HackerTrans
TopNewTrendsCommentsPastAskShowJobs

wek

no profile record

Submissions

Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering

arxiv.org
2 points·by wek·14 days ago·0 comments

Configuring Agentic AI Coding Tools: An Exploratory Study

arxiv.org
3 points·by wek·last month·0 comments

Building the harness around our coding agents. Eight failure modes and pillars

nimbalyst.com
3 points·by wek·2 months ago·0 comments

Constraint Decay: The Fragility of LLM Agents in Back End Code Generation

arxiv.org
287 points·by wek·2 months ago·197 comments

Show HN: Nimbalyst open source Obsidian, Codex app, and Linear for coding agents

github.com
7 points·by wek·2 months ago·1 comments

[untitled]

1 points·by wek·2 months ago·0 comments

Agyn: A Multi-Agent System for Team-Based Autonomous Software Engineering

arxiv.org
2 points·by wek·3 months ago·0 comments

The Code Agent Orchestra: what makes multi-agent coding work

addyosmani.com
2 points·by wek·3 months ago·1 comments

Managing context in long-run agentic applications

slack.engineering
2 points·by wek·3 months ago·0 comments

Jetbrain's Research: Understanding AI's Impact on Developer Workflows

blog.jetbrains.com
1 points·by wek·3 months ago·0 comments

[untitled]

1 points·by wek·3 months ago·0 comments

Speed at the cost of quality: Study of use of Cursor AI in open source projects (2025)

arxiv.org
148 points·by wek·4 months ago·81 comments

Ask HN: How is your team collaborating while working with coding agents?

3 points·by wek·4 months ago·3 comments

AI is an enchantment, not a level booster

2 points·by wek·4 months ago·0 comments

One plan/spec to rule them all (at least replace lots of docs)

3 points·by wek·4 months ago·0 comments

Workflow to build context for coding agents

3 points·by wek·4 months ago·0 comments

Things I keep reminding myself about while working with AI Agents

2 points·by wek·4 months ago·1 comments

Comprehensive Benchmarking of Agentic Systems Across 104 Real-World Challenges

arxiv.org
1 points·by wek·4 months ago·0 comments

[untitled]

1 points·by wek·4 months ago·0 comments

Local WYSIWYG Markdown, mockup, data model editor powered by Claude Code

nimbalyst.com
29 points·by wek·7 months ago·5 comments

comments

wek
·12 days ago·discuss
[dead]
wek
·2 months ago·discuss
[flagged]
wek
·2 months ago·discuss
The article is correct to emphasize the importance of definition and that this can be a bottleneck. But it is incorrect to show the layered documentation and development lines taking just as long as they did pre-coding-agents.

Our team is coding much much faster at high quality then we were before coding agents. As this commenter says, if you empower individuals and small teams to define, document and they set up good practices and harnesses, they can accelerate dramatically.
wek
·2 months ago·discuss
Well said. It is so much better for when the human can see what the LLM has changed and iterate on it with the LLM, making their own changes. Markdown is better for that.
wek
·2 months ago·discuss
I kind of felt the same way reading the article! It felt so unusual to encounter someone who is both smart and humble and willing to admit they were learning. And I was happy to encounter it and sad that I was so surprised by it.
wek
·2 months ago·discuss
Congratulations! I think that a lot of the value will be in the judgement of the maintainer about the marginal next feature (and saying no to all those other features) ... if software is a stream then the value is in what gets into the stream. That is an AI resistant value and if you can provide it for your project.
wek
·2 months ago·discuss
What an excellent article by a smart, humble, still-learning person!

Favorite quote:" There are a whole bunch of reasons I’m not scared that my career as a software engineer is over now that computers can write their own code, partly because these things are amplifiers of existing experience. If you know what you’re doing, you can run so much faster with them. [...]

I’m constantly reminded as I work with these tools how hard the thing that we do is. Producing software is a ferociously difficult thing to do. And you could give me all of the AI tools in the world and what we’re trying to achieve here is still really difficult. [...]"
wek
·2 months ago·discuss
And as of today Nimbalyst is open source!
wek
·2 months ago·discuss
This is on our wish list for a custom extension. Many users have asked for it. If someone in the community wants to take a crack at it....
wek
·2 months ago·discuss
Thanks! A good way to learn the platform is by building an extension.
wek
·3 months ago·discuss
I use Nano Banana all the time and this seems like a step up
wek
·3 months ago·discuss
I agree. Why would they not keep the $20 plan as a gateway drug?
wek
·3 months ago·discuss
What are the implications of this for Cursor being model agnostic?
wek
·3 months ago·discuss
Consider Nimbalyst, its a free visual workspace for Claude Code and Codex that has visual editing of markdown, mockups, diagrams, code with your agents with WYSYWIG diffs as well as task management and kanban session management tied into your agents. Its got a files/plan/editing mode and an agent/sessions mode.
wek
·3 months ago·discuss
this is true of AI in general
wek
·3 months ago·discuss
so cool. This whole mission makes me feel like a kid again.
wek
·3 months ago·discuss
This is cool. Simple prototype. Is it dependent on lighting ... what if you are outside or backlit or glare etc...?
wek
·3 months ago·discuss
Amaze. Amaze. Thank you for sharing.
wek
·4 months ago·discuss
I'm concerned about these laws and their implications for privacy, but as a parent, I'm not sure what you mean to say parents should parent. How? What should the parent do? How would you recommend a parent protect a 13 year old who spends their time in their room and out with their friends on their phones?
wek
·4 months ago·discuss
Thanks for sharing. I appreciated getting different perspectives. I come down on ultimately this is lying and I don't see how lying to oneself is going to be helpful.