Phind
AI
coding assistant model
SHOW HN2023
79points
22comments
#799of 3,109 in 2023
Top 26%of 2023 by points
How HN took it
MixedNo clear lean
38 positive, 60 neutral or asking, 9 mixed, 63 critical, out of 170 comments about the project. Thread score -0.12.
Execution: 8 for, 30 againstPerformance: 9 for, 13 againstDesign: 6 for, 7 againstDocs: 4 for, 4 againstPricing: 2 for, 5 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Cites sources and links well
From 2 comments
I love that Phind cites what it scrapes. This should be the obligation of all LLM. I always suggest people use it over ChatGPT.
slowhadoken on HNI gave it two tries, GPT-4 was much better in both cases. Tried with two Leetcode questions. It came back with an empty response for one, and provided a worse code (O(n2)…
shazar on HN
Matches or beats GPT-4 on some tasks
From 3 comments
I am a heavy user of GPT4, and Phind was surprisingly able to match GPT4 on several initial programming tasks I gave it. Given the large context window of Phind, it will likely…
drcode on HNRan a quick test with a Rust async code snippet that contains an error. Compared with GPT-4 its gives a far clearer solution, with linked sources to learn more! Super impressive!
eoinboylan on HNI 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.…
alex-moon on HN
Objections
Inconsistent answers and hallucinated APIs
From 3 comments
I like that it provides sources, but I have to check them EVERY time because too often it hallucinates bogus solutions or protocols for me. I'm asking network questions, though,…
standardly on HNDidn't work fine when I asked it a design question: the code and API it used is not correct. GPT-4 did a better job. https://www.phind.com/search?cache=ay8rx37gq8oy3z7uixftlqkt…
iillexial on HNI tried this, but I still have yet to get any LLM to answer me a programming question (that actually works) that I actually want to solve. Basically: "How can I send network…
SirMaster on HN
Weaker than GPT-4 on several coding questions
From 3 comments
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…
cccybernetic on HNI tried this question and GPT4 did way way better to getting closer to a final answer. Phind was horribly wrong. I can't help but think something seems off with your eval given…
dontreact on HN"Python script to extract a list of all Elastic IP's from all regions, from multiple AWS accounts." ChatGPT4 gave me a solid answer hitting all the points I wanted. Phind din't…
ShakataGaNai on HN
HumanEval is a limited benchmark
From 1 comment
This is great work, but HumanEval is an extremely limited benchmark and I don’t think you can seriously claim to beat GPT-4 at coding based only on that metric.
pleonasticity on HN
Requests
Open source the model
From 2 comments
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…
quickthrower2 on HNThis is awesome. Are you planning to open-source the V7 model?
tydunn on HN
Editor integration for Emacs or Vim
From 1 comment
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.
xrd on HN
API access
From 1 comment
Will you be offering the model as an API service? The product my team is working on would benefit from a significantly faster and possibly better performing model than GPT-4. If…
tinco on HN
Questions
What is the training cutoff date
From 1 comment
What‘s the cutoff date?
JanSt on HN
Alternatives named
GPT-4
From 2 comments
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…
cccybernetic on HNI tried this question and GPT4 did way way better to getting closer to a final answer. Phind was horribly wrong. I can't help but think something seems off with your eval given…
dontreact on HN
ChatGPT
From 1 comment
"Python script to extract a list of all Elastic IP's from all regions, from multiple AWS accounts." ChatGPT4 gave me a solid answer hitting all the points I wanted. Phind din't…
ShakataGaNai on HN