Viewing profile — SilenN
SilenN
HN member- Joined
- Thu, Sep 05, 2019, 12:26 PM UTC
- HN karma
- 97
- Public activity
- 48 items
- HN profile
- View on Hacker News ↗
About SilenN
Recent public activity
-
comment
Comment #49127039
^this There's two ways to functionally measure this, reconstruction fidelity (which we're able to get to 0.7 - 0.95), and downstream performance (which agrees on the best and worst…
- comment
-
comment
Comment #49116710
Exactly
-
comment
Comment #49115727
Expensive, in the thousands. We have our own infra in house and are working on bringing these costs down
-
comment
Comment #49115387
Technically 0 because a) it ingests your already existing traces and does an initial training run b) in the app we'll have pre-trained routers you can start with that will then lea…
-
comment
Comment #49063834
Fixed formatting which will help with readability. We do routing, distillation, and token compaction.
-
comment
Comment #49063833
Let me know if you have any questions!
-
comment
Comment #49063830
Thanks :)
-
comment
Comment #49063822
Thanks for the heads up, removed mention!
-
comment
Comment #49063790
Happy to answer any qs.
-
comment
Comment #49063778
Valid criticism. Happy to answer any qs. We're still working on solidfying results.
-
comment
Comment #49063775
It's open source! We do have a platform we'll be launching as well to manage training + serving for you which will require more diligent privacy guarantees.
-
comment
Comment #49063769
Open source models. wmo routes requests between frontier models and open source models that continuously train using Tinker. As the smaller models improve, more traffic gets routed…
-
comment
Comment #49063728
That's cool, thanks for sharing!
-
story
Show HN: Optimize and serve models with Fable quality at half the cost
Hi HN, we built world-model-optimizer, an open source tool to continually improve a specialized model for an agent. It does this by simulating production tool responses through tex…
- story
-
comment
Comment #48735125
world-model-harness makes it easy to go from agent traces to faithful replication of your production environment where your agents run. Basically, an LLM pretends to be a virtual m…
- story
-
comment
Comment #46894192
Thanks! I do have a section on this in the article "Why genetic algorithms aren't state of the art" "Physics simulation involves discontinuities (contacts, friction regimes), long …
- story
-
comment
Comment #46726672
Simply, it's when your output embedding matrix = input. You save vocab_dim*model_dim params (ex. 617m for GPT-3). But the residual stream means that the weight matrices are roughly…
- story
-
comment
Comment #46695378
https://news.ycombinator.com/item?id=46685327
-
comment
Comment #46695294
I disregard any comments like this one as baseless hate unless given an example or something constructive.
-
comment
Comment #46695272
See what you don't understand is that you need to coordinate the deacon to take the witness out back and talk to the mayor. It's actually quite trivial.