HN user

grandimam

80 karma
Posts52
Comments19
View on HN
news.ycombinator.com 2d ago

Ask HN: Are Rust migrations delivering any benefits?

grandimam
4pts4
blog.grandimam.com 11d ago

HackerRank's LLM-Based Hiring Agent

grandimam
1pts0
blog.grandimam.com 11d ago

Inside HackerRank's LLM-based Hiring Agent

grandimam
1pts0
blog.grandimam.com 14d ago

The math that makes senior engineers look like a bad deal

grandimam
2pts0
blog.grandimam.com 27d ago

Repricing of Software Engineering Labor

grandimam
5pts0
news.ycombinator.com 2mo ago

Ask HN: Why hasn't automation testing been disrupted with LLMs?

grandimam
1pts0
news.ycombinator.com 3mo ago

Show HN: Building your first ASGI framework – step-by-step lessons

grandimam
2pts0
github.com 4mo ago

Show HN: Pure Python web framework using free-threaded Python

grandimam
3pts0
github.com 4mo ago

Show HN: A pure Python HTTP Library built on free-threaded Python

grandimam
2pts0
news.ycombinator.com 5mo ago

Tell HN: Thoughts on the Future

grandimam
2pts1
news.ycombinator.com 6mo ago

Ask HN: Would you hire someone who codes only using agents?

grandimam
1pts3
techcrunch.com 7mo ago

ChatGPT Apps

grandimam
1pts2
news.ycombinator.com 7mo ago

Journaling and Prompting

grandimam
1pts0
news.ycombinator.com 7mo ago

Ask HN: What is Fullstack Engineering?

grandimam
2pts1
news.ycombinator.com 7mo ago

Thoughts on Cursor

grandimam
1pts1
news.ycombinator.com 7mo ago

AI-Native vs. Anti-AI Engineers

grandimam
1pts1
news.ycombinator.com 7mo ago

Ask HN: What has been your experience with Agentic Coding?

grandimam
7pts7
docs.qalam.dev 8mo ago

Show HN: Qalam - a CLI that remembers commands

grandimam
1pts1
news.ycombinator.com 8mo ago

Ask HN: Builders vs. Mercenaries – does this distinction make sense?

grandimam
1pts1
news.ycombinator.com 8mo ago

Ask HN: How to orchestrate multi-agent workflows (beyond one-shot prompts)?

grandimam
1pts0
news.ycombinator.com 9mo ago

Ask HN: What would an ideal matchmaking platform look like today?

grandimam
7pts14
news.ycombinator.com 1y ago

Ask HN: Is it okay to stop chasing expertise?

grandimam
5pts7
news.ycombinator.com 1y ago

Ask HN: Using AI daily but not seeing productivity gains – is it just me?

grandimam
23pts41
news.ycombinator.com 1y ago

Ask HN: Anyone else lose interest right after proving an idea works?

grandimam
6pts3
news.ycombinator.com 1y ago

Ask HN: Is Hackers and Painters still relevant today?

grandimam
2pts2
www.ycombinator.com 1y ago

Ask HN: Thoughts on companies hiring autonomous AI agents?

grandimam
1pts0
news.ycombinator.com 1y ago

Tell HN: What CPython Layoffs Taught Me About the Real Value of Expertise

grandimam
7pts2
news.ycombinator.com 1y ago

Ask HN: How do early-stage builders solve the distribution problem in a AI era?

grandimam
1pts0
deepcue.ai 1y ago

Show HN: DeepCue – The Anti-Cluely Tool to Help Detect Interview Fraud

grandimam
1pts0
news.ycombinator.com 1y ago

Ask HN: How do you balance deep technical exploration with shipping the product?

grandimam
1pts2
Kimi Work 2 days ago

Is there an opensource version of such a tool. I would really like a desktop app and use different models instead of a CLI.

Interesting! I wonder how much of this improvement is actually due to Rust. I suspect implementing the same approach in C would produce similar results. The speedup seems hardware-level optimizations than the language itself.

The rewrite itself is amazing, but I don't think folks realise the actual conditions that made it possible. It's not as simple as a company spending ~$160K on tokens.

This was done by someone who has essentially already rewritten Node once. Bun itself is a reimplementation of Node, so the author was walking in knowing exactly what the correct behavior is. And an exhaustive amount of test suite to verifiy the changes?. On top of that, there is a reference from Node and V8 to validate more throughly. So the $160K is simply the price of translating knowledge that already lived in one engineer's head in a newer syntax.

I have always found similarities between programming and filmmaking.

Programmer being the director and the LLM being the entire apparatus upon which the film/software is built. This became evident to me while doing spec-driven development for a few of my projects where I specify the constraints upon which the software should be build, but have limited control over the performance similar to how a director has limited control over an actor's performance.

Nice writeup. If I am reading it right, the core bug was that two independent paths each generated the per-invocation namespace, and the fix was to generate it once and propagate it to the workers. That reads more like an implementation slip than a design failure. The multi-level naming scheme is sound, it just has to be computed in exactly one place.

The part I would actually love more detail on is the agent side. How are you orchestrating agents to fan out the test runs?

I agree with some of reasonings in the article especially around agents write behaviors. However, a large portion of this is a consequence of poorly-defined agent roles, and moving away from building deterministic systems.

An agent working on a customer analytics task might issue a join across five tables that has never been issued before, hold the connection while it thinks about the result, then issue a completely different follow-up.

Aren't agents simply automated human persona's? Like, why would an Agent make a join across five tables given that its reasoning is grounded on human-aligned decisions. For eg.

If the agent knows the schema, and is aware of the indexes defined. Then, shouldn't it only work its way through those 'known paths'. Why would you allow the agents to deviate known paths?

I could be wrong, but the idea of ending backend and front end reactivity (or sync) is not a good idea. As far as I understand FE reactivity occurs when there is an action but the backend reactivity doesn’t require an action there could be backend jobs that sync state between two components.

I enjoy building frameworks and libraries for fun, so kudos to you for that. At first glance, BlackSheep seems to combine the aspects of Flask, Django, and FastAPI. However, I’m a bit skeptical about its ability to coexist alongside them. The one feature I believe could drive the success of the next Python framework is the ability to operate in nogil mode.

How is the no-gil performance compared to other languages like - javascript (nodejs), go, rust, and even java? If it's bearable then I believe there is enormous value that could be generated instead of spending time porting to other languages.

Interesting! I was wondering why the author choose Python + Django on the server-side when they could have just used TS + React + NextJS across the stack? On reason is that the author is relying on Celery for background jobs, but is there any performance reasoning for having a completely different backend stack.