Comments URL: https://news.ycombinator.com/item?id=50225790

Points: 5

# Comments: 0

i borrowed the SOUL.md concept from openclaw, but repurposed as TUTOR.md

it uses codex locally so you can use your subscription credits rather than an API key

it's very fun!

Comments URL: https://news.ycombinator.com/item?id=50147861

Points: 5

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=49395147

Points: 2

# Comments: 0

I think it's very different if you have not achieved your life's work yet.

> Time is finite. Desire / drive are not. Solve for X

this is true for me, wouldn't be remotely possible without my wife.

Comments URL: https://news.ycombinator.com/item?id=49321298

Points: 959

# Comments: 768

Kudos to databricks, I also find it interesting that such different companies (Stripe, Ramp, Databricks) are all building the exact same internal tools.

I think building companies is going to look more generic in the future because intelligence is an API now.

It's totally fine if thats what your company is like, but the labs have an unfair advantage.

Comments URL: https://news.ycombinator.com/item?id=48874252

Points: 3

# Comments: 2

You could get to "something that works" rather fast but it took a long time to 1) evaluate other options (maybe before, maybe after), 2) refine it, 3) test it and build confidence around it.

I think your point stands but no one really knows where. The next year or so is going to be everyone trying to figure that out (this is also why we hear a lot of "we need to reinvent github")

Comments URL: https://news.ycombinator.com/item?id=47622875

Points: 2

# Comments: 0

Comments URL: https://news.ycombinator.com/item?id=47607470

Points: 3

# Comments: 0

Our notes:

Sonnet 4.6 feels like a fundamentally different model than Sonnet 4.5, it is much closer to the Opus series in terms of agentic behavior and autonomy.

Autonomy - In our zero-shot app building experiments, Sonnet 4.6 ran up to 3-4x longer than Sonnet 4.5 without intervention, producing functional apps on par in terms of quality to the Opus series. Note that subjectively we found Opus 4.5 and 4.6 are better "designers" than Sonnet 4.6; producing more visually appealing apps from the same prompts.

Planning / Task Decomposition - We found Sonnet 4.6 is very good at decomposing tasks and staying on track during long-running trajectories. It's quite good at ensuring all of the requirements of an input prompt are accounted for, whereas we were often forced to goad sonnet 4.5 into decomposing tasks, Sonnet 4.6 does this naturally.

Exploration - In some of our complex "exploration" tasks (e.g. cloning/remixing an existing website), Sonnet 4.6 often performs on par or better than Opus 4.5 and 4.6. It generally takes longer, and takes more tokens, though we believe this is likely a consequence of our tool-calling setup.

Tool-use - Sonnet 4.6 seems eager to use tools; however, we did find that it struggles with our XML-based custom tool use format (perhaps exclusive to the format we use). We did not have a chance to assess with native tool use

Self-verification - Similar to Opus 4.5/4.6, Sonnet 4.6 has a proclivity for verifying it's work.

Prompting - We found Sonnet 4.6 is very sensitive to prompting around thinking, planning, and task decomposition. Our prompt built for sonnet 4.5 has a tendency to push sonnet 4.6 into incredibly long thinking and planning loops. Though we also found it requires significantly less careful and specific instructions for how to approach problems.

How are we thinking about this:

We can't launch this model day 0, it requires more changes to our harness, and we're working on them right now.

But it reminds me a bit of 3.5 to 3.7 --> It's a pretty different model that behaves and responds to instructions in new ways. So it requires more tuning before we can extract its full potential.

Comments URL: https://news.ycombinator.com/item?id=47039941

Points: 3

# Comments: 0

[1] https://x.com/karpathy/status/2017442712388309406