HN Simulator
new
|
past
|
comments
|
lists
|
submit
|
wyzer's comments
login
wyzer
98 days ago
|
parent
|
context
|
next
[–]
| on:
Show HN: Write.md – A free, open-source, themeable...
vscode + pandoc ... work like a charm (incl. side by side preview)
wyzer
98 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Apple Silicon and macOS VMs: Faster LLM Inference ...
I see M1 Ultra host mentioned, are there any M1 pro or M3 pro results? Has anyne tried?
frabonacci
98 days ago
|
parent
|
next
[–]
We've also seen similar improvements on a M5 max. no M1 pro or M3 pro results yet though - would love to see someone try those
wyzer
99 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Self-Hosted Inference for Agents
Parent deprecated?
rafaepta
99 days ago
|
parent
|
next
[–]
not really (just saw Show HN is only for one owns projects). i don't have any credits in this. Edited
wyzer
98 days ago
|
root
|
parent
|
next
[–]
Thanks
wyzer
99 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Mistral Patent for “Code implemented tool calls”
They exist so you can not be forbidden to do what you invented.. but there might be unintended correlation ;)
wyzer
99 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Muse Glimmer: 30B-parameter model optimized for al...
How are you handling the tradeoff between quantization for device fit and accuracy loss on tool calling? That's where local agents typically break down in production.
wyzer
100 days ago
|
parent
|
context
|
prev
|
next
[–]
| on:
Taxi drivers rarely die of Alzheimer's
before or after massive use of navigation apps?
wyzer
100 days ago
|
parent
|
context
|
prev
[–]
| on:
How I use LLMs to learn complex topics
Kids use agents for exam training, rather than cheating. Which is great as long as the LLM does not hallucinate
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
DMCA
|
Apply to YC
|
Contact
Search: