HackerTrans
TopNewTrendsCommentsPastAskShowJobs

jameswhitford

41 karmajoined 2 lata temu

Submissions

Show HN: Agent Draw: An agent draws while you talk, built on TLDraw

techstackups.com
37 points·by jameswhitford·6 dni temu·14 comments

Claude is skeptical about OpenClaw

wecreatethis.com
2 points·by jameswhitford·3 miesiące temu·2 comments

comments

jameswhitford
·4 dni temu·discuss
Agreed! The world is a little unbalanced in this way right now unfortunately.
jameswhitford
·4 dni temu·discuss
This is sick where have you been all my life!
jameswhitford
·4 dni temu·discuss
This is awesome! I love mermaid but have struggled to get my agents to be any good at it. Maybe I just need to context engineer a little better
jameswhitford
·4 dni temu·discuss
It would be great if it could have examples of your own diagrams in its context, so it knows what points you like to map out and how you like to visualize them
jameswhitford
·4 dni temu·discuss
That’s awesome! My inspiration was the IBM YouTube channel where they write on the board in front of them, maybe you could use the white canvas as like a green screen or something to get a similar effect?
jameswhitford
·4 dni temu·discuss
The potential use cases was my favorite part of designing it, it’s not perfect now but it’s so fun to think what people might do with these kinds of designs in the future
jameswhitford
·4 dni temu·discuss
Yes I would love to see some work on the design, because I think it could be useful, just needs some speed and accuracy improvements, and maybe some design towards specific use cases
jameswhitford
·4 dni temu·discuss
Yes it could get a lot better with some design improvements, maybe live streaming the transcription, and maybe after some trial and error testing the best + fastest model for the job
jameswhitford
·4 dni temu·discuss
Facts!
jameswhitford
·21 dni temu·discuss
That is a great suggestion that I am definitely going to look into, thanks!
jameswhitford
·21 dni temu·discuss
I hear you
jameswhitford
·21 dni temu·discuss
Cool to hear, what kind of tasks have you been using GLM for? And what other models have you found useful through Ollama?
jameswhitford
·21 dni temu·discuss
I see your point. Just the fact that one model does have vision and one does not might be an interesting point of comparison, however.
jameswhitford
·21 dni temu·discuss
This is excellent feedback thank you! These LLMisms in writing are a challenge I am living with currently and trying to improve on. The technical writing industry is taking a huge knock right now with companies demanding more work in less time with a big drop in quality, day to day I get less and less time to work on the quality in the prose of my work. We are working at the frontier of this right now, so we are the most heavily effected, but also get to experiment with the changes first which can be both stimulating and very frustrating.
jameswhitford
·21 dni temu·discuss
Hi, author here, can you link? I would love to read about this.
jameswhitford
·21 dni temu·discuss
Yes I agree 100%. My next guide would do better to use identical harnesses.
jameswhitford
·21 dni temu·discuss
GLM 5.2 is text only, not multi modal. And Opus is multi modal.
jameswhitford
·21 dni temu·discuss
Hi, author here, I cannot give an exact number for how many token the verification step took, but the verification GLM 5.2 ran was very stupid and definitely a waste of time. It read the pixel color data to try and verify the scene rendered properly. Which is really bad. Opus opened the game in a Playwright browser and took screenshots to verify the actual image. Which helped a lot.

Pro tip: You could use a multi-modal model to verify images as a subagent spawned by GLM 5.2, to get around this issue.
jameswhitford
·21 dni temu·discuss
Yes I 100% agree. Time-taken can be improved (with harnesses, subagent workflows etc.) and varies based on task.
jameswhitford
·21 dni temu·discuss
Yes, part of the reason I chose the one-shot test was really to test long-running tasks. A lot of people seem to be experimenting with this format, for example in the now trending loop-writing workflows. And really I am interested in diving into the murky waters of these novel workflows.