HackerLangs
TopNewTrendsCommentsPastAskShowJobs

david_shi

284 karmajoined 7 ปีที่แล้ว
https://operator.io

you can probably guess my email

Submissions

Daytona is going closed source. Here's why

daytona.io
4 points·by david_shi·14 วันที่ผ่านมา·1 comments

Ask HN: How do you make AI writing usable?

4 points·by david_shi·18 วันที่ผ่านมา·7 comments

Lo and Behold, Reveries of the Connected World (Werner Herzog) [video]

youtube.com
3 points·by david_shi·20 วันที่ผ่านมา·0 comments

Ask HN: Why did you open source your project?

4 points·by david_shi·25 วันที่ผ่านมา·5 comments

Ask HN: What have you built with Claude Managed Agents?

2 points·by david_shi·25 วันที่ผ่านมา·0 comments

Ask HN: How do you solve AI's confused deputy problem?

2 points·by david_shi·เดือนที่แล้ว·1 comments

EinsteinArena: AI agents collaborate and compete on unsolved science problems

einsteinarena.com
2 points·by david_shi·4 เดือนที่ผ่านมา·0 comments

Ask HN: Have you built a public facing agent skill?

1 points·by david_shi·4 เดือนที่ผ่านมา·2 comments

China Restricts OpenClaw as Security Fears Grow

operator.io
4 points·by david_shi·4 เดือนที่ผ่านมา·0 comments

How to Build a Personal Intelligence Agency

operator.io
1 points·by david_shi·4 เดือนที่ผ่านมา·0 comments

Show HN: OpenClaw Swarm as a Service (YC W20)

operator.io
1 points·by david_shi·5 เดือนที่ผ่านมา·1 comments

comments

david_shi
·3 วันที่ผ่านมา·discuss
Is this meant to be read in order?
david_shi
·7 วันที่ผ่านมา·discuss
Is this the story of Johnny Rotten?
david_shi
·16 วันที่ผ่านมา·discuss
Interesting that there's not a single mention of cannabis, perhaps it's more of a musician's choice.
david_shi
·16 วันที่ผ่านมา·discuss
> I believe eval startups can work when they're targeting safety benchmarks specifically.

Are there any examples of successful startups doing this?
david_shi
·18 วันที่ผ่านมา·discuss
Yeah. I'm realizing that the models are strong at drafting the overall shape of the writing but the specific phrases are grating once you've seen it hundreds of time in slop.
david_shi
·18 วันที่ผ่านมา·discuss
Even with the examples, I've found that explicitly pointing out what not to do is moderately helpful if the model is given some time to self-evaluate. I wish this was something that came out of the box though.
david_shi
·18 วันที่ผ่านมา·discuss
Ah this is very helpful. I've been pointing out things that the model does, labeling it, and then adding them into a skill.

The models (Opus, etc) are very good at labeling the pattern when I point it out, but if I don't prompt it beforehand it responds like a host from Westworld.

https://www.youtube.com/watch?v=UTZ6Lvh5gL4
david_shi
·19 วันที่ผ่านมา·discuss
This is a charitable read, but I think that being able to pick from a panoply of models will actually yield much better results in the long run.

The same model that has been post-trained to operate for hours as a Linux admin will be incapable of writing a heartfelt email, but with something like Fugu, you'd get both the Linux admin for driving the browser harness and the smaller writing specialist model for drafting the email itself.
david_shi
·19 วันที่ผ่านมา·discuss
> GLM-5.2 cost a fraction as much. Opus finished in half the time and shipped a cleaner game.

Off topic, but does anyone else instantly pick up on LLMisms like this? It seems like all the models have converged on this style of writing, and improvements aren't really changing it.
david_shi
·19 วันที่ผ่านมา·discuss
It's similar to this: https://openrouter.ai/blog/announcements/fusion-beats-fronti...

Basically, if you combine a bunch of near-frontier models (like GPT 5.5, etc) you can get performance that sometimes surpasses top line models like Claude's Fable.

Sakana seems to have a separate approach using a domain specific model to perform the model routing step.
david_shi
·19 วันที่ผ่านมา·discuss
Their research around building a domain specific model is pretty cool, it's kind of like Karpathy's autoresearch but pointed at deciding the optimal model to use at each step of the inference.

If cost becomes an even bigger problem being able to choose "best performance possible" or "strong but cost effective" will be useful.

https://arxiv.org/pdf/2512.04695
david_shi
·19 วันที่ผ่านมา·discuss
Whoa, say more about Fable sabotaging your codebase?
david_shi
·19 วันที่ผ่านมา·discuss
These models don't seem very competitive, who's their target audience?
david_shi
·19 วันที่ผ่านมา·discuss
Super helpful, thanks for sending.
david_shi
·20 วันที่ผ่านมา·discuss
Speaking from personal experience, I already know exactly what I’m getting with containers. Same with Postgres.
david_shi
·20 วันที่ผ่านมา·discuss
The price can move after the IPO too
david_shi
·21 วันที่ผ่านมา·discuss
The economics of working at a pre-IPO company that will likely have a successful IPO and a 20+ year post-IPO company are also very different.
david_shi
·21 วันที่ผ่านมา·discuss
It’s incredible how much higher quality Carolingian art is compared to the drawings that medieval art is usually associated with.

https://en.wikipedia.org/wiki/Carolingian_art#/media/File:Ka...
david_shi
·21 วันที่ผ่านมา·discuss
Nominative determinism.
david_shi
·21 วันที่ผ่านมา·discuss
How did you find out? Did they serve you like in the movies?