tlonny

I much prefer cursor paginated API requests vs. webhooks. The obvious downside being that in order to not get 429'd you need a respectable poll frequency - meaning you lose reactivity to new events.

Thus I think webhooks still have a place - but as a simple "poke" that can be sent to the client to tell them something has changed - supplementing a default low frequency polling interval.

This gives us the best of both worlds:

1. No need to bother de-duping/retrying pokes - if you miss a webhook you will shortly recover anyway when you next poll. 2. No need for any local-specific tunnelling/tooling - the local app will work just fine with the default poll interval. 3. No need to keep a connection live for each client. 4. All the good stuff OP mentioned in his blog post.

As I understand it, anything publicly viewable is free to be scraped without issue.

If you scrape stuff behind a sign-up, you potentially open yourself up to being sued for breach of ToS.

Now I'm sure the Chinese labs don't give a rats arse about that threat, but I imagine it stops the likes of Google, OAI, Anthropic from scraping and instead forces them to purchase the data.

I would argue that my proposed flow is far more convenient. I don’t have to sign up, enter payment details and I can interface in plain English.

Not to disparage, but I wrote:

"Using the attached image as a stencil/background - please generate a QR code for https://XXX"

into ChatGPT and got something valid that looks similar in style to your offering.

I think the age of trying to wrap a highly focused AI task in a SaaS has come and gone.

Trying to polish a bunch of my projects I've worked on over the years but never had the cojones to release to the wider world:

Hallways (https://hallways.lonnycorp.com) - a web browser for 3D spaces, where instead of hyperlinks you have portals that you can seamlessly walk through

LonnyMQ (https://lonnymq.lonnycorp.com) - a performant, production-ready TS PostgreSQL message queue library and accompanying blog post that walks through its design (of which I'm quite proud of)

I think _some_ but not _too much_ typechecking is the sweet spot for LLMs.

Without any typechecking, LLMs obviously find it harder to work agentically and validate their work.

With too much typechecking (I'm looking at you, rust), I've found agents get themselves stuck in local "architectural minima" and end up doing insane shit to mitigate ownership/borrow-checker issues inherent in the design they ended up with.

That said, if you're hands-on I think rust is a fantastic language for pairing with an LLM.

Presumably because API keys are n bytes of random data vs. a shitty user-generated password we don’t have to bother using a salt + can use something cheap to compute like SHA256 vs. a multi-round bcrypt-like?

Bugginess in the Claude Code CLI is the reason I switched from Claude Max to Codex Pro.

I experienced:

- rendering glitches

- replaying of old messages

- mixing up message origin (as seen here)

- generally very sluggish performance

Given how revolutionary Opus is, its crazy to me that they could trip up on something as trivial as a CLI chat app - yet here we are...

I assume Claude Code is the result of aggressively dog-fooding the idea that everything can be built top-down with vibe-coding - but I'm not sure the models/approach is quite there yet...

how does it work?

Indeed - the future is RL meet-ups and small, intimate online communities.

Perhaps not the worst thing in the world?

I’d love something like this implemented for email.

Sending an unsolicited email to a random person X requires you to pay a small toll (something like 50p).

Subsequent emails can then be sent for free - however person X can “revoke” your access any time necessitating a further toll payment.

You would of course be able to pre-authorise friends/family/transactional emails from various services that you’ve signed up for.

This would nuke spam economics and be minimally disruptive for other use cases of email IMO…

HN may not be “mainstream” but it is certainly _very_ vulnerable to bot spam given the topics discussed and the make-up of the audience.

You can already see it happening now - at least the bots that write like vanilla Claude/ChatGPT. Presumably there is a much larger hidden cohort of bots that are instructed to talk more naturally and thus are better adept at flying under the radar…

Look at his other comments - its textbook LLM slop. Its a fucking tragedy that people are letting their OpenClaws loose on HN but I can't say I'm surprised. I desperately need to find a good network of developers because I think the writing is on the wall for message boards like these...

