I agree, and it’s why I have come to dislike OpenAI.

We are getting front row seats to an object lesson in “absolute power corrupts absolutely”, and I am relieved they have a host of strong competitors.

The difference between Google had it just tried to be an enterprise search API, versus owning the consumer destination for search input/results.

This sounds like a good way of guaranteeing profits and moving the mindset away from just producing good products.

Your argument, which could be correct, makes their choice of the name ChatPGT* even more idiotic

* Or which ever variant the average user might try to type in

Those look more like one-off prompts, and not a proper chat/collab with Gemini.

Every app with a significant installed user base is adding AI features.

OP is lamenting that Cursor and OpenAI chose to create new apps instead of integrating with (someone else’s) existing apps. But this is a result of a need to be always fully unblocked.

Also, owning the app opens up greater financial potential down the line…

How many people use Pages these days? I don't think Apple even mentions the product in their WWDC these days. My guess is that most people either use Microsoft suite as required by their employer or use cloud based knowledge base/notes tools like Notion/Quip/Obsidian/Confluence etc. I doubt Apple thinks it worthwhile to invest in these products.

Apparently it is predicted(1) that their API is a profit making business while chatgpt is a loss leader so far…

(1) https://www.tanayj.com/p/openai-and-anthropic-revenue-breakd...

75%? Thats astonishing to me. Where are you able to see those details?

It wouldn't surprise me if not a lot of enterprises are going through OpenAI's enterprise agreements - most already have a relationship with Microsoft in one capacity or another so going through Azure just seems like the lowest friction way to get access. If how many millions we spend on tokens through Azure to OpenAI is any indication of what other orgs are doing, I would expect consumer's $20/month to be a drop in the bucket.

never figured out on how to activate it in my workspace

The most amazing thing with notebooklm is that is can turn your docs into a very high quality podcast of two people discussing the content of your docs.

The Amazon model.

Same as it ever was.

It's pretty trivial to get increased limits, I've used the API for a few consulting projects and got to tier 4 in a month. At that point you can burn near $200 a day and 2 million tokens per minute.

You only need 45 days to get tier 5 and if you have that many customers after 45 days you should just apply to YC lol.

Maybe you checked over a year ago, which was the wild wild West at the time, they didn't even have the tier limits.

150,000,000 tokens per minute and 30,000 requests per minute is unusable?! Maybe that’s just Tier 5 but the API is most definitely not unusable.

I’m firmly in the camp that their rate limits are entirely reasonable.

You need to use it for some time to get into their higher tiers of usage. I used to also have this problem and it annoyed me greatly, but once I got to usage tier 4 it never happened again (except for o1-preview but that just wastes tokens IMO).

You mean downstream, not upstream. Upstream is closer to the raw materials.

> If they don't secure their position as #1 Chatbot I think they will eventually become #2, then #3, etc.

But can they do it at all? It's not like they are like early Google vs other search engines.

Microsoft is integrating Copilot into many of their products, including Visual Studio and Office/365.

Eh, GitHub CoPilot? Microsoft is literally THE company that understands developers' workflows and creates good IDEs.

Cursor is a funny company. They were invested into by OpenAI, but almost everyone using Cursor uses it with Claude Sonnet 3.5.

> which is basically ChatGPT?

Yea, I'm wondering the same. Is there any good resource to look up whether copilot follows the ChatGPT updates? I would be renewing my subscription, but it does not feel like it has improved similarly to how the new models have...

But my subscription at $20/mo is a fraction of my API usage at $5/day (about $100/mo).

You can sell a lot more GPT services through a higher bandwidth channel — and OpenAI doesn’t give me a way to reach the same bandwidth through their user interface.

idk, I can definitely see value in a lightweight LLM component for VIM to help me look up the correct command sequence to exit :P

I only use Gemini in Colab perhaps 5% of the times I use Colab, yet it is nice to have.

I use Gemini, OpenAI, Claude, smaller models in Grok, and run small models locally using Ollama. I am getting to the point where I am thinking I would be better off choosing one (or two.)

Why do you ask? I did use "4o with canvas" shortly after writing the above. To be clear, my original comment was not about the actual OpenAI implementation of a "canvas style chatbot", but rather that I have found the canvas-chat-UX to be the most effective way to interact with a chatbot. I am basing this on many hours with both ChatGPT (non-canvas until today) and Claude/Anthropic (who has had this feature). As of this writing, I prefer Claude both because of (a) the content of its output and (b) the canvas style, which allows my brain to easily parse what is the topic vs. discussion about the topic.

Not the op, but I just tried it. I agree with his point that this is a huge step up in having the discussion and then a separate canvas where the work takes place, and then iterations are done to the canvas.

I LOVE the UX animation effect ChatGPT added to show the canvas being updated (even if it really is just for show).

