HNHacker News
TopNewBestAskShowJobs

siquick

2,417 karma · joined May 10, 2014

submissionscomments
siquick··on Mistral OCR 3
That links gives an error and so does https://openrouter.ai/docs/guides/overview/multimodal/pdfs
siquick··on How elites could shape mass preferences as AI reduces persuasion costs
> Personally, I think a big driver of this belief is a tendency in the West to not challenge each other's views or hold each other accountable - "don't talk politics at Thanksgiving" sort of thing

We’re in such a “you’re either with us or against us” phase of politics that a discussion with the “other team” is difficult.

Combine that with people adopting political viewpoints as a big part of their personality and any disagreement is seen as a personal attack.

siquick··on (New Update) Back2Back: Deep Research for Music Discovery
Suggestion - don’t require the latest iOS26. A lot of people aren’t installing it as it’s not great. You’re missing out on a lot of users and unless you require a specific feature that only 26 has then it’s no necessary to mandate 26.
siquick··on PlanetScale for Postgres is now GA
This is the thought I always come back to with the non-big cloud services. It’s pretty much always been mandatory at non-startups to have all databases to be hidden away from the wider internet.
siquick··on AirPods live translation blocked for EU users with EU Apple accounts
I’d rather not have my conversations recorded and sent to a third party, without my knowledge, so that your experience could be SO much better.
siquick··on Show HN: Building a web search engine from scratch with 3B neural embeddings
Brilliant write up - learnt a lot.
siquick··on ChatGPT's enterprise success against Copilot fuels OpenAI/Microsoft rivalry
That was epic. The type of email we all dread to receive at work. Can’t fault Bill for his detail though, most of those kind of emails are “website slow, make fast”.
siquick··on OpenAI for Countries
This sounds like the sales pitch for the AI Prime Ministers in Ray Naylers excellent new book, Where The Axe is Buried.

https://us.macmillan.com/books/9780374615369/wheretheaxeisbu...

siquick··on The Friendship Recession: The lost art of connecting
I’ve got a feeling that if you looked at the average persons average internet usage it would not be full of interesting stuff.
siquick··on Why Kagi launched "no use, no pay"
I’ve been paying for Kagi for about 18 months and it’s pretty much the only subscription I have that it’s never crossed my mind to cancel it.
siquick··on Literate Development: AI-Enhanced Software Engineering
My strategy is generally to have a back and forward on the requirements with the LLM for 3/4 prompts, then get it write a summary, and then a plan. Then get it to convert the plan to a low level todo list and write it to TODO.md.

Then I get it to go through each section of the todo list and check each item off as it completes it. Generally results in completed tasks that stay on track but also means that I can stop half way through and go back to the tasks without having to prompt from the start again.

siquick··on Testing the latest AI tools for prototyping and building simple websites
Cursor has gone to the next level with Gemini 2.5. The reasons it gives for what it’s doing are well thought through and far more in context.

Gemini seems to now advise you when you’re telling it to do something that may not make sense - first time I’ve really seen a non-Yes Man LLM. It’s more like a Yes-but-are-you-sure man.

siquick··on I use Cursor daily - here's how I avoid the garbage parts
Cursor in agent mode + Sonnet 3.7 love nothing better than rewriting half your codebase to fix one small bug in a component.

I've stopped using agent unless its for a POC where I just want to test an assumption. Applying each step takes a bit more time but means less rogue behaviour and better long term results IME.

siquick··on BM25 in PostgreSQL
Can this be used on AWS RDS? I’ve seen a few things like this that would be great to use but without RDS support they’re unusable for us.
siquick··on Launch HN: A0.dev (YC W25) – React Native App Generator
Building a RN app without any features (authentication, notifications) is easy - but adding those features and then navigating the outside-app ecosystem isn’t. It’s definitely not like the web.
siquick··on Ingesting PDFs and why Gemini 2.0 changes everything
Strange that LlamaParse is mentioned in the pricing table but not the results. We’ve used them to process a lot of pages and it’s been excellent each time.
siquick··on A standards-first web framework
> The core issue, however, is the inability to participate in the actual craft. Design decisions are buried in React components with cryptic expressions like flex items-center shadow-lg p-6 hover:bg-gray-50 dark:bg-gray-800 py-[calc(theme(spacing[2.5])-1px)]

Give me Tailwind standardised utility classes over having to search through the codebase to find what a dev 6 years ago called a CSS class.

siquick··on GPT-4o with scheduled tasks (jawbone) is available in beta
You can’t edit on iOS either
siquick··on Matt Mullenweg deactivates WordPress accounts of contributors planning a fork
> Django with plugins could be made to look like and work similar to Wordpress I bet.

https://wagtail.org/ is a solid CMS

siquick··on Little Snitch: Network Monitor and Application Firewall for macOS
What was the library?
siquick··on United Health CEO Decries "Aggressive" Media Coverage in Leaked Recording
For some reason my brain thought you meant Falling Down with Michael Douglas (which also feels pretty apt for the situation)

https://www.imdb.com/title/tt0106856/

siquick··on Amazon Nova
Is there any difference in latency when calling models via Bedrock vs calling the providers APIs directly?
siquick··on Show HN: FastGraphRAG – Better RAG using good old PageRank
> 1. Lexical search with BM25 alone gives you very relevant results if you can do some work during ingestion time with an LLM

Can you expand on what the LLM work here is and it’s purpose?

> 3. Hypothetical answer generation from a query using an LLM, and then using that hypothetical answer to query for embeddings works really well.

Interesting idea, going to add to our experiments. Thanks.

siquick··on Show HN: The App I Built to Help Manage My Diabetes
First up - awesome work.

Having been through the year long build of a similar app for another health condition here’s some thoughts focusing on the GenAI side of things:

- What’s the source of the responses? Is this a RAG system or straight-to-LLM?? We have an ever-growing huge repo of domain expert written content which is the source for our RAG system. It’s far easier to control potential misinformation with a well set up RAG and some tight prompting/guardrails.

- What verification do you have that the responses are correct? We have a group of 50 highly experienced experts in the field who constantly vet the responses to our synthetic set questions and it was eye opening how often our “looks good to me” analysis was off at the beginning.

- The main reason for this questions was that your responses are going to be wrong sometimes, what legal protection do you have? Disclaimers, terms of use at absolute minimum. Who is liable if the answer is wrong? Just presume someone is going to be very upset if your response gives them bunk info.

Either way - great work.

siquick··on Kagi Update: AI Image Filter for Search Results
When deepfake images of MicolashKyoka start clogging up image searches you may wish for this feature.
siquick··on The other British invasion: how UK lingo conquered the US
I’ve lived in Australia for nearly 15 years and still say “swimming costume” - the locals ridicule me and call me for posh for not saying “bathers”.
siquick··on What Excessive Screen Time Does to the Adult Brain
This is great, thanks.
siquick··on What excessive screen time does to the adult brain
I try and avoid screens before sleep but also use a Kindle for reading before sleeping - wondering if the e-ink displays count as screen time in studies like this?
siquick··on Orion, our first true augmented reality glasses
Staring at your phone > unconsciously staring at an increasingly uncomfortable person trying to enjoy a quiet cup of coffee
siquick··on Orion, our first true augmented reality glasses
I don’t know a single person who is interested in anything like this, including massive gadgets nerds. Who’s the target market? The Verge reporters?
← PreviousPage 2 of 30Next →