Daniel Mulec

I need to write a new bio

[Daniel Mulec @danielmulec]

Noch 3 Wochen bis Agentic Coding Graz #3!

Show & Tell: 5-10 min für euer Projekt, euren Workflow oder euren schönsten Fail. Keine Slides, kein Pitch.

Slot sichern? Meldet euch bei mir - oder entscheidet euch am 02.07. spontan.

Anmeldung (max. 35): https://t.co/bovjXc5toh

[Daniel Mulec @danielmulec]

@thoughtlesslabs Show them the wonders that is Codex remote

[Daniel Mulec @danielmulec]

@xikhar @vaxryy @EbikoVtuber Gotta appreciate a fine arts enthusiast

[Daniel Mulec @danielmulec]

More useful than all of the GLM benchmarks posted on X or YouTube so far

[Da7em @Da7_Tech]

Same task. Same prompt. Same setup.

Opus 4.8 completed the task.
It used 2% of the weekly limit and 7% of the 7-hour limit.
GLM 5.2 did not complete the task.
It consumed 20% of the weekly limit and 100% of the 5-hour limit.

Token usage is completely abnormal:
Opus 4.8: less than 1.5M tokens

GLM 5.2: reached 53M tokens

And this is despite the app showing only around 1.67M tokens.
This means one thing very clearly: cached tokens are not working properly on GLM 5.2. The repeated context is being counted as normal input instead of cached tokens.

I have been dealing with this issue for more than a month with no real solution.

By the way, I am on the Pro plan, and I paid for a full yearly subscription.

These numbers are not normal. This is not usage behavior. This is a serious billing/cache accounting problem on GLM 5.2.

[Daniel Mulec @danielmulec]

@f4micom Except that you're pushing the least capable of the chinese competition. Kimi and GLM are far better than Minimax

[Daniel Mulec @danielmulec]

@kenwheeler Imagine using Claude Remote Control out there

[Daniel Mulec @danielmulec]

@GuGi263 One of those examples why I don't like dogs. Cats rule dogs drool 😡

[Daniel Mulec @danielmulec]

@khaydo30 War es Wert 👍

[Daniel Mulec @danielmulec]

@khaydo30 Ich kommentier hier damit ich später das mit Ton mir zu Gemüte führen kann

[Daniel Mulec @danielmulec]

@Iam_best_dev @BitGameHD @mersomas Nein. Der Satz ist zu Ende weil es impliziert dass man fragen kann

Wo ist mein iPhone?
Wo ist mein iPad?
Wo ist mein Mac?

Usw usf

Heißt nicht dass ich es selbst gut finde, Ich würde lieber kommandieren als fragen aber das ist wie Lokalisation funktioniert

[Daniel Mulec @danielmulec]

@Iam_best_dev @BitGameHD @mersomas Seeing what meek socialists Germans are these days, no surprise btw

[Daniel Mulec @danielmulec]

@Iam_best_dev @BitGameHD @mersomas It's called localisation, an entirely different field from translation, that is used to make texts match different markets.

Apple determined, that Germans rather ask "where is my iPhone?" Than to tell it to "find my iPhone"

[Daniel Mulec @danielmulec]

@emobaxxter Das links is doch nicht die Mutter vom Sandro

[Daniel Mulec @danielmulec]

@reach_vb Graz, Austria. Been offering you guys to host it numerous times but never got a reaction, so I am now into month 3 of my general Agentic Coding meetup here

[𓆩♡𓆪 @fairyprxncess]

"Where do you see yourself in 40 years?"

me:

[Daniel Mulec @danielmulec]

Honestly I'd say go ahead, but I think that's too much of a stretch in real life engineering. Let's be real about how for example Kimi k2.6 is more Claude Sonnet 4.5 level than anything else.

With that, if GLM 5.2 produces real life code of equal quality to GPT 5.2 or Opus 4.5 I'd already be incredibly happy

[Daniel Mulec @danielmulec]

@thekitze This is where all my haters go for a drink