News for hackers. Stuff that matters.

SerCe

Re:Write some software, give it away for free on Tuesday May 05, 2026 @06:51PM (#48029822)
Or don't. I've done both, published OSS projects and sold some software. The level of entitlement in some comments I received on the OSS side was pretty crazy at times. While with the paid software, all of the interactions I had were so much more constructive. YMMV, but willingness to pay is a great filter.
Re:Many SWE-bench-Passing PRs would not be merged on Thursday March 12, 2026 @03:33AM (#47347602)
While I somewhat understand the impact on the craft, the agents have allowed me to work on the projects that I would never have had enough time to work on otherwise.
Re:Many SWE-bench-Passing PRs would not be merged on Thursday March 12, 2026 @03:29AM (#47347576)
> Do you have any examples or resources that worked well for you?

Using this particular example, if you simply paste the exact code into the prompt, the model should able to reproduce it. Now, you can start removing the bits and see how much you can remove from the prompt, e.g. simplify it to pseudocode, etc. Then you can push it further and try to switch from the pseudocode to the architecture, etc.

That way, you'll start from something that's working and work backwards rather than trying to get there in the absence of a clear path.

Re:Many SWE-bench-Passing PRs would not be merged on Thursday March 12, 2026 @12:47AM (#47346565)
If you've got some time, I highly recommend going through the exercise of trying to change the prompt in a way that would produce code similar to what you've achieved manually. Doing a similar exercise really helps to improve agent prompting skills, as it shows how changing parts of the prompt influences the result.
What's incredibly ironic is that research labs are releasing the most advanced hacking toolkit ever known, and cybersecurity defence stocks are going down as a result somehow. There’s no logic in the stock markets.
Re:Evaluating AGENTS.md: are they helpful for coding agents? on Tuesday February 17, 2026 @06:59AM (#47046571)
In Theory There Is No Difference Between Theory and Practice, While In Practice There Is.

In large projects, having a specific AGENTS.md makes the difference between the agent spending half of its context window searching for the right commands, navigating the repo, understanding what is what, etc., and being extremely useful. The larger the repository, the more things it needs to be aware of and the more important the AGENTS.md is. At least that's what I have observed in practice.

Older »