howdareme
Re:Jailbreaking the Switch 2
on Thursday October 22, 2026 @08:21AM (#50194325)
this was clearly human written
Re:Qwen-Image-2.1: Compact, efficient, and unified image creation
on Sunday September 20, 2026 @01:05PM (#49777675)
Qwen is trained off of gpt’s outputs. This is both a positive and negative
Re:Navier-Stokes – Tristan Buckmaster [pdf]
on Tuesday September 08, 2026 @04:14AM (#49607190)
They are not training a whole model in a matter of days
Re:GPT 5.6 Sol is the best "vision" model OpenAI ever released
on Monday August 17, 2026 @08:56AM (#49330076)
How can a vision model have taste?
Re:Cursor Bridge – Run Unlimited Claude Code on Your Cursor Subscription
on Sunday July 26, 2026 @07:49PM (#49063558)
Claude’s native harness is pretty bad though relatively. Pretty sure at one point it was scoring last on harness related benchmarks using Opus at the time
Re:Gemini 3.5 Flash
on Tuesday May 19, 2026 @02:17PM (#48197102)
Google’s pro models are almost certainly bigger than Openai’s lol
Re:Show HN: OSS Agent I built topped the TerminalBench on Gemini-3-fla...
on Monday April 27, 2026 @09:48AM (#47921521)
Going to assume you didnt capture the data but could you add time taken to completion for each if you have it?
Re:Claude Design
on Friday April 17, 2026 @04:32PM (#47810259)
Does anyone know how they turn html to enable powerpoints so seamlessly?
Re:Muse Spark: Scaling Towards Personal Superintelligence
on Wednesday April 08, 2026 @01:40PM (#47693614)
The benchmarks they released
Re:Show HN: We analyzed 1,573 Claude Code sessions to see how AI agent...
on Thursday March 12, 2026 @10:58AM (#47351571)
LLM comment spotted
Re:Google Titans architecture, helping AI have long-term memory
on Monday December 08, 2025 @05:34AM (#46190731)
I mean looking antigravity, jules & gemini cli, they have have no problem with their developers fighting for resources