Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Launch HN: Bloop (YC S21) – Code Search with GPT-4

news.ycombinator.com

Post reply on HN
Print view View original

91–100 of 131 posts

Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4

#91

Post by x-complexity »

dabei wrote: post #90

This is awesome and has huge potential to improve developer productivity! The only thing that it gives me pause is that it requires a very broad Github authorization. Do you really need to "be able to read and write all public and private repository data"?

> This is awesome and has huge potential to improve developer productivity! The only thing that it gives me pause is that it requires a very broad Github authorization. Do you really need to "be able to read and write all public and private repository data"?

Compared to a regular search engine, the permissions required are pretty much the same. Both this & regular search engines need to go through a repo's codebase to be even able to give results in the first place.

Privacy-wise, they could probably make it better by requiring each repo to be approved before they can be searched, but that would make for a more friction-laden developer UX. The broad permissions are likely just a consequence of not wanting to ask the user every time a new repo is to be searched through.

Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4

#92

Post by danbala »

tedsanders wrote: post #65
tkiolp4 wrote: post #46

I 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…

To me, your question seems to boil down to the economics of vertical integration. Two thoughts: First, GPT is all marginal cost, no fixed cost. So the marginal economics of 1 super app vs 10 specialized mini apps is roughly the same. Second, imagine the same argument applied to a utility like electricity. "Why would any company pay for lightbulbs from one company, HVAC from a second company, and appliances from a thi…

pretty quickly llvm/ai support is going to be more on the level of electricity itself. like a utility.

Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4

#94

Post by 8n4vidtmkvmk »

rcme wrote: post #73
tedsanders wrote: post #65

Earlier quoted context omitted.

To me, your question seems to boil down to the economics of vertical integration. Two thoughts: First, GPT is all marginal cost, no fixed cost. So the marginal economics of 1 super app vs 10 specialized mini apps is roughly the same. Second, imagine the same argument applied to a utility like electricity. "Why would any company pay for lightbulbs from one company, HVAC from a second company, and appliances from a thi…

> 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.

Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4

#95

Post by 8n4vidtmkvmk »

x-complexity wrote: post #91
dabei wrote: post #90

This is awesome and has huge potential to improve developer productivity! The only thing that it gives me pause is that it requires a very broad Github authorization. Do you really need to "be able to read and write all public and private repository data"?

> This is awesome and has huge potential to improve developer productivity! The only thing that it gives me pause is that it requires a very broad Github authorization. Do you really need to "be able to read and write all public and private repository data"? Compared to a regular search engine, the permissions required are pretty much the same. Both this & regular search engines need to go through a repo's codebase t…

Why does it need "write" permission?

Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4

#96

Post by DalasNoin »

tedsanders wrote: post #65
tkiolp4 wrote: post #46

I 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…

To me, your question seems to boil down to the economics of vertical integration. Two thoughts: First, GPT is all marginal cost, no fixed cost. So the marginal economics of 1 super app vs 10 specialized mini apps is roughly the same. Second, imagine the same argument applied to a utility like electricity. "Why would any company pay for lightbulbs from one company, HVAC from a second company, and appliances from a thi…

Have you tried just asking gpt4 to write a script that then implements the SAAS as a script that then calls gpt4? You should be careful about analogies, intelligence is special.

Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4

#97

Post by btbuildem »

hn_throwaway_99 wrote: post #49
tkiolp4 wrote: post #46

I 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…

The point is that the interface to Bloop (or whatever 3rd party SaaS product) is just plain text. In programming parlance I would call this a facade [1] on top of GPT-4. The benefit is that you, the end user, can just continue typing things like "Where do we create our database pool?" in a search box, but under the covers Bloop can use GPT-4, but then eventually upgrade to GPT-5, GPT-6, or some other much better curr…

Except in the case of GPT-x, the facade builder must take extra pains to sanitize the inputs, so it doesn't become just a free GPT account for the user to interact with on unrelated topics. That's much more challenging due to the open nature of the prompts (the selling feature). One really lame solution is to ask the user to use their own openai API key.

Re: Launch HN: Bloop (YC S21) – Code Search with GPT-4

#100

Post by siva7 »

tkiolp4 wrote: post #46

I 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…

What you're asking is like "Why should i pay for N different internet saas" because they share a common characteristic (e.g.they use a database) paired with the naivety where you don't understand the underlying complexity of a business application and think you can do this all by yourself
Post reply on HN