Here's my user test so you know I actually used it. My jaw begins to drop around minute 7: https://news.pub/?try=https://www.youtube.com/embed/jx9LVsry...

That's funny, I do the exact same thing. If I'm out and about or otherwise not at a computer, and I have an idea or solution to a bug I wanted to solve, I'll fire up an LLM on my phone (usually Claude these days) and basically brainstorm together the pros and cons, with code sometimes as well.

And venture capital.

Bonus points if you work for Canva.

Will also need to port it to a Slack Canvas.

Can you please use Obsidian to create a canvas showing the situation? ;-)

Strangely too short for AI.

How things get named Canvas:

"Name it clay" -- artistic CMO

"Won't people think they will have to get their hands dirty?" -- CEO

"Right. Name it sculpt. It has a sense of je ne sais quoi about it." -- hipster CMO

"No one can spell sculpt, and that French does not mean what you think it means." -- CFO

"Got it! Name it canvas! It's a blank canvas! It can be anything!" -- CMO

"Perfect!" -- Entire executive team who is now sick of CMO's naming excercise.

> wonder how Paul Graham thinks of Sam Altman basically copying Cursor

If OpenAI can copy Cursor, so can everyone else.

It's just a company that promised AGI would somehow come from developing LLM-based products, rapidly scrambling to keep up with other LLM-based products, to distract from the fact that it's becoming increasingly apparent that AGI is not coming anytime soon.

Cursor was one of the first AI editors I used, but recently Aider has completely replaced the AI assisted coding for me. I still use cursor but just as an editor, all LLM work is done with aider in the shell.

Like Amazon cloning the best selling products, bringing them in house, and then closing the accounts of competitors.

Met a guy who got brought in by Amazon after they hit 8 figures in sales, wined and dined, then months later Amazon launched competing product and locked them out of their accounts, cost them 9 figures.

> potentially every upstream AI company out of YC

You mean downstream.

Agreed on the principle (using the better product) but interestingly I've had the opposite experience when comparing Claude 3.5 Sonnet vs GPT 4o.

Claude's been far and away superior on coding tasks. What have you been testing for?

I have the exact opposite experience. I canceled my crapGPT subscription after >1 year because Claude blew it out of the water in every use case.

Projector make it even better. But I could imagine it depends on the specific needs one has.

This hasn't been my experience. Claude often hallucinates less for me and is able to reason better in fields where knowledge is obscure.

ChatGPT will just start to pretend like some perfect library that doesn't exist exists.

I code and document code and imho Claude is superior, try to tell Gpt to draw a mermaid chart to explain a code flow... the mermaid generated will have syntax errors half of the time.

Code output from is Claude pretty good. It seems to hallucinate less than o1 for me. It's been a struggle to get o1 to stop referencing non-existent methods and functions.

This is why free markets aren't the solution to all our problems.

This is similar to Artifacts [0] in Claude.

[0] https://support.anthropic.com/en/articles/9487310-what-are-a...

I think you can enable Artifacts, which are similar to OpenAI Canvas. Recently, Anthropic also added the ability to select elements within the created Artifact and adjust them (e.g., adjust length, improve code), similar to what Canvas can do.

Claude can generate Artifacts but they are not inline editable and they keep getting regenerated at every prompt.

Canvas appears to be different in that it allows inline editing and also prompting on a selection. So not the same as Claude.

I'm guessing they mean Artifacts: https://www.anthropic.com/news/artifacts

Attempting to do any form of security work using LLM is nigh impossible without a few steps of nudging it out of its “while user is asking me to do bad things: say no” loop.

After a year of heavy LLM use I’ve found the utility limits, my usage has peaked, and I’m developing very restrictive use cases.

Beyond functioning as an interactive O’Reilly manual, LLM only save time if you never read the code they produce. Which is a short term win, but things will blow up eventually, as with all code, and now you’ve got a bigger problem than you started with.

insuflating?

In your landing page it says about competitors

> They're not wasting hours trying to "figure out" a solution

I am pretty sure that we don't have AGI that would figure our solutions to our problems (coding or not) on its own yet. And from experience, you would need to solve the problems at least conceptually before using LLM and try to get something useful out of that.

That's probably the most FOMO driven landing page I've seen so far! I'll bite:

    Your competition is using AI to build their product right now.
    They're not writing code by hand.
    They're not Googling code answers on StackOverflow.
    They're not wasting hours trying to "figure out" a solution.

Extraordinary claims require some investigation!

Let's see how far I get without "Googling answers".

Spoiler: If the competition uses such AI that, good for me!

