anonymoushn
Joined 16 years ago
Karma
6,269
Submissions
3,523
Member since
Dec 9
[email protected]
View on Hacker NewsRecent submissions
Comment · 5 months ago
I couldn't reproduce this behavior with Sonnet 4, and Sonnet 3.7 has been deprecated since I messed with this stuff. You can try tokenizing the string "<hello> </hello>"
I think the correct tokenization of the string will not have any tokens that contain mixed punctuation and letters, but the result of this approach does contain such claimed tokens.
Comment · 6 months ago
That's " 'd ".strip(), an english contraction suffix. it's 1 token, but using this echo approach you will be served the apostrophe and the subsequent letter for the first time in different steps.
Comment · 6 months ago
You can't reliably obtain correct token boundaries with this method. For example, "'d" is 1 token, but the API will return "d" stuck to the next token. Weirdly this seems to be specific to the letter "d". Similar stuff happens around "<". About all caps words, some words are in the vocab in all caps, such as MERCHANTABILITY.
Comment · 6 months ago
their old tokenizer performed some space collapsing that allowed them to use the same token id for a word with and without the leading space (in cases where the context usually implies a space and one is not present, a "no space" symbol is used).
Comment · 6 months ago
Is this the wrong URL? this seems to be a blog post from October 2025 called "Introducing: Local Browser AI"
Comment · 6 months ago
How do you guys decide which settings should be configurable via environment variables but not settings files and which settings should be configurable via settings files but not environment variables?
Comment · 6 months ago
> On of our product principles is to avoid changing settings on users' behalf
Ideally there wouldn't be silent changes that greatly reduce the utility of the user's session files until they set a newly introduced flag.
I happen to think this is just true in general, but another reason it might be true is that the experience the user has is identical to the experience they would have had if you first introduced the setting, defaulting it to the existing behavior, and then subsequently changed it on users' behalf.
Comment · 7 months ago
Oh, can you post some benchmarks? I didn't know that parser throughput per core would change with the amount of data like that.
Comment · 7 months ago
why
Comment · 7 months ago
are those tools known for their fast json parsers?
Comment · 8 months ago
ideally users could be banned for posting LLM outputs as if they were authored by humans https://www.pangram.com/history/49335ddf-118d-43e4-9340-a58a...
Comment · 9 months ago
Hello, the part about canonical filtering in https://openreview.net/pdf?id=DFybOGeGDS doesn't seem to try to account for pretokenization. For example, if you receive " 天天中彩票APP" in o200k, it means there has to be a lowercase letter within the span of letters, and while tokens like (4 spaces) may be pairwise compatible with tokens like "123" according to the BPE merge rules, the pretokenizer would split the span of spaces to give (3 spaces), " ", "123" instead. Are you aware of any work that does actual canonical generation for models with this kind of pretokenization regex?
Comment · 9 months ago
use claude code if you want to use opus
Comment · 9 months ago
what does "logprobs look off" mean
Comment · 9 months ago
Hello, a couple years ago I participated in a contest to count word frequencies and generate a sorted histogram. There's a cool post about it featuring a video discussing the tricks used by some participants. https://easyperf.net/blog/2022/05/28/Performance-analysis-an...
Some other participants said that they measured 0 difference in runtime between pshufb+eq and eqx3+orx2, but i think your problem has more classes of whitespace, and for the histogram problem, considerations about how to hash all the words in a chunk of the input dominate considerations about how to obtain the bitmasks of word-start or word-end positions.