brianjking

Joined 12 years ago

Karma

1,303

Submissions

758

Member since

Aug 18

https://twitter.com/iamrobotbear https://twitter.com/brianjking https://brianjking.io https://www.linkedin.com/in/brianjking

- Product Manager, AI & Machine Learning - AI Engineer & Product Consultant

Located in the PNW, USA.

View on Hacker News

Recent submissions

Comment · 1 day ago

In fairness, nor does Salesforce.

Comment · 2 days ago

I've been using ChatGPT since release and Codex since before ChatGPT was a thing (with the original Codex model). Am I the only one who didn't realize these limits weren't already merged since the current Codex app was released?

Comment · 3 days ago

This is sadly not surprising to me as if you listened to/watched the [Latent Space episode on Opus 5.5](https://latent.space/p/how_anthropic_ships_the_1_llm_in_the_...) 25 minutes into the podcast and instead of talking about how they've released one of the best models in the world, they were busy talking about the changes to the API and why normies must not be trusted to perform inference outside of Dario's blessing.

It's frankly disgusting and really makes me not want to use Anthropic, despite previously feeling aligned with a lot of what Anthropic published.

Comment · 16 days ago

4-6 months? Try between 8-18 days for a foundation lab release.

Comment · 2 months ago

This is happening at every other AI lab. What are you talking about? Have you not seen the stories from Meta, Anthropic, Deepseek, etc?

Comment · 2 months ago

Furthermore, it almost surely limits the quality of the output. At least the finterprinting of the text tokens has to, how can you otherwise constrain token output?

Comment · 2 months ago

This! So much this. After Opus 4.8 I could barely comprehend anything it was attempting to communicate.

Comment · 2 months ago

.... Minus that Nvidia keeps contributing to the open ecosystem with nemotron, among countless other open contributions.

Comment · 2 months ago

It's lies all the way down...or up?

Comment · 2 months ago

What about your life's OKRs?

Comment · 2 months ago

I've found it so much easier to work without a 5 hour usage limit. I really hope we rapidly get to a world without as much need of one.

Comment · 2 months ago

Tagging files in Claude desktop in code mode works fine for me, as does CLI. With that said, in Cowork, it's been broken for some time and driving me crazy.

I've shifted most of my usage to Codex/ChatGPT Work. The UX of appshots, browser annotations (now available in claude), and the computer use being so much less intrusive in OpenAI.

Comment · 3 months ago

Yeah, there's a ton of great improvements in 7-28. I'm personally excited about what you posted about, but also with [tasks](https://blog.modelcontextprotocol.io/posts/2026-07-28-releas...) being officially adopted.

Comment · 3 months ago

Yes.

Comment · 3 months ago

Definitely agree on the title. Also could have worked as 'Some minor annoyances that, when fixed, would improve OpenCode. Also, I don't like AI"