(Note I don't want to pick on Parrot here; from my first 5 minutes with the tool, it's /fun/, has a nice UI, a good idea for iteration, and somebody has to build such tools to make them work eventually even if they don't work great today yet. I wish it lots of success. But I want to also point out examples of the practical limitations of all such tools, and state that I highly doubt that they today can _in any way_ replace a human programmer who knows what they are doing, and has the awesome skill to use Google, StackOverflow, and "figure out" things.)

Prompt:

    I need a Haskell function that hashes a given file (FilePath)
    with the blake3 hash function.
    It is important that it works on large files (e.g. 100 GB)
    without freezing the Haskell runtime.

Output:

    import qualified Crypto.Hash.BLAKE3 as BLAKE3
    import qualified Data.ByteString as BS
    import System.IO (withFile, IOMode(ReadMode))

    hashFileBLAKE3 :: FilePath -> IO BS.ByteString
    hashFileBLAKE3 filePath = do
      let chunkSize = 8192  -- 8KB chunks
      withFile filePath ReadMode $ \handle -> do
        let loop ctx = do
              chunk <- BS.hGet handle chunkSize
              if BS.null chunk
                then return $ BLAKE3.finalize ctx
                else loop $! BLAKE3.update ctx chunk
        loop BLAKE3.init

Explanation:

    This Haskell function, `hashFileBLAKE3`, calculates the BLAKE3 hash of a
    given file. It's designed to work efficiently with large files without
    freezing the Haskell runtime. Here's a step-by-step explanation of how it
    works:

    1. We import necessary modules: `Crypto.Hash.BLAKE3` for the BLAKE3 hash
       function, `Data.ByteString` for efficient byte handling, and `System.IO`
       for file operations.

    2. The function takes a `FilePath` as input and returns an `IO ByteString`
       containing the hash.

    3. We define a `chunkSize` of 8192 bytes (8KB) for reading the file in
       manageable chunks.

    4. The `withFile` function is used to safely open and close the file,
       ensuring proper resource management.

    5. Inside the file handling function, we define a recursive `loop` that
       reads the file in chunks:
       - It reads a chunk of the file using `BS.hGet`.
       - If the chunk is empty (end of file), it finalizes and returns the
         hash.
       - Otherwise, it updates the hash context with the new chunk and
         continues the loop.

    6. The loop starts with `BLAKE3.init` to create the initial hash context.

    7. By using lazy evaluation (`$!`), we ensure that the hash context is
       strictly evaluated in each iteration, preventing memory buildup.

    This implementation is memory-efficient and can handle very large files
    without issues, as it processes the file in small chunks rather than
    loading it entirely into memory.

My remark:

    * This solution is already pretty good.
    * The explanation is also useful for people new to Haskell
      or this type of task.
    * Some explanations are subtly wrong, e.g. `$!` is the
      _opposite_ of lazy evaluation, and the sentence
      is contradicting itself.
    * It mainly got the imported module name wrong
      (should be `import BLAKE3` from
      https://hackage.haskell.org/package/blake3).
      Let's see if it fixes it when I tell it what I'd observe
      when trying to compile the code.
      A simple Google search for "haskell blake3" should point out the correct name.

Corrective prompt:

    The mentioned `Crypto.Hash.BLAKE3` module doesn't exist as a Haskell library.

Output:

    import Crypto.Hash (hash, Blake2b_512, Digest)
    import qualified Data.ByteString as BS
    import qualified Data.ByteString.Lazy as LBS
    import System.IO (withFile, IOMode(ReadMode))

    hashFileBLAKE2b :: FilePath -> IO (Digest Blake2b_512)
    hashFileBLAKE2b filePath = do
      let chunkSize = 8192  -- 8KB chunks
      withFile filePath ReadMode $ \handle -> do
        let loop acc = do
              chunk <- BS.hGet handle chunkSize
              if BS.null chunk
                then return $ hash (LBS.fromChunks acc)
                else loop (chunk : acc)
        loop []

My observation:

    * I asked for BLAKE3, but now it implemented BLAKE2B.
    * The solution is very wrong.
      It splits the file into _reversed_ chunks and then hashes them.
      The error is subtle and will be hard to debug.

So I'm quite sure I wouldn't allow anybody to build my "product" with such tools yet.

But it certainly is fun and there's definitely some usefulness in there, especially for learning general concepts that are well understood.

I guess in the end it's this: Programmers don't need to "roughly get it right" (which is what current tools do well) when it comes to products. They need to get it /precisely/ right.

Comments on HN are made by all sorts of people, some are geniuses that contribute authentically to threads that interest them, and some others operate or invest in glorified template generators that they use to write propaganda about their own products in order to fake popularity and consensus. If one believes everyone else is a genius that uses whichever product, then whoever's not on that train is already obsolete. The nature and style of top comments on LLM related (last years news) threads often reads in such a predictible and distinguishable way from other arbitrary threads that it seems a bit... robotic. Same thing on Reddit.