Repugnant.

Doors - A first person, exploration game/experience that I built from scratch.

Doors lets you explore URL addressable 3D rooms that link together seamlessly via portals. The idea is that people would upload rooms to the internet (to github, S3, whatever) and connect them together to form one giant inter-connected space that would be a real trip to explore.

Right now rooms consistent of a: - Manifest JSON file that points to requisite resources and configures portals - An optional skybox - An optional background music track - A .vox file containing voxel terrain data

Here is a video I filmed on my phone of flying through a room that links back to itself: https://www.youtube.com/shorts/BCqOYTISS_k

Portals can be arbitrarily sized and everything is prefetched/loaded seamlessly in the background.

I'm nearly done - I just need to add in a very lightweight interface and give the code a bit of a spit shine (I will open source it - so I want it to look pretty)

EDIT: As an aside, I finally decided to give this whole Claude Code thing a go - I purchased a max subscription and I'm trying to write as little code as possible. I certainly wouldn't call what I'm doing "vibe-coding". I discuss a feature in plan mode (incl. how I want to implement it in high level terms) iterate on the plan 2-3 times until I'm satisfied and then let it rip. I'm both very impressed and quite frightened by the productivity boost...

0.0005%*

If this is somewhat common for games, could one create a virtual fs with FUSE that dedupes using via content-defined chunking and install games there?

I feel like writes would probably be quite painful, but with game assets are essentially write-once read-forever so not the end of the world?

As an aside, its messed up that people with expensive SSDs are unnecessarily paying this storage tax. Just feels lazy...

Also check airline miles haven’t gone missing.

A friend of mine recently had his BA account compromised, all his Avios stolen and he was none the wiser after receiving about 60 emails a minute

The rank disrespect of somebody asking you to review something they haven't even looked at is eye watering.

I feel like AI-induced brain-rot of engineers is inevitable. Unless we see AI leapfrog into something close to AGI in the future (certainly not ruling this out), I think there will be very lucrative careers available to engineers who can maintain a balanced relationship with AI.

To quote Mean Girls: "Stop trying to make Doxbridge happen".

I totally agree.

Isaac, if you're reading this - stop sending me PDFs generated by Perplexity!

> Gmail is so big that when Outlook, Apple Mail, and even Thunderbird connect to it, they do an OAuth exchange and then talk over a proprietary protocol.

Can you elaborate? Anything I can read on this?

The product (from the perspective of the consumer) _is_ relatively straightforward IMO. What isn't straightforward is accurately modelling the credit risk of the bonds when this class of debt is securitized (the meat of this article). Thus I don't think understanding this article is a prerequisite for making educated decisions re: BNPL.

If AI is what stops me having this exchange with Siri 50% of the time:

> Hey Siri, please play Emerald Rush, by Jon Hopkins on Youtube Music.

> Sorry, you'll need to continue in Youtube Music.

Then yes - I want AI on my phone

AI "polishing" tools are essentially a form of anti-compression. Lets take some information represented concisely and needlessly pad it with formalities and waffle so it appears more "professional" (whilst also throwing away useful "metadata" like message tone).

No doubt the recipient will also be using some form of AI summarization that strips away all that added "polish" - making the whole exercise entirely redundant!

It just feels absurd.

Given the size of the training data - I don’t think it would economical to validate all training data with high-end LLM models.

> For example, CA schools have to publish statistics on suspensions and expulsions.

Are there actionable consequences if these numbers get too high? If they're merely published, as a parent, I would see high numbers as a positive signal if anything...

I'm pretty sure you pee it out too.

For some terminal patients, there are types of pain that no amount of morphine or money can fix.

I'm thankful to know that when its my time to go, I'll have the choice to skip enduring several days of torture should I wish.

You can cross wherever and whenever is safe to do so. If traffic conditions don’t facilitate this, pedestrian crossings provide guaranteed crossing points where pedestrians have right of way.