Viewing profile — Computer0

I do not have positive connotations regarding Theo Browne. Does anyone have any input regarding the others?

I believe the intention is for you to put it in the M.2

I was notified Framework customers were impacted.

"Auto mode runs a classifier on every tool call, which uses a small number of extra tokens. As of today, that classifier overhead no longer counts toward your usage limits on Pro, …

[flagged]

I found this site [ https://fontsinuse.com/ ] mentioned in the article to be quite interesting to browse through.

I find the value of this site to be the people. There are insightful discussions about immigration, visas, law, and other news-adjacent topics that have commenters who engage in a …

Oil is a global market and these corporations have a legal fiduciary responsibility to stakeholder. I doubt the legality of them providing fuel at a lower cost to American's if it …

Have not had great ds performance in agentic harnesses in the past compared to glm or k3

For anyone else wondering, the companies are not named in the article, and the models mentioned are Claude Opus 4.7, Claude Mythos 5 and an internal research model. There is little…

This is unfamiliar territory, and honestly it's still an assumption. No one is sure at what level the system needs to remain stable.

Much of the stress I see from people who are struggling with stress from online is caused by “the news” at large. Could this same result be said if these same individuals read the …

My understanding is that models can suffer “context limit anxiety” and a higher context limit will make it perform better especially as the context expands

I follow the New York Times, as well as being an avid news follower and have found them to be of poor reporting quality a handful of times over the past year.

Doesn't open ai give away 'the gate' for free?

Release it under a fake name?

My usage of GLM 5.2 has been defined by slow throughput and flaky providers, in many (definitely not all!) applications a dumber, faster, and more consistent model makes more sense…

In a corporate setting yes Opencode all the way. However in a non corporate setting I am getting $3000 of api usage a month for $100 at Anthropic and only use open code for the sma…

My nas has an N100 because I wanted to avoid Synology's shite CPU offerings. I similarly have had no issues.

I just put media in a folder and then watch it I rarely have to manage my Jellyfin server

You should release it though.

The canadian government will provide lots of historical data for curious citizens, many of which are recordings of interviews from decades and decades ago. For a book project this …

Subagents are quite inefficient and the lossy context transfer between them does lead to more cost and more waiting. However I have found it to produce more reliable output, whethe…

I see it everyday

thank you for being a voice of reason. I am with you.