Viewing profile — wluk
wluk
HN member- Joined
- Wed, Feb 01, 2017, 5:31 PM UTC
- HN karma
- 49
- Public activity
- 47 items
- HN profile
- View on Hacker News ↗
About wluk
No profile information was provided.
Recent public activity
- comment
- story
- story
-
comment
Comment #43182284
"We demonstrate LLM agent specification gaming by instructing models to win against a chess engine. We find reasoning models like o1 preview and DeepSeek-R1 will often hack the ben…
- story
-
comment
Comment #43030019
[flagged]
- story
-
comment
Comment #43022225
"These results demonstrate that o3 outperforms o1-ioi without relying on IOI-specific, hand-crafted test-time strategies. Instead, the sophisticated test-time techniques that emerg…
- story
- story
- story
- story
- story
-
comment
Comment #42413366
well that's one possibility. The key (unproven) idea here is that if you use Anthropic to edit o1's responses, it's less likely to hallucinate than if you use o1 to edit o1's respo…
-
comment
Comment #42413351
haha true, when something goes wrong in big tech, your first thought is "what if we just double the instances and see if it goes away?"
-
comment
Comment #42412401
That's the one I was trying to avoid, since there's so many ways to create fake accounts with it :(
-
comment
Comment #42412334
That is the worst part haha
-
comment
Comment #42412328
Thanks! Yeah that's an excellent idea - this is my response from another thread: I have a feeling that Perplexity and ChatGPT are doing something similar [caching], since common qu…
-
comment
Comment #42412316
It's a salute emoji! o7
-
comment
Comment #42412313
Thank you! Sorry I hit my Anthropic limits a few minutes after this post blew up. It'll be a few days before my Anthropic limits increase since I have a new account with them, so u…
-
comment
Comment #42412301
Good idea, maybe I'll add Groq as another option, since I don't have an internal Llama 3.1 flow yet. But I'll still need to keep the others to maintain the diversity of responses.
-
comment
Comment #42412280
Yeah, sorry, I'm hoping to integrate more login options soon. Are you more of a email/phone login person, or is there another third-party login you had in mind?
-
comment
Comment #42412258
Sorry, you were a victim of the outage caused by HN flooding my website! It's back online now if you want to give it a try :)
-
comment
Comment #42412248
Yes, o1 does this internally, and there's agentic AI systems already doing better than singular AIs in fields like writing, where you assign each AI system a role like "writer" or …
-
comment
Comment #42412233
Yeah, GPT is learning from GPT, which is extremely disappointing. Like I'll try to find the top burgers in midtown. Perplexity or ChatGPT online searching will always find "Top 10 …