Viewing profile — seanmcdirmid

Alibaba probably. They are doing work on both already, that is if a quantum LLM is even feasible.

You still have to make a call on whether it’s worth it or not. People who think price doesn’t matter don’t live very long anyways.

Dying as a motorcyclist is different from dying. Life insurance either pays off or it doesn’t, if you hold it from 20 to 90, it usually doesn’t pay off.

You can compare Qwen with thinking to Qwen with no thinking though. I find my results are better without thinking because of overthinking.

Not parent, but I use Goose for my non-handcrafted Qwen use cases, I’m also working on handcrafting as well. Goose was the only harness that didnt bloat context too much with syste…

Disable thinking? I think many harnesses disable thinking on Qwen anyways because it interferes with tool calling.

Existentials are always true trivially.

> You can die unexpectedly from things far less dangerous than motorcycles. Existantials are always trivially true. But statistically: > The lifetime odds of dying as a motorcyclis…

Has anything really changed for transparency?

If you were living in Nepal and your country was getting all of its refined gasoline from India, and therefore that was super expensive, while China was helping your country build …

Is it really that painful? If you are charging from home, you just look at your local power rates. If you charge for one or two road trips a year, you don't even bother calculating…

No, it is exactly like gardening leave, except you have a chance of switching to a new role at the company by applying for internal job transfers. I'm abusing the term also, for Am…

Ya, it means my role at Google is gone and I have to find a new role or be laid off. I think “on the beach” sounds better than gardening leave, the term comes from the American con…

I actually considered lite LLM to get Qwen to work with codex. It mostly works without lite LLM but MCP servers aren’t available, lite LLM tricks into think Qwen is an OpenAI model…

No, it could be python or a DSL or whatever. Using Bazel and starlark is just a shortcut given a lack of any good ideas yet for a purpose built orchestration language.

I’m currently on the beach at Google (since mid July), so I’m looking internally and externally for a new role. But I’m exhausted, so I’m playing around with local LLMs and DeepSee…

[dead]

The story was from the time he was working on Microsoft Office, so after Parc in the early or mid 80s. I was actually just surprised someone who worked at Microsoft back then was s…

If you don’t have a way to automatically check the results via redundancy, you need a really good model, since even 99.9% reliability is going to cause slot of headaches. If you do…

I heard this directly from someone who worked with simonyi back then, although she could have been making it up.

Charles Simonyi Has that story about how a PM began publicly calling out engineering productivity by having them report weekly lines of code, and Simony one week put a negative num…

I use Chinese models, even smaller local ones, for much more than pair programming. If we are talking about deepseek v4 flash, which is basically a frontier model, it is much more …

Note they double the price if you use during peak time. However, they define peak time with respect to China, not Europe or the USA...so if you are out of Asia, I guess Australians…

It really isn’t that bad even if you do adjust for local salaries, but only to a point. Still have lots of people commuting in from the suburbs and that can be a brutal 2 hour comm…

Those deals are only for locals though. If you move to Switzerland you need to pay. Actually, the same is true of any place with any kind of public housing or rent control, it’s a …