HNHacker News
TopNewBestAskShowJobs

ryan-a

16 karma · joined April 26, 2025

Indie Hacker and Full Stack Developer Founder of Hostibly.io, a booking engine for short stay property managers. I build apps for people too, send me an email! Email: ryan@nativelab.dev
submissionscomments
ryan-a··on GLM-5.3: Frontier coding with emergent cyber capabilities
I used the legacy plan with only the 5 hour limits on lite. It was super awesome but sadly not comparable to the new plan.

Currently I am on the new max plan with the 5hr limits and weekly limits, I can't speak for the credit plan. Using it exclusively in zcode because of the usage multiplier + the harness is genuinely good.

Easily do a billion tokens per week on my limits and generally have no problems with limits, however if I use it during peak hours I will hit the 5hr limit super fast even in zcode.

Zcode gives much more usage: Normal hours 1x -> 0.67x usage multiplier Peak hours 3x -> 2x usage multiplier

Peak lines up with the afternoon for me and I prefer coding morning/night so its not really a problem + I have the codex $20 plan and opencode go so I can always use other subs during peak hours.

If the peak hours are your main work hours (its a 4 hour window) then the value is going to be MUCH lower, especially in CC or other harnesses (1/3rd the usage limits is harsh).

It does also change a bit depending on demand, so I recommend getting the max plan because you get priority access if you really like the model, it would be a 10/10 recommendation for me if it had vision but rn its mainly useful for backend or throw away internal tools where IDK about the UI as much.

ryan-a··on DeepSeek V4—almost on the frontier
You don't need to run the model locally if you don't care about sharing your data. Personally I am happy to share data with Kimi or Deepseek if it means we get better OSS models. For private stuff though local is king
ryan-a··on DeepSeek V4—almost on the frontier
This is huge for me too, I was working on something super benign the other day and GPT flagged it for Cyber risk, Deepseek just does the work, its fast and cheap. Its only missing image support IMO, once deepseek cracks image too its going to be hard for anthropic and openai to compete.
ryan-a··on VS Code inserting 'Co-Authored-by Copilot' into commits regardless of usage
Time to leave for something else if you haven't already, vscode has been good to us but this kind of behavior is only going to ramp up as Microsoft seeks to get a return on their AI investments.
ryan-a··on Show HN: WebRTC LAN Baby Monitor for iOS and iPadOS
Thats really interesting, yeah I think that audio alone can be helpful. The notification though is actually really important now that you mention it I will see if I can add that in the next update!
ryan-a··on Show HN: WebRTC LAN Baby Monitor for iOS and iPadOS
Great idea! I will add that ASAP
ryan-a··on Show HN: WebRTC LAN Baby Monitor for iOS and iPadOS
Thank you <3
ryan-a··on Show HN: WebRTC LAN Baby Monitor for iOS and iPadOS
Thats great! I got the idea from a similar setup actually, I set this app up so you can connect and disconnect any time though so you dont have to walk into the room to accept the call.