HNHacker News
TopNewBestAskShowJobs

sneilan1

283 karma · joined May 6, 2019

https://seanneilan.com/
submissionscomments
sneilan1··on Asus Ascent GX10
Does anyone have any information on how much this will cost? Or is it one of those products where if you have to ask you can't afford it.
sneilan1··on Kafka is Fast – I'll use Postgres
You know what, you have a very good point. I'll give this another shot. Maybe it can be fast enough and I can just isolate the orm queries to some kind of repository pattern so I'm not testing sql queries over and over.
sneilan1··on Kafka is Fast – I'll use Postgres
This is the way.
sneilan1··on Kafka is Fast – I'll use Postgres
The other unspoken aspect of this is with agentic coding, the ability to have the ai also test queries quickly is very valuable. In a non-agentic coding setup, mongomock would not be as useful.
sneilan1··on Kafka is Fast – I'll use Postgres
Not familiar with OrioleDB. I’ll look it up. May I ask how this helps? Just curious.
sneilan1··on Kafka is Fast – I'll use Postgres
True but if you wind up using parts of postgres that aren't supported by sqlite then it's harder to use sqlite. I agree however, if I was able to just use sqlite, I would do that instead. But I'm using a lot of postgres extensions & fields that don't have direct mappings to sqlite.

Otherwise SQLITE :)

sneilan1··on Kafka is Fast – I'll use Postgres
Because I can read the mongomock library and understand exactly what it's doing. And mongo's aggregation pipelines are easier to model than sql queries in code. Sure, it's possible to run into an edge case but for a lot of general queries for filtering & aggregation, it's just fine.
sneilan1··on Kafka is Fast – I'll use Postgres
True but then my tests take longer to run. I really like having very fast tests. And then my tests have to make local network calls to a postgres server. I like my tests isolated.
sneilan1··on Kafka is Fast – I'll use Postgres
Yes, performance can be a big issue with postgres. And vertical scaling can really put a damper on things when you have a major traffic hit. Using it for kafka is misunderstanding the one of the great uses of kafka which is to help deal with traffic bursts. All of a sudden your postgres server is overwhelmed and the kafka server would be fine.
sneilan1··on Kafka is Fast – I'll use Postgres
I'm starting to like mongodb a lot more given the python library mongomock. I find it wonderful to create tests that run my queries against mongo in code before I deploy them. Yes, mongo has a lot of quirks and you have to know aws networking to set it up with your vpc so you don't get nailed with egress costs. And it's not the same query patterns and some queries are harder and you have maintain your own schemas. But the ability to test mongo code with mongomock w/o having to run your own mongo server is SO VALUABLE. And yes, there are edge cases with mongomock not supporting something but the library is open source and pretty easy to modify. And it fails loudly which is super helpful. So if something is not supported you'll know. Maybe you might find a real nasty feature that's hard to implement but then just use a repository pattern like you would for testing postgres code in your application.

https://github.com/mongomock/mongomock Extrapolating from my personal usage of this library to others, I'm starting to think that mongodb's 25 billion dollar valuation is partially based on this open source package :)

sneilan1··on Show HN: Write It Down – Personal finance tracker
This is awesome! I’m already integrated into TillerHQ. Apart from price, do you have any differentiators that make it take less time for auto categorizing? Tiller doesn’t have any built in AI tools for auto categorization so I had to roll my own.

Also I’m extremely skeptical of your pricing. $5 one time seems too good to be true.

sneilan1··on Claude Sonnet 4.5
https://app.grantpuma.com/

It's a startup for finding grants. We have california state, federal, non-profit and california city/county grants. My landing page absolutely sucks but if you sign up / upload some papers or make some search cards you'll like the experience.

I'm very excited to try out the new Qwen XL that came out recently for visual design. I could really use some better communication to users of the capabilities of the platform.

sneilan1··on Claude Sonnet 4.5
Same. I haven't written any code by hand in some time. Oh well. I guess I'm just doing it wrong.
sneilan1··on Instant Checkout and the Agentic Commerce Protocol
I love the little synthesizer in the square in the footer :) What an awesome easter egg..
sneilan1··on Getting AI to work in complex codebases
True, if you are in a big company with lots of people, you won't benefit much from the improved throughput of agentic coding.

A greenfield startup however with agentic coding in it's DNA will be able to run loops around a big company with lots of human bottlenecks.

The question becomes, will greenfield startups, doing agentic coding from the ground up, replace big companies with these human bottlenecks like you describe?

