technocrat8080

Joined 3 years ago

Karma
44
Submissions
28
Member since
Sep 28
Reach out at throwawayapples409 on gmail.
View on Hacker News

Recent submissions

Comment · 7 months ago
Wow, would love to see a source for this.
Comment · 7 months ago
Have they ever talked about their size or weights?
Comment · 7 months ago
5.4 Mini's OSWorld score is a pleasant surprise. When SOTA scores were still ~30-40 models were too slow and inaccurate for realtime computer use agents (rip Operator/Agent). Curious if anyone's been using these in production.
Comment · 7 months ago
You can provide the screencapture cli as a tool to Claude and it will take screenshots (of specific windows) to verify things visually.
Comment · 7 months ago
In my experience, especially with Opus 4.6, using subagents greatly mitigates the startup context hit. 4.6 has very obviously been RL'ed on subagent usage and it almost always spins up an Explore agent to get a feel of the codebase and get a token-efficient summary. The 1M context version of 4.6 further alleviates this.

My original question was more along the lines of implementing things like PR review yourself. I was tinkering with an internal service that spins up ephemeral CC instances to analyze PRs, but realized this can easily generalize across arbitrary tasks. Was curious what sort of things folks could use that for.

Comment · 11 months ago
To be clear, it's not a TEE replacement but does address one of the most common use cases of TEEs
Comment · 1 year ago
Seems pretty obvious Sky.app's functionality will land in the macOS ChatGPT app at some point. I wonder how Atlas fits into that story.
Comment · 1 year ago
Sky is macOS only. It essentially gives an LLM access to various system APIs coupled with a floating user interface that you can access on command.
Comment · 1 year ago
By parallel, do you mean editing the codebase in parallel? Does it use some kind of mechanism to prevent collisions (e.g. work trees)?
Comment · 1 year ago
What kind of agents do you have setup?
Comment · 1 year ago
Curious about this too – does it use the standard context management tools that ship with Claude Code? At 200K context size (or 1M for the beta version), I'm really interested in the techniques used to run it for 30 hours.
Comment · 1 year ago
A bit confused, all this to say you folks use standard containerization?
Comment · 1 year ago
I sense the undertone here is that there's a cost to genetic testing – did I get that right? Could you expand on that philosophy?
Comment · 1 year ago
My god, how can I take photos like that? Do you describe your setup and process somewhere?

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton