Viewing profile — miguelaeh
miguelaeh
HN member- Joined
- Wed, Feb 02, 2022, 6:09 PM UTC
- HN karma
- 29
- Public activity
- 60 items
- HN profile
- View on Hacker News ↗
About miguelaeh
Recent public activity
-
comment
Comment #48577110
This is a "search engine" I built a couple of weeks ago while thinking about the agentic economy. Our agents need a way to find other agents and tools that help them complete compl…
- story
- story
-
comment
Comment #47924073
There is an event on the Frontier Tower today to talk about this paper in case someone is interested
-
comment
Comment #45685764
> Most importantly, you need to carefully engineer the learning process, so that you are not simply compiling an ever growing laundry list of assertions and traces, but a rich set …
- story
-
comment
Comment #44847735
Hey there! Nitpicks creator here. I built Nitpicks initially because I was tired of PMs sending me small screen recordings with changes they wanted, so that it automatically implem…
- story
- story
-
comment
Comment #43114695
You should add some way of contact in the website
-
comment
Comment #43050734
Hi HN! I believe there are many issues for devs and users with the current approach of copy-pasting AI provider API keys into applications. I have built brainlink.dev as a solution…
- story
-
comment
Comment #42791022
Cool! Are you indexing the web or just using a search engine like Bing? I understand that using a search engine is a problem because your results will be as good as those of the se…
-
comment
Comment #41947575
I have been recently exploring and testing this approach of offloading the AI inference to the user instead of using a cloud API. There are many advantages and I can see how this c…
- story
- story
-
comment
Comment #41610273
I am betting on local AI and building offload.fyi to make it easy to implement in any app
-
comment
Comment #41585081
Wow. I didn't know that. It's crazy. I am aware of the legal and tax burdens that many entrepreneurs suffer because of the exit tax. That's the reason why many of them (me included…
-
comment
Comment #41584946
The first cars, networks, and many other things were not unexpensive. They became so with time and growing adoption. Cost of compute will continue decreasing and we will reach that…
-
comment
Comment #41578379
I am from Spain, the system is just a joke. It is not taxing the wealthy people, just those wealthy enough to live well but not worth creating a holding company, which is in most c…
-
comment
Comment #41578334
You're welcome! Let me know if you plan to integrate local models as mentioned in other comments, I am working on something to make it transparent.
-
comment
Comment #41578295
I don't think the point here should be the cost, but the fact that you are sending everything you write to OpenAI to train their models on your information. The option of a local m…
-
comment
Comment #41578242
I am a Grammarly user and I just installed Scramble to try it out. However, it does not seem to work. When I click on any of the options, nothing happens. I use Ubuntu 22.04. Also,…
-
comment
Comment #41529484
I guess what some people do not understand is that K8s was created internally at Google, for managing their services and handling millions of users. For new projects that, with luc…
-
story
Are companies interested on running LLM inference locally?
I have been thinking about this recently. Many projects are focused on running LLMs and SLMs locally. However, is that just for playing around? Or do you actually want to run the i…