I kinda find it funny when I use the advisor on claude code and it agrees with the ideas that the previous model did. For info: the advisor(s) available are higher end models. For example: you use sonnet, the available…
I mean they all do it right ? Mistral is just the first one to publicly say it.
hmm that's a bit low right now, since you need at least 48Gb of VRAM to be confortable. 32Gb might do it (on quantitized models + optimized) but it would be very slow.
yep why not ? "Unified Memory" was always their favourite selling argument
same spec, same chip. I tought Apple would at least bump the RAM
Keep in mind also that LLMs are currenctly heavily subsidized. Once VCs money are gonna run out, you will see the real price, and your 200K per year dev is probably nothing.
same playbook than Huawei
The Chinese are coming after these greedy-ass frontier labs. Today Xiaomi unveiled it's own inference machine .... I bet it's gonna be cheaper than Nvidia DGX, shipped with open source models that anybody can have at…
checkout my claude-code plugin to display Claude Code status directly in the status line (below prompt textfield) https://github.com/moumine9/claude-status
I developed a small plugin for claudeCode that allows you to directly see in the console whats the status of claude-code in general and the status for your current model check => https://github.com/moumine9/claude-status
at this point, it's a feature, not a bug.
Sometimes you got to find a way to buy the silence of your top employee, to prevent them from going to the competition. This "start-up" is shallow as hell
On today's episode of "AI Frontier Labs running scams": Now that the narrative of "too dangerous to be released" is not longer working since Chinese gave it all away, they have to come up with another one. You had the…
On today`s episode of "Ai Frontier Labs ongoing scams"
I do not agree at all. When you have multiple repos accross different services, commits are the best way to follow up with differents changes. We adopted conventional commits guidelines a few months ago and everyone is…
Alex Karp was right, AI Compagnies are stealing people code while making them pay for unproductive tokens
So Alex Karp was right, AI companies "are stealing customers' data while charging them for unproductive tokens."
unfortunately yes. Too much bullshits jobs (to suck up funds mostly and critize every aspects of non existant projects) and not enough people to take risks and do the job.
Fake money in a fake economy to buy out real companies.
I use those commands also to filter output and fee ai agents with that. Tail and Head are my favourites to avoid wasting tokens. Wayy too many fancy build logs messages.
nope. With ClaudeCode you can create skills ( basically markdown instructions) to teach your agents what command to use. You can also update CLAUDE.md to inject custom instructions that are feeded anything ClaudeCode is…
they did the same thing in Afghanistan and some scanners were found by the talibans once american soldiers left. Somebody even bought these from ebay and retro-engineered the software to access the data. Edit: Article…
Only C-Series program was sold to Airbus, Bombardier still makes private jet.
exactly. That's really sad. The land is completely corrupted, it will take decades to rehabilitate
[flagged]
I kinda find it funny when I use the advisor on claude code and it agrees with the ideas that the previous model did. For info: the advisor(s) available are higher end models. For example: you use sonnet, the available…
I mean they all do it right ? Mistral is just the first one to publicly say it.
hmm that's a bit low right now, since you need at least 48Gb of VRAM to be confortable. 32Gb might do it (on quantitized models + optimized) but it would be very slow.
yep why not ? "Unified Memory" was always their favourite selling argument
same spec, same chip. I tought Apple would at least bump the RAM
Keep in mind also that LLMs are currenctly heavily subsidized. Once VCs money are gonna run out, you will see the real price, and your 200K per year dev is probably nothing.
same playbook than Huawei
The Chinese are coming after these greedy-ass frontier labs. Today Xiaomi unveiled it's own inference machine .... I bet it's gonna be cheaper than Nvidia DGX, shipped with open source models that anybody can have at…
checkout my claude-code plugin to display Claude Code status directly in the status line (below prompt textfield) https://github.com/moumine9/claude-status
I developed a small plugin for claudeCode that allows you to directly see in the console whats the status of claude-code in general and the status for your current model check => https://github.com/moumine9/claude-status
at this point, it's a feature, not a bug.
Sometimes you got to find a way to buy the silence of your top employee, to prevent them from going to the competition. This "start-up" is shallow as hell
On today's episode of "AI Frontier Labs running scams": Now that the narrative of "too dangerous to be released" is not longer working since Chinese gave it all away, they have to come up with another one. You had the…
On today`s episode of "Ai Frontier Labs ongoing scams"
I do not agree at all. When you have multiple repos accross different services, commits are the best way to follow up with differents changes. We adopted conventional commits guidelines a few months ago and everyone is…
Alex Karp was right, AI Compagnies are stealing people code while making them pay for unproductive tokens
So Alex Karp was right, AI companies "are stealing customers' data while charging them for unproductive tokens."
unfortunately yes. Too much bullshits jobs (to suck up funds mostly and critize every aspects of non existant projects) and not enough people to take risks and do the job.
Fake money in a fake economy to buy out real companies.
I use those commands also to filter output and fee ai agents with that. Tail and Head are my favourites to avoid wasting tokens. Wayy too many fancy build logs messages.
nope. With ClaudeCode you can create skills ( basically markdown instructions) to teach your agents what command to use. You can also update CLAUDE.md to inject custom instructions that are feeded anything ClaudeCode is…
they did the same thing in Afghanistan and some scanners were found by the talibans once american soldiers left. Somebody even bought these from ebay and retro-engineered the software to access the data. Edit: Article…
Only C-Series program was sold to Airbus, Bombardier still makes private jet.
exactly. That's really sad. The land is completely corrupted, it will take decades to rehabilitate
[flagged]