Viewing profile — mattyyeung
mattyyeung
HN member- Joined
- Wed, Sep 28, 2011, 3:05 PM UTC
- HN karma
- 98
- Public activity
- 20 items
- HN profile
- View on Hacker News ↗
About mattyyeung
Recent public activity
-
comment
Comment #45779570
oooh fantastic. Thanks! Exciting My initial test looks pretty good, seems I will need to muck around a bit to get to "one click runs the simulation and displays the trace and stats…
-
comment
Comment #45779436
Does anybody have advice on how to embed perfetto UI into local tool? I'm currently using the old catapult chrome trace viewer to visualise and inspect scheduler outputs but there …
-
comment
Comment #40553834
You may be interested "Deterministic Quoting"[1]. This doesn't completely "solve" hallucinations, but I would argue that we do get "good enough" in several applications Disclosure:…
-
comment
Comment #40388613
I think you could get a pretty good solution for that using RAG and some tricks with prompt engineering and semantic chunking. With google's very-long-context models (Gemini) you m…
-
comment
Comment #40388575
I would love to learn more, where would you recommend I look?
-
comment
Comment #40334918
Yes, extractive QA is one of the improvements beyond the "minimalist implementation" from the article. In our lingo, we'd say that's another way to create a deterministic quotation…
-
comment
Comment #40333469
Can quotations be hallucinated? Or are you using something like "deterministic quoting"[1]? Disclosure: author on that work. [1] https://mattyyeung.github.io/deterministic-quoting
-
comment
Comment #40292841
Thanks for the thought-provoking comment. It's all grey isn't it? Vanilla RAG is a big step along the spectrum from LLM towards search, DQ is perhaps another small step. I'm no exp…
-
comment
Comment #40292627
I'd put it like this: RAG = search engine, but sometimes hallucinates RAG + deterministic quoting = search engine that displays real excerpts from pages.
-
comment
Comment #40292582
Unfortunately I don't believe that accuracy will scale "multiplicitively". You'll typically only marginally improve beyond 95%... and how much is enough? Even with such a system, w…
-
comment
Comment #40292538
Two possibilities: (1) if the contents (unique reference string) doesn't match, then it's trivially detected. Typically the query is re-run (non-determinism comes in handy sometime…
-
comment
Comment #40292459
Author here, thanks for your interest! Surprising way to wake up in the morning. Happy to answer questions
- story
- story
- story
- story
-
comment
Comment #35452488
I didn't really track... apparently there's 30-ish hours of video, but lectures are just the beginning. The real learning happens when you play and build. The first lesson was rele…
-
comment
Comment #35452434
Depends. Some would benefit from simultaneous, others sequential. I did them in "chunks" starting with fastai but that was more driven by the release schedule. Personally I'd recom…
-
comment
Comment #35450742
I just finished this! My thoughts: I recommend it. I feel I can now read an arbitrary paper, frown a lot, and eventually understand what it's talking about - to the point where I c…
- story