HackerTrans
TopNewTrendsCommentsPastAskShowJobs

vijgaurav

no profile record

Submissions

Show HN: Qwen Lens Studio – multimodal app on Qwen3.6-35B-A3B, runs on Ollama

github.com
3 points·by vijgaurav·vor 3 Monaten·0 comments

Neo Scored 34.2% SOTA on OpenAI MLE-Bench

github.com
3 points·by vijgaurav·vor 10 Monaten·0 comments

comments

vijgaurav
·vor 2 Monaten·discuss
The 60-minute single-pass transcription is the part that actually matters. Most ASR models chunk audio and you lose speaker continuity across boundaries. If the diarization actually holds up on hour-long recordings without drifting, thats a real solve for podcast and meeting transcription workflows.
vijgaurav
·vor 2 Monaten·discuss
The fact theyre shipping the actual agent harness alongside the weights is the part that matters. Most labs dump the model and make you figure out the agent layer yourself. If its the same runtime they use for RL training, its actually been exercised in production rather than being some demo wrapper.
vijgaurav
·vor 2 Monaten·discuss
[dead]
vijgaurav
·vor 3 Monaten·discuss
[dead]
vijgaurav
·vor 3 Monaten·discuss
[dead]
vijgaurav
·vor 3 Monaten·discuss
[dead]
vijgaurav
·vor 3 Monaten·discuss
[dead]
vijgaurav
·vor 3 Monaten·discuss
[dead]
vijgaurav
·vor 3 Monaten·discuss
Unless it is AI slop, I don't mind reading submissions that can be genuinely helpful.
vijgaurav
·vor 3 Monaten·discuss
[dead]