Viewing profile — jbergqvist

Doesn't this whole argument fall apart if we consider iteration over time? Sure, the initial implementation might be uncoordinated, but once the subagents have implemented it, what…

"Helped build itself" is a bit of a stretch here, it makes it sound as if the model was doing lasting self-improvements. What the article describes is that the model was able to tw…

In my experience, one reason for unnecessarily complex solutions during vibe coding is the incremental work pattern. Most users don't spend much time designing the solution, but in…

When I want to solve a new problem with an agent, I always ask it to search broadly for prior work in the given area online, and then analyze if we can build our solution using it …

Limit access to whatever their project requires. The difference is that human interns have some common sense and won't suddenly be hijacked by a hidden message they stumble upon wh…

This works well for vibecoding on a codebase in isolation, which to be fair is what the author is addressing. I don’t think it solves the problems at the current frontier of agent …

Maybe. Personally I find it hard to tell how sincere this is. The cynical take is that this is just an attempt to secure their own position, especially if AI progress slows down an…

Usage limits are more generous and GPT 5.4 is a good model, but yes, UI/UX lags behind Claude Code. Currently I'm especially missing /rewind with code restoration and proper suppor…

NemoClaw is an OpenClaw security wrapper, not a replacement

Not to give Snowflake credit for a design that clearly wasn't a sandbox, but I think it's worth recognizing that they probably added the escape hatch because users find agents with…

I've found that spending most of my time on design before any code gets written makes the biggest difference. The way I think about it: the model has a probability distribution ove…

Does this matter in practice though? By modifying some of the generated code and not taking a solution produced by an LLM end-to-end but borrowing heavily from it, can't a human cl…

I think AGENTS.md will still have a place regardless. There are conventions, design philosophies, and project-specific constraints that can't be inferred from code alone, no matter…

Would have loved to see a more detailed breakdown of performance by task type. The commit metadata is right there, seems straightforward to tag commits as feature vs refactor vs bu…

Producing the most plausible code is literally encoded into the cross entropy loss function and is fundamental to the pre-training. I suppose post training methods like RLVR are su…

This would be my guess too. It can probably be generated synthetically or via agentic rollouts, but high quality long context examples where outputs meaningfully depend on long-ran…

This seems like a win for open source maintainers pressed on time and resources. Whether or not LLMs find novel security risks or just pattern-match known issues, many vulnerabilit…

In a way, isn't this the same old data moat that always existed in AI/ML, but supercharged? Generalist models can now reason over proprietary data as context instead of requiring y…

Very interesting benchmark, excited to see what comes out of this. Considering humans are enourmously more sample efficient compared to today's models, it seems clear there's a lot…

One could also argue that if the developers did that, the market value of the digital item in question would drop. The value that the buyer receives is grounded in the large time i…