News for hackers. Stuff that matters.

sidgtm

Re:Grok 4.7 on Monday September 21, 2026 @12:36PM (#49789572)
In my experience Grok especially inside Grok build is pretty solid choice, it’s a no nonsense model and stays on its course. Another surface where I truly enjoy the experience of using Grok model is Grok bot
Re:Codex for almost everything on Thursday April 16, 2026 @01:21PM (#47796599)
They felt the pressure of posting something after Claude 4.7
Re:Push events into a running session with channels on Thursday March 19, 2026 @10:23PM (#47449652)
It’s quite basic if I am using it correctly! It expects certain commands to be still approved on main machine.
Re:Push events into a running session with channels on Thursday March 19, 2026 @09:37PM (#47449272)
yes! its all happening
Re:Push events into a running session with channels on Thursday March 19, 2026 @09:37PM (#47449266)
this is exactly i thought!
Re:GLM-4.7: Advancing the Coding Capability on Monday December 22, 2025 @09:54PM (#46361907)
I am quite impressed with this model. Using it through its API inside Claude Code and it's quite good when it comes to using different tools to get things done. No more weekly limit drama of Claude also their quarterly plan is available for just $8
Re:Ask HN: What Are You Working On? (October 2025) on Sunday October 12, 2025 @08:29PM (#45563465)
I am building https://www.indiancoffeeguide.com/ in side to document coffee roasters from India and Indian coffee scene in general
Re:Two things LLM coding agents are still bad at on Thursday October 09, 2025 @04:20AM (#45524969)
specific inputs e.g. move, color change, or giving specific inputs for interaction piece.
Re:Two things LLM coding agents are still bad at on Thursday October 09, 2025 @02:55AM (#45524405)
As a UX designer I see they lack the ability of being opinionated about a design piece and go with the standard mental model. I got fed up with this and made a simple java script code to run a simple canvas on the localhost to pass on more subjective feedback using highlights and notes feature. I tried using playwright first but a. its token heavy b. it's still for finding what's working or breaking instead of thinking deeply about the design.