World & Business

Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

Home
Technology
Gaming
Entertainment
World & Business
Science
Sports
AI

GLM 5.3 Flash results could be off · Digg

Report

GLM 5.3 Flash results could be off

A user says they had Codex find the results, but cautions that they could be off.

TLDR

A user mentioned GLM 5.3 Flash alongside results they said Codex found, while warning that those results could be off.

Combined views

147.3K

13 Sources, first seen 20d ago

Combined views

147.3K

13 Sources, first seen 20d ago

3.1K likes

20d ago

first seen 20d ago

3.1K likes

81 comments

324 saves

80 reposts

81 comments

324 saves

80 reposts

Featured Source

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Sentiment

Positive——Negative

Summary

Not enough discussion yet.

No sentiment analysis available yet.

Today's Rank

—

Not ranked yet

Today's Rank

—

Not ranked yet

13 Sources

@TheZachMuellerBtw GLM 5.3 Flash (had codex go find the results, could be off)20d

@xeophonRT @TheZachMueller: Btw GLM 5.3 Flash (had codex go find the results, could be off)20d

@scaling01the actual highest scores highlighted and consider that Haiku 5.5 is probably much smaller than GLM 5.3 Flash19d

@MiaAI_labRunning GLM 5.3 Flash at 227 tok/s on DGX Sparks looks unreal to me. But here it is. This is 4 concurrent streams, mixed.19d

@willcbwow i cannot believe how well this aged19d

@sundeep⚡️⚡️⚡️19d

@ClementDelangueRT @MiaAI_lab: Running GLM 5.3 Flash at 227 tok/s on DGX Sparks looks unreal to me. But here it is. This is 4 concurrent streams, mixed. h…19d

@peteskomorochRT @MiaAI_lab: This is why DGX Spark prices have sky rocketed19d

@teortaxesTexHm not surprising given what Whale Bros are making their models for (and their biggest headache in the middle of moving to Ascends, probably)17d

@zeegif it is helpful for anyone who is curious if their luna use case might be doable on haiku, id assume the default is prob not (this is high effort)17d

13 Sources

@TheZachMuellerBtw GLM 5.3 Flash (had codex go find the results, could be off)20d

@xeophonRT @TheZachMueller: Btw GLM 5.3 Flash (had codex go find the results, could be off)20d

@scaling01the actual highest scores highlighted and consider that Haiku 5.5 is probably much smaller than GLM 5.3 Flash19d

@MiaAI_labRunning GLM 5.3 Flash at 227 tok/s on DGX Sparks looks unreal to me. But here it is. This is 4 concurrent streams, mixed.19d

@willcbwow i cannot believe how well this aged19d

@sundeep⚡️⚡️⚡️19d

@ClementDelangueRT @MiaAI_lab: Running GLM 5.3 Flash at 227 tok/s on DGX Sparks looks unreal to me. But here it is. This is 4 concurrent streams, mixed. h…19d

@peteskomorochRT @MiaAI_lab: This is why DGX Spark prices have sky rocketed19d

@teortaxesTexHm not surprising given what Whale Bros are making their models for (and their biggest headache in the middle of moving to Ascends, probably)17d

@zeegif it is helpful for anyone who is curious if their luna use case might be doable on haiku, id assume the default is prob not (this is high effort)17d