (API-price-equivalent) worth of usage out of a $20/mo Pro plan each day (2 * 5h window) - and for good reason, because LLM agentic coding is extremely token-heavy, people simply wouldn't return to Claude Code for the second time if provided usage wasn't generous or every prompt costs you $1. And then Codex started trying to poach Claude Code users by offering even greater limits and constantly resetting everyone's limit in recent months. The API price would have to be 30x operating cost to make this not a subsidy. That would be an extraordinary claim.
crazylogger
·قبل 3 أشهر·discuss
Training data == source code, training algorithm == compiler, model weights == compiled binary.
crazylogger
·قبل 3 أشهر·discuss
If all they do is "just" brute-force problem solving, then they are already bound to take over R&D & other knowledge work and exponentially accelerate progress, i.e. the SciFi "singularity" BS ends up happening all the same. Whether we classify them as true reasoning is just semantics.
crazylogger
·قبل 3 أشهر·discuss
Why would this be in the client code though?