Instead of asking for read permissions to repos, it is asking me to login to Github, via Bloop. Why such setup was done? Isn't just read access enough?
Launch HN: Bloop (YC S21) – Code Search with GPT-4
101–110 of 131 posts
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#102Where to go next? A Toolformer that calls an AST parser. In VS Code I am running Copilot and IntelliSense side by side. Two competing tab completions -- ridiculous. They should be integrated. I want a Copilot that listens to the interpreter / compiler, so that it only makes correct suggestions.
I can't stand how co-pilot hijacks the standard code completion, often overriding the typescript completion I actually want or generating something distracting. There should be a way to only run completions when prompted. Please upvote this issue if you run into the same problems: https://github.com/community/community/discussions/9817
I had the same issue of Copilot hijacking suggestions with Intellij family of IDEs. Apparently there is a setting, disabled by default, to show both the suggestions (copilot's and Intellij's). Not on my laptop but it's somewhere in
Settings > languages and frameworks> Copilot
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#103From the Codeium ( https://www.codeium.com ) team here! Exciting to see more teams take on the code search problem - modern pure regex definitely is a suboptimal solution. Just to objectively highlight some of the similarities and differences between Bloop and Codeium Search (Codeium also provides Autocomplete) to a user: - Both are free for individuals - Both use a mix of AI and regex - Bloop has both free local and…
Posting about your company when relevant is one thing, advertising it another’s launch thread is another, and it’s pretty gauche… especially when, in this very thread, one of your testimonials is saying he doesn’t actually use your product: https://news.ycombinator.com/item?id=35236557
I disagree, I am very happy that parent posted this. I want to know about other tools in this space, and the comment contains a nice summary of pros and cons, some of which are extremely relevant to me!
Bloop looks awesome too, don't get me wrong, and I'll check it out.
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#104Tangential note to the person doing the video voiceover: pls process the audio a bit (high-pass filter at least?), or use higher a quality headset.
what is a high-pass filter?
What a coincidence, just learned about those in my EE class lol
It filters out low frequencies (e.g. motorcycle) and only lets higher frequencies (like a human voice) be expressed
Edit: mixed em up, rookie mistake :p
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#105Would be interesting to see precision and recall numbers - do you have any?
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#106Earlier quoted context omitted.
> Second, imagine the same argument applied to a utility like electricity. Isn’t that how electricity works? You purchase electricity directly from the producer, and buy additional plugins (literally) that work with the single source of electricity you’re purchasing.
That would be akin to giving each of the 'plugins' your GPT API key and pay the usage bill directly to OpenAI. The plugin developers would still want $$$ for the app even if the GPT usage was excluded though.
Wouldn't it be a one-time purchase then? "Buy my prompt for $10 that enables you to search your codebase"
And we're back to Prompt Engineers :)
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#107I don’t understand these new saas that rely on GPT. It surely is my lack of understanding, but since the interface to GPT is mainly text: why any company would pay for N different GPT saas (e.g., one for searching for code, another for searching for documentation on confluence, another for allowing your business analysts with their queries, etc.)? Wouldn’t it make more sense for any company to have only ONE interface…
It seems you're doing the opposite of "missing the forest for the trees". You see the forest (the app) but you're not seeing the individual trees.
The answer to why companies don't have one interface with GPT is that they would still need to invest time and money into building the application that uses GPT. Checkout the bloop source code to get an idea of what's needed https://github.com/bloopAI/bloop there are also many complex things to deal with. You can't just shove an entire codebase into GPT-4, it has limited ability to track context. The codebase needs to be indexed and stored in a way that sematic search can be done on it very quickly. Every app has their own unique challenges towards getting the data into GPT and making it fast.
TL;DR companies are buying apps that use GPT-4 API, not just access to GPT-4. They'd rather buy the apps instead of building and maintaining them.
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#108I don’t understand these new saas that rely on GPT. It surely is my lack of understanding, but since the interface to GPT is mainly text: why any company would pay for N different GPT saas (e.g., one for searching for code, another for searching for documentation on confluence, another for allowing your business analysts with their queries, etc.)? Wouldn’t it make more sense for any company to have only ONE interface…
Most of bloop's interface is search results, which are driven by the LLM and have highlighted line ranges and go-to-ref/def. Down the line, many other LLM powered tasks will need specialised interfaces too, like showing a diff or a git history tree.
This is quite different from a GPT tool for most other jobs, and I think having granular control of the interface layer certainly helps us ship a better product.
That's not to say everything needs to be an app. If the output is just conversational text, it can and probably will be some kind of 'Alexa skill' like plugin.
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#109This looks great! Is there documentation in the repository that goes into greater detail about the query process? It might be nice to add some diagrams or other explanations about the architecture there.
Query flow looks to be roughly along the lines of: - llm rephrases the last conversation entry into a standalone, context-free search query - rephrased query is embedded, top-k results retrieved from the vector db - llm selects a top-1 winner from the top-k results - llm answers the question given conversational context and the top-1 code search result (from https://github.com/BloopAI/bloop/blob/8905a36388ce7b9dadaed…
That's correct. A good one to to get bloop to answer, here's what I got: https://imgur.com/a/nlx4YRq
To create a response to a user's natural language query, the code follows these steps:
Parse the input query using parse_query(), which internally calls parser::parse_nl() to convert the natural language query into a structured format.
Rephrase the query if necessary, or proceed with the initial query by extracting keywords using get_keywords().
Perform a search for relevant code snippets using search_snippets(), which calls the semantic.search() method to retrieve matching snippets.
If needed, grow the relevant snippet using grow_snippet(), which extends the snippet's surrounding lines while maintaining its token count within a predefined limit.
Construct an AnswerResponse object with the user ID, session ID, query ID, and the snippets obtained.
Convert the AnswerResponse into a webserver::Response and return it to the user.
Please note that this is a simplified explanation of the process. The actual code may have additional checks and logic.
Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4
#110Tangential note to the person doing the video voiceover: pls process the audio a bit (high-pass filter at least?), or use higher a quality headset.
Apologies, was very hastily recorded in between about a million other pre-launch tasks.
I thought my Sennheiser Momentum 4's would do a better job, but even they were no match for a glass call booth.