301–310 of 358 posts
> Show HN: Phind Model beats GPT-4 at coding Does it? I don't see any evidence of this strong claim in your post, and I think it's quite deceptive how the only link is to a benchmark of open source models (which doesn't include GPT-4). I've tried Phind a few times in the past when it made equally strong claims and been somewhat unimpressed. (To be fair, comparing anything to GPT-4 is tough!) I think it would strength…
I know it isn't popular, but I wish there was a way to use this inside Emacs. Or, vim. I just don't want to use VS Code anymore.
I know it isn't popular, but I wish there was a way to use this inside Emacs. Or, vim. I just don't want to use VS Code anymore.
I've hacked together a basic Emacs ollama api integration that does simplistic code completion against a local LLM from someone else's copilot example. It's slower than I want (about 7 seconds per inference on my M1 mac, typically) and very stupid about what context it sends, but nevertheless: it's just , and only just , enough to be useful. Hadn't considered publishing it because it relies on a python façade to conv…
> You can now get high quality answers for technical questions in 10 seconds instead of 50. ChatGPT 4 does not take 50 seconds to answer, so I don't understand this comparison.
I know it isn't popular, but I wish there was a way to use this inside Emacs. Or, vim. I just don't want to use VS Code anymore.
The standardizing on VS code is one of the saddest developments over the last several years IMHO. I think it's great that VS Code exists, but we're headed for a world where you have to use VS Code if you want the best tooling because it won't support other options. The same thing happened with Java dev and IntelliJ, and IMHO it has been extremely unhealthy for the ecosystem. I'm immensely glad that Copilot supports v…
While I agree, at the very least IntelliJ stood up on its own as a good IDE. I cut my baby teeth on Eclipse, and as soon as I realised how good IntelliJ is, I jumped ship without looking back. The same can barely be said about VS Code.
Could you open source these great models? OK yes you need a competitive advantage. So maybe open source them when you are say 2 models ahead in production? In any case I am happy there is some competition and that it has come from a more pragmatic scrappy space than one of the multiple billion dollar funded places.
Can we have a larger discussion about the tradeoffs that come with open sourcing a model? When fb released Llama they obviously gained a huge amount of developer goodwill but it also required them to invest a serious amount of their own developer time to engage with the community. I'm asking the community what it can offer the company? Or is this just self-abnegation by the company that releases the model?
I tried my standard "trick" question I use for LLMs: "Give me five papers with code demonstrating the state of the art of machine learning which uses geospatial data (e.g. GeoJSON) as both input and output." There is no such state of the art. My hand-wavey understanding is that GIS data is non-continuous, which makes it useless for transformers, and also contextual, which makes it useless for anything else. Will defe…
I tried my standard "trick" question I use for LLMs: "Give me five papers with code demonstrating the state of the art of machine learning which uses geospatial data (e.g. GeoJSON) as both input and output." There is no such state of the art. My hand-wavey understanding is that GIS data is non-continuous, which makes it useless for transformers, and also contextual, which makes it useless for anything else. Will defe…
The code model isn't trained to retrieve papers/articles, it's meant to complete code. Whether or not you find hallucination in a unrelated task isn't particularly interesting.
I'm glad there's growing competition, but GPT4 still outperforms. Here's a recent question I asked: Could you please provide me with a query for my PostgreSQL table? It consists of three columns: 'id,' 'teaser,' and 'full_text,' all of which are of type 'text.' Most 'full_text' entries are articles around 1000 words in length. I'd like to update the 'teaser' column for each row with the first approximately 200 words…
UPDATE your_table SET teaser = substring(full_text from '(\S+\s*){1,200}')
Earlier quoted context omitted.
LOL, it’s not just for “public acceptance”. Look up Chain of Thought. Asking it to get to the point typically reduces the accuracy.
You are being snarky but are right. I have scripts set up to auto summarise expansive answers. I wish I could build this into the ChatGPT ui though.