Maybe I'll try that myself, because it feels like it could be a great source of improvements. It would be really useful to see adaptive per-token sampling as an additional decode-only baseline.

It was a travesty that the UK government let it be sold, admittedly.

Comments URL: https://news.ycombinator.com/item?id=47035215

Points: 1

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=46999339

Points: 2

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=46900632

Points: 2

# Comments: 0

Look at the 'Product Engineer' roles we are seeing spreading in forward-thinking startups and scaleups.

That's the future of SWE I think. SWEs take on more PM and design responsibilities as part of the existing role.

A. Using a role prompt to configure a single function's scope ("you are a code reviewer, focus on X") - totally reasonable, leverages training

B. Building an elaborate multi-agent orchestration layer with hand-offs, coordination protocols, and framework abstractions on top of that

I'm not arguing against A. I'm arguing that B often adds complexity without proportional benefit, especially as models get better at long-context reasoning.

Fairly recent research (arXiv May 2025: "Single-agent or Multi-agent Systems?" - https://arxiv.org/abs/2505.18286) found that MAS benefits over single-agent diminish as LLM capabilities improve. The constraints that motivated swarm architectures are being outpaced by model improvements. I admit the field is moving fast, but the direction of travel appears to be that the better the models get, the simpler your abstractions need to be.

So yes, use roles. But maybe don't reach for a framework to orchestrate a PM handing off to an Engineer handing off to QA when a single context with scoped instructions would do.

"Comprehensively disproven" was too strong - should have said "evidence suggests the effect is largely random." There's also Gupta et al. 2024 (arxiv.org/abs/2408.08631) with similar findings if you want more data points.

https://arxiv.org/abs/2311.10054

Key findings:

-Tested 162 personas across 6 types of interpersonal relationships and 8 domains of expertise, with 4 LLM families and 2,410 factual questions

-Adding personas in system prompts does not improve model performance compared to the control setting where no persona is added

-Automatically identifying the best persona is challenging, with predictions often performing no better than random selection

-While adding a persona may lead to performance gains in certain settings, the effect of each persona can be largely random

Fun piece of trivia - the paper was originally designed to prove the opposite result (that personas make LLMs better). They revised it when they saw the data completely disproved their original hypothesis.

Agents are stateless functions with a limited heap (context window) that degrades in quality as it fills. Once you see it that way, the whole swarm paradigm is just function scoping and memory management cosplaying as an org chart:

Agent = function

Role = scope constraints

Context window = local memory

Shared state file = global state

Orchestration = control flow

The solution isn't assigning human-like roles to stateless functions. It's shared state (a markdown file) and clear constraints.

Though you're right that there's no I in team. There is one in AI though, which probably tells us something.

Comments URL: https://news.ycombinator.com/item?id=46668237

Points: 1

# Comments: 0

If I was a junior today, I'd be studying business impact, effective communication, project management, skills that were previously something you could get away with under-indexing on until senior+.

In my experience, if you just ask an LLM to write tests, it'll write you a ton of boilerplate happy path tests that aren't wrong, per se, they're just pointless (one fun one in react is 'the component renders').

How do you plan to handle this?