the business model, I suspect, is classic rug-pull in some time after building user base.

proof: boldly claiming being open source in literally first sentence, while cowardly hiding on-by-default telemetry (WTF??) in truly last paragraph of readme.

sorry to sound harsh, but this is typical old era playbook here.

in the era of AI, fortunately, such products has much lower value. people and VCs didn’t yet tune to it.

Telemetry is off by default. PostHog is for usage analytics on the open source repo. Audit it if you're skeptical.

We make money off enterprise licenses and hosting models.

I have strong reason to suspect you either can't read or are a bad actor.

Your GitHub readme says telemetry is on by default

"Anonymous aggregate PostHog product telemetry is enabled by default. It never includes prompts, traces, actions, observations, paths, model names, credentials, or raw customer content."

impressive only if using pre-gpt era assumptions about saas/products/software.

unfortunately a small team can reproduce it in two months, which greatly lowers value of it.

we, as a collective, have to change our value-judging logic and tune it to post AI world.

It is still slow.

Honestly I do not understand those last ten years craziness about 'new-native-gpu-turbo-ultra-xhigh-max-terminal' <insert current trend here>.

(my) battle tested urxvt under X11 is STILL faster then shitty (and all others):

## ascii (95 MiB cat, best wall of 3)

| terminal | wall | user | sys | throughput | |---|---|---|---|---| | urxvt | 0.78s | -s | -s | ~122 MiB/s |

these days on HN, if you oppose someone, you get dead-flagged.

I vouched for your comment, as I find it perfectly 'not agreeing' answer.

It wasn't me flagging, by the way.

The burden of proof also falls on the person making the claim.

There are three things to make money:

- tell lies to ones who want to hear lies -> riches

- tell truth to ones who want to hear truth -> modesty

- tell truth to ones who want to hear lies -> bankruptcy

p.s. read it on a blog name I dont remember :(

If my polite neighbour smiles, holds the door, but also pisses on my doormat every few days, I call him LOUD a jerk and tell him to stop. I never approve the piss because he said good morning.

How is this a fair analogy? The NYT isn't pissing on your doormat. Making it harder to cancel is an annoyance, but it's not like they don't let you.

Thank you for writing this and your below longer comment.

I printed them with OP to remind me any time i’m afraid somebody can criticize my work and that it’s not worth to produce/write/publish.

no matter how good, there will always be people like you here, so no need to worry.

## performance data for token generation using lmstudio

- gemma4-31b normal q8 -> 5.1 tok/s

- gemma4-31b normal q16 -> 3.7 t/s

- gemma4-31b distil q16 -> 3.6 t/s

- gemma4-31b distil q8 -> 5.7 tok/s (!)

- gemma4-26b-a4b ud q8kxl -> 38 t/s (!)

- gemma4-26b-a4b ud q16 -> 12 t/s

- gemma4-26b-a4b cl q8 -> 42 t/s (!)

- gemma4-26b-a4b cl q16 -> 12 t/s

- qwen3.5-35b-a3b-UD@q6_k -> 52 t/s (!)

- qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive@q8_0 -> 34 tok/s (!)

- qwen3.5-35b-a3b-uncensored-hauhaucs-aggressive@bf16 -> 11 tok/s

- qwen3.5-27b-claude-4.6-opus-reasoning-distilled-v2 q8 -> 8 tok/s

- qwen3.5 122B A10B MXFP4 Mo qwen3.5-122b-a10b (q4) -> 11 tok/s

- qwen3.5-122b-a10b-uncensored-hauhaucs-aggressive (q6) -> 10 tok/s

interesting, I just tried this very model, unsloth, Q8, so in theory more capable than Simon's Q4, and get those three "pelicans". definitely NOT opus quality. lmstudio, via Simon's llm, but not apple/mlx. Of course the same short prompt.

Simon, any ideas?

https://ibb.co/gFvwzf7M

https://ibb.co/dYHRC3y

https://ibb.co/FLc6kggm (tried here temperature 0.7 instead of pure defaults)

try Unsloth recommended settings

    Thinking mode for general tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

    Thinking mode for precise coding tasks (e.g. WebDev): temperature=0.6, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=0.0, repetition_penalty=1.0

    Instruct (or non-thinking) mode for general tasks: temperature=0.7, top_p=0.8, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

    Instruct (or non-thinking) mode for reasoning tasks: temperature=1.0, top_p=0.95, top_k=20, min_p=0.0, presence_penalty=1.5, repetition_penalty=1.0

(Please note that the support for sampling parameters varies according to inference frameworks.)

all the examples for visual UI, are tasks which already are (or soon be) done by the agent, not human. hence not needed.

I suspect that final(*) UI is much more similar to TUI: being kind of conversational (human <> AI). Current GUIs provided by your bank/etc are much less effective/useful for us, comparing to conversation way: 'show/do me sth which I just need'. Not to mention (lack of) walled garden effect, and attention grabbing not in the user interest (popups, self-promo, nagging). Also if taking into account age factor. Also that we do not have to learn, yet another GUI (teach a new bank to your mom ;). So at least 4 distinct and important advantages for TUI.

My bet: TUI/conversation win (*).

*) there will be some UI where graphical information density is important (air controller?) especially in time critical environments. yet even there I suspect it's more like conversation with dynamic image/report/graph generated on the go. Not the UI per se.