Viewing profile — supermdguy

Dupe: https://news.ycombinator.com/item?id=49241679

Here's the performance of frontier models without reasoning, to more directly address the claim that raw performance is plateauing: https://artificialanalysis.ai/evaluations/artifi…

Interesting, what did you use for the data? And do you have a write-up anywhere?

It'll be really interesting when they run RL training on the harness self-improvement loop. I've tried using LLMs for harness engineering, but it often creates too much bloat that …

It has read only access, so it’s able to check query statistics, find slow queries, then run EXPLAIN ANALYZE to find the root cause and either tweak the query or suggest indexes. A…

Still figuring it out, but it's been really convenient to have an always-on agent that has access to internal systems and can be triggered by webhooks. Some examples of what we use…

It would require collusion with HuggingFace, including getting them to release their disclosure blogpost a week in advance. Huggingface is primarily a hub for open models, so there…

The administration promised they'd find a cause by September 2025. I guess that was the best they had at that point? https://www.cbsnews.com/news/rfk-jr-cause-of-autism-research...…

“Do you know what the industry term for a project specification that is comprehensive and precise enough to generate a program? Code. It’s called code.” - CommitStrip ( https://www…

[dead]

> We're also launching GPT‑5.6 Sol on Cerebras at up to 750 tokens per second in July, bringing frontier intelligence to customers at unprecedented speed. This is really exciting. …

Agreed, there were also a few where I deduced the correct definition by comparing the options.

One trick I’ve used is creating a folder and then adding a .gitignore inside it with *. Then nothing in that folder gets tracked, without needing to add anything to the public giti…

I agree that current memory systems are pretty bad, and I think that’s because memory is a prompted behavior instead of a learned one. In theory, if memory was an emergent behavior…

I think good taste is objective to an extent, especially given a particular production context.

Someone posted a tool that does this recently: https://news.ycombinator.com/item?id=47140042

There was a show HN for something similar a couple months ago[0]. Looks like they shut it down. Probably too difficult/low-margin to run as a business, but I think the co-op model …

It's interesting because their last model series (Phi) was based around the thesis that high-quality synthetic data is better than a large pre-training corpus.

I think the conduit exception still applies for analog faxes. Which makes no sense, since tapping a fax line is probably way easier than compromising a data center.

Apparently from a third party seller in New York....and tastes really bad. I was surprised steak could be safely mailed in such normal looking packaging! https://www.delish.com/foo…

Interesting to see this after the recent post about Chrome’s on-device model using up 4gb of storage, which frustrated a lot of people [1]. I agree local models are great, and it’s…

Better auth is great! I love how it's way more hackable than using a something like Clerk. We were able to add a plugin to allow auth via iframe postMessage (embedded in a CRM) and…