davidsainez
Joined 2 years ago
Karma
152
Submissions
41
Member since
Nov 6
https://bsky.app/profile/davidsainez.com
View on Hacker NewsRecent submissions
Comment · 20 days ago
AFAIU prefill speed makes a bigger difference in agentic coding workflows as the harness likely spends more time reading than creating new code. Qwen in particular spends a lot of time reasoning so it does make a larger impact there
Comment · 3 months ago
The Maverick is a different class of vehicle: it has a unibody with no mechanical 4x4.
Comment · 8 months ago
I put off podman for a while because of claims of compatibility issues, which is unfortunate because I've had an excellent experience since switching over. Can you point as specific issues you've had (not doubting, just curious)?
I also have heard a lot of recommendations for OrbStack, but I haven't had problems with speed either. And I could never stomach using a proprietary system for such a core part of my workflow.
For context I use containers for practically everything and I run some decently complex workflows on them: fullstack node codebases, networking, persistent volumes, mounting, watch mode, etc. Red Hat knocked it out of the park with podman!
Comment · 11 months ago
Ever heard of Debian or Linux?
Comment · 11 months ago
Excited to put this through its paces. It seems most directly comparable to GPT-OSS-20B. Comparing their numbers on the Together API: Trinity Mini is slightly less expensive ($0.045/$0.15 v $0.05/$0.20) and seems to have better latency and throughput numbers.
Comment · 11 months ago
Why would that undermine its integrity? AFAICT there are a selection of "open" US-based LLMs to choose from: Google's Gemma, Microsoft's Phi, Meta's LLAMA, and OpenAI's GPT-OSS. With Phi licensed under MIT and GPT-OSS under Apache 2.
Comment · 11 months ago
I find the existence of opennext convincing proof of lock-in: https://blog.logrocket.com/opennext-next-js-portability/
Personally, I don’t bother with nextjs at all.
Comment · 11 months ago
But to determine its merit a maintainer must first donate their time and read through the PR.
LLMs reduce the effort to create a plausible PR down to virtually zero. Requiring a human to write the code is a good indicator that A. the PR has at least some technical merit and B. the human cares enough about the code to bother writing a PR in the first place.
Comment · 11 months ago
Not wanting to review and maintain code that someone didn't even bother to write themselves is childish?
Comment · 11 months ago
> works flawlessly
> intermittent outages
Those seem like conflicting statements to me. Last outage was only 13 days ago: https://news.ycombinator.com/item?id=45915731.
Also, there have been increasing reports of open source maintainers dealing with LLM generated PRs: https://news.ycombinator.com/item?id=46039274. GitHub seems perfectly positioned to help manage that issue, but in all likelihood will do nothing about it: '"Either you have to embrace the Al, or you get out of your career," Dohmke wrote, citing one of the developers who GitHub interviewed.'
I used to help maintain a popular open source library and I do not envy what open source maintainers are now up against.
Comment · 11 months ago
AFAICT, kimi k2 was the first to apply this technique [1]. I wonder if Anthropic came up with it independently or if they trained a model in 5 months after seeing kimi’s performance.
1: https://www.decodingdiscontinuity.com/p/open-source-inflecti...
Comment · 11 months ago
I never claimed that it was being done in secrecy. Here is another example: https://groq.com/blog/inside-the-lpu-deconstructing-groq-spe....
I have seen multiple people mention openrouter multiple times here on HN: https://hn.algolia.com/?dateRange=all&page=0&prefix=true&que...
Again, I'm not claiming malicious intent. But model performance depends on a number of factors and the end-user just sees benchmarks for a specific configuration. For me to have a high degree of confidence in a provider I would need to see open and continuous benchmarking of the end-user API.