HackerTrans
TopNewTrendsCommentsPastAskShowJobs

lerchmo

no profile record

comments

lerchmo
·5 bulan yang lalu·discuss
This is important. 20 billion is just like a rumor? would love to see the breakdown in the form of audited financials.
lerchmo
·6 bulan yang lalu·discuss
I also see ghosty consume a massive amount of memory and periodically need to restart.
lerchmo
·7 bulan yang lalu·discuss
I would assume he is a fiduciary... I am curious what happens with investors here?
lerchmo
·7 bulan yang lalu·discuss
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 bulan yang lalu·discuss
I see thinking can be toggled in the CLI, anyone figured out how to toggle it in the extension?
lerchmo
·10 bulan yang lalu·discuss
smolagents uses a similar mechanism.
lerchmo
·11 bulan yang lalu·discuss
in the context of LLM's we are in the Friendster era
lerchmo
·11 bulan yang lalu·discuss
Boggle head is basically pick 2-3 vanguard etfs and check back in 25 years.
lerchmo
·11 bulan yang lalu·discuss
assuming this is something like covered calls?
lerchmo
·12 bulan yang lalu·discuss
Why don’t they just offer a $500/m plan?
lerchmo
·12 bulan yang lalu·discuss
Time to start using Claude code proxy and other models. This black box rate limit is really lame.
lerchmo
·12 bulan yang lalu·discuss
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
·tahun lalu·discuss
You could hire 100 people to manage your timeseries data and save 70%
lerchmo
·tahun lalu·discuss
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
·tahun lalu·discuss
claude code will do this https://www.youtube.com/watch?v=2TIXl2rlA6Q&t=580s
lerchmo
·tahun lalu·discuss
Enough to kill is a meaningless metric.
lerchmo
·tahun lalu·discuss
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
·tahun lalu·discuss
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
·tahun lalu·discuss
[flagged]