HackerTrans
トップ新着トレンドコメント過去質問紹介求人

lerchmo

no profile record

コメント

lerchmo
·5 か月前·議論
This is important. 20 billion is just like a rumor? would love to see the breakdown in the form of audited financials.
lerchmo
·6 か月前·議論
I also see ghosty consume a massive amount of memory and periodically need to restart.
lerchmo
·7 か月前·議論
I would assume he is a fiduciary... I am curious what happens with investors here?
lerchmo
·7 か月前·議論
curious how the execs can honor the fiduciary duty to share holders assuming only they? get the 20 billion and the company is left headless and leaking all of its intellectual property to Nvidia?
lerchmo
·10 か月前·議論
I see thinking can be toggled in the CLI, anyone figured out how to toggle it in the extension?
lerchmo
·10 か月前·議論
smolagents uses a similar mechanism.
lerchmo
·11 か月前·議論
in the context of LLM's we are in the Friendster era
lerchmo
·11 か月前·議論
Boggle head is basically pick 2-3 vanguard etfs and check back in 25 years.
lerchmo
·11 か月前·議論
assuming this is something like covered calls?
lerchmo
·12 か月前·議論
Why don’t they just offer a $500/m plan?
lerchmo
·12 か月前·議論
Time to start using Claude code proxy and other models. This black box rate limit is really lame.
lerchmo
·12 か月前·議論
Alot of deterministic systems externalize their edge cases to the user. The software design doesn’t fully match the reality of how it gets used. Ai can be far more flexible in the face of dynamic and variable requirements.
lerchmo
·昨年·議論
You could hire 100 people to manage your timeseries data and save 70%
lerchmo
·昨年·議論
One thing I don’t understand about these agent frameworks… cursor, Claude, Claude code, cline, v0… all of the large production agents with leaked prompts use xml function calling, and it seems like these frameworks all only support native json schema function calling. This is maybe the most important decision and from my experience native tool calling is just about the worst option.
lerchmo
·昨年·議論
claude code will do this https://www.youtube.com/watch?v=2TIXl2rlA6Q&t=580s
lerchmo
·昨年·議論
Enough to kill is a meaningless metric.
lerchmo
·昨年·議論
https://aider.chat/docs/leaderboards/ your experience doesn't align with my experience or this benchmark. o1 pro is good but I would rather do 20 cycles on gemini 2.5 rather than wait for Pro to return.
lerchmo
·昨年·議論
The switching costs are so low (zero) that anyone using these models just jumps to the best performer. I also agree that this is not a brand or narrative sensitive project.
lerchmo
·昨年·議論
[flagged]