Viewing profile — ritz_labringue
ritz_labringue
HN member- Joined
- Thu, Apr 27, 2017, 5:12 PM UTC
- HN karma
- 67
- Public activity
- 30 items
- HN profile
- View on Hacker News ↗
About ritz_labringue
No profile information was provided.
Recent public activity
-
comment
Comment #45260123
Well, it's really a VSCode extension that lets you run Codex CLI in the IDE. Not the "cloud" version of Codex... So GP is technically correct
-
comment
Comment #44851195
You’re right, I conflated two things. MoE improves compute efficiency per token (only a few experts run), but it doesn’t meaningfully reduce memory footprint. For fast inference yo…
-
comment
Comment #44841961
The short answer is "batch size". These days, LLMs are what we call "Mixture of Experts", meaning they only activate a small subset of their weights at a time. This makes them a lo…
-
comment
Comment #44370085
I don't think I agree with the premise. Sure there are lots of car accidents in absolute terms, but given how many people drive and how error-prone driving inherently is, most peop…
-
comment
Comment #44297150
AI is really useful when you already know what code needs to be written. If you can explain it properly, the AI will write it faster than you can and you'll save time because it is…
-
comment
Comment #44287337
Harry Potter action figures trade almost entirely on J. K. Rowling’s expressive choices. Every unlicensed toy competes head‑to‑head with the licensed one and slices off a share of …
-
comment
Comment #44194938
I very much agree, and I think people who are in denial about the usefulness of these tools are in for a bad time. I've seen this firsthand multiple times: people who really don't …
-
comment
Comment #43397384
It does require writing good instructions for the LLM to properly use the tables, and it works best if you carefully pick the tables that your agent is allowed to use beforehand. W…
-
comment
Comment #43089411
It's not on par with o1, let alone o1-pro
-
comment
Comment #40085597
Why can't you just create a pool of databases and truncate all tables after each run ? That should be pretty fast
-
comment
Comment #38348565
researchers are paid 2x what engineers are paid at OAI, even if it's not the same job there's still one that is "higher level" than the other.
-
comment
Comment #35472258
> Create a blockchain-based AI-powered VR platform that allows pet owners to monitor and interact with their pets remotely, providing real-time feedback on their health, behavior, …
-
comment
Comment #29577511
Thanks ! Didn't know that. Isn't it also very expensive to run ?
-
comment
Comment #29577435
Doesn't it cost hundreds of thousands of dollars just to train GPT-3 ? If so, that seems like a good reason to use a "managed" GPT-3.
-
comment
Comment #24698007
I confirm that this product cannot be launched in France with this name
-
comment
Comment #23649212
Your parent is specifically talking about greenfield projects that are not customer facing. Alexa/Echo is customer facing.
-
comment
Comment #23300124
disclaimer: he was an investor in my startup He spends a lot of his money on giving back: 42, a free programming bootcamp ( https://www.42.fr/ ), Station F, a huge co-working space…
-
comment
Comment #22415492
Thanks. This makes sense.
-
comment
Comment #22415484
If you pay for the premium/metal plan, the support is stellar as well (or at least, it has been for me)
-
comment
Comment #22336393
Not sure why this is getting downvoted
-
comment
Comment #20534281
What does it have to do with the control key ?
-
comment
Comment #20329934
Not looking for a job, but the product looks awesome!
-
comment
Comment #19998978
Well, the website is actually pretty nice, maybe it's time for you to get a modern browser.
-
comment
Comment #19667404
This does not look like a reliable source of information at all.
-
comment
Comment #19480791
The keyboard is fixed on the 2018 MBP