What does a startup, built using agentic coding with proper engineering practices, look like when it becomes a big corporation & succeeds?

sneilan1··on Getting AI to work in complex codebases
It’s not necessarily faster to do this for a single task. But it’s faster when you can do 2-3 tasks at the same time. Agentic coding increases throughout.
sneilan1··on Trevor Milton's Nikola case dropped by SEC following Trump pardon
It's not skills that got him ahead. It's the connections to the "right" people that can be benefit him the most.
sneilan1··on API, Claude.ai, and Console services impacted [resolved]
SHODAN
sneilan1··on 996
This is just rage bait.
sneilan1··on We put a coding agent in a while loop
Yes, thank you for being one of the few people to appreciate this experiment. Sure, maybe it's a little wonky right now but I'm glad someone took this risk and tried the "jesus take the wheel" move with Claude Code.

We, as human beings, keep trying this and eventually figure out how to get models to build more and more of the software stack for us and professionally!

sneilan1··on AI is predominantly replacing outsourced, offshore workers
They do a lot of work but a lot of market research can be automated too.
sneilan1··on Cerebras Code
Oh so this is not an integrated command line tool like Claude code? I assumed it was something where Cerebras released a decent prompt and command line agent setup. A lot of the value of Claude Code is how polished it is and how much work went into the prompt design.
sneilan1··on Cerebras Code
Claude code weekly limits are hard to distinguish. It's not easy to understand their usage limits. I've found when I run into too much opus usage, I switch to sonnet but I've never ran into a usage limit with sonnet 4 yet.
sneilan1··on Cerebras Code
1,000 messages per day should be plenty as a daily development driver. I use claude code sonnet 4 exclusively and I do not send more than 1,000 messages per day. However, that is my current understanding. I am certainly not pressing enter 1,000 times! Maybe there are more messages being sent under the hood that I do not realize?
sneilan1··on Cerebras Code
I'm so excited to see a real competitor to Claude Code! Gemini CLI, while decent, does not have a $200/month pricing model and they charge per API access - Codex is the same. I'm trying to get into the https://cloud.cerebras.ai/ to try the $50/month plan but I can't even get in.
sneilan1··on Cerebras launches Qwen3-235B, achieving 1.5k tokens per second
You can copy paste my entire previous comment into Claude code and along with your question and ask for suggestions. I’m sure it could create an MCP server for you.
sneilan1··on Cerebras launches Qwen3-235B, achieving 1.5k tokens per second
So I installed litellm proxy, pointed it at the new Cerebras API with Qwen-235B and hooked up Aider to litellm. This is not as good as claude code yet but it's so much faster. I even tried using the leaked claude code prompt into Aider but it doesn't do what I expect. Still worth trying but I learned that claude code's prompt is very specific to claude. I think this is very promising however! Aider basically spat out a bunch of text, installed some stuff, made some web calls & exited. WAS REALLY FAST LOL.

you can repeat my experiment quickly with the following>

config.yaml for litellm ``` model_list: - model_name: qwen3-235b litellm_params: model: cerebras/qwen-3-235b-a22b api_key: os.environ/CEREBRAS_API_KEY api_base: https://api.cerebras.ai/v1 ```

run litellm with ``` litellm --config config.yaml --port 4000 --debug ``` (may need to install litellm[proxy])

start aider with ``` aider --model cerebras/qwen-3-235b-a22b --openai-api-base http://localhost:4000 --openai-api-key fake-key --no-show-model-warnings --auto-commits --system-file ./prompt.txt --yes ```

install whatever you need with pip etc. prompt.txt contains the leaked claude code prompt which you can find yourself on the internet.

sneilan1··on Workers at Snopes.com win voluntary recognition
This is incredible! Bravo! Good for you guys!!!
sneilan1··on Anthropic tightens usage limits for Claude Code without telling users
yes. https://app.grantpuma.com/
sneilan1··on Anthropic tightens usage limits for Claude Code without telling users
As a follow-up, I've gotten much much faster at modeling code in my mind and directly translating it into prompts. It really changes how you code! For each task, I'm extremely specific about what I want and depending on how closely claude does what I want, I change my specificity. Sometimes like with the lambda function, I can be high level and with my react.js codebase, due to it's lack of types (I know...) needs extra attention.

To be effective with agentic coding, you have to know when to go high level and low level. And have to accept that sometimes agentic coders need a lot of help! It all depends on how much context you give it.

← PreviousPage 2 of 5Next →