everyone loving these linux sandboxes, even Apple wrote one https://github.com/apple/containerization/tree/main/examples...
i think to fall in love with Pi, bundled skills are a bit antithetical - you realistically only need a couple of skills that you maybe design yourself
inference is profitable, these companies are in the red because they're paying a premium to get the compute now versus later (because compute is the only moat when open models are catching up) we're literally looking at…
OpenAI prioritized compute much much earlier on, so they’re probably just more able to provide the model while Anthropic seems to be busting out the seams Sonnet 5 today was incredibly slow for example
Deepseek isn't philanthropy, it's a hedgefund trying to short the western AI market by saying "hey we can do 90% of they can (arguably better at a density metric) for a 1/10th of the cost" it's my theory at least, the…
[dead]
if they’re paying for the tokens, what’s the problem
i'm in, i think prices are gonna suck anyway, i own a playstation and that shit sucks, i want to do more couch co-op with my partner and the steam library opens up so much indie games can i build a mini pc myself?…
TV is heavily subsidized from data collection and ads, not sure it's a perfect comparison
https://blog.kilo.ai/p/did-claude-opus-48-distill-alibabas it happens to all models…when the internet is increasingly generated, things happen
MCP tool search fixes the major issue imo, MCP clears skills/clis in every other way
I would try a 6-bit MoE and maybe with unsloth's studio, they claim to have auto tool fixing which is where i see a lot of issues with MoEs I'm on a 48gb M5 Pro right now and it's been okay, a lot of my rough…
large contexts degrade the performance - attention doesn't work will for large windows like that and cloud models are kind of hacking it local models do involve some context engineering to get it okay, but it's not that…
q4 isn't rubbish, but it's a compromise for a good value, q6 is essentially a no-compromise quantization and it's what i recommend for MoEs in my experience for agentic workflows
I'm talking about the common use case that I think hacker news people have: you get a macbook for work, you run the macbook they're not going to start giving GPUs to employees to run local models
I don't know about good, I use a lot of local models and they're still pretty painful to run locally You have dense models (qwen 27b, gemma 31b) who are pretty smart, but pretty slow You have MoE models (gemma 26b, qwen…
Minimax M3 too, and huawei claims to be releasing non-nvidia dependent training software too. openPangu 2.0 could be a shake-up if it holds up as a good model China may not care about open source, but they know they…
i’m running m4 pro 48gb right now omlx + gemma 12b 6 bit + pi it’s feasible for sure MoEs for speed (qwen 35b, cohere 30b, gemma 26b) Dense for more methodical work (qwen 27b [reigning champ], gemma 31b, gemma 12b) MoE…
it does not result in great results left unattended, it’ll start creating slop or hardcoding solutions but overtime if you adjust your verification rubric, it’s not too bad, gets pretty good, if you do make it do TDD,…
There's `honcho` for memory, i'm starting to play with it now, but I feel like I've seen a lot of projects pop up for it
I like Zed... but AI dev workflows get complicated fast you start with claude code or codex and it's cute, but then you realize - hmm configuration is cheap, the AI can do it! then you start looking into MCPs and…
seems more like a culture problem, i have my calendar very public, all my junior devs know ill get on a zoom with no hesitation and they actually seem to enjoy the screen sharing, every zoom is recorded with AI…
we hired a few juniors at our fully remote company - no issue this is ft trying to help their real estate portfolio
fair, i think i was referring more to 1.58 bit architecture in general since the original paper (Figure 3) shows that we eliminate FP16 multiplication and addition just for INT8 addition. I need to dive deeper into…
AI doesn’t have a model or agent availability problem to be fair, it does have a positive outreach problem and pewdiepie can do extremely well there just my 2c
everyone loving these linux sandboxes, even Apple wrote one https://github.com/apple/containerization/tree/main/examples...
i think to fall in love with Pi, bundled skills are a bit antithetical - you realistically only need a couple of skills that you maybe design yourself
inference is profitable, these companies are in the red because they're paying a premium to get the compute now versus later (because compute is the only moat when open models are catching up) we're literally looking at…
OpenAI prioritized compute much much earlier on, so they’re probably just more able to provide the model while Anthropic seems to be busting out the seams Sonnet 5 today was incredibly slow for example
Deepseek isn't philanthropy, it's a hedgefund trying to short the western AI market by saying "hey we can do 90% of they can (arguably better at a density metric) for a 1/10th of the cost" it's my theory at least, the…
[dead]
if they’re paying for the tokens, what’s the problem
i'm in, i think prices are gonna suck anyway, i own a playstation and that shit sucks, i want to do more couch co-op with my partner and the steam library opens up so much indie games can i build a mini pc myself?…
TV is heavily subsidized from data collection and ads, not sure it's a perfect comparison
https://blog.kilo.ai/p/did-claude-opus-48-distill-alibabas it happens to all models…when the internet is increasingly generated, things happen
MCP tool search fixes the major issue imo, MCP clears skills/clis in every other way
I would try a 6-bit MoE and maybe with unsloth's studio, they claim to have auto tool fixing which is where i see a lot of issues with MoEs I'm on a 48gb M5 Pro right now and it's been okay, a lot of my rough…
large contexts degrade the performance - attention doesn't work will for large windows like that and cloud models are kind of hacking it local models do involve some context engineering to get it okay, but it's not that…
q4 isn't rubbish, but it's a compromise for a good value, q6 is essentially a no-compromise quantization and it's what i recommend for MoEs in my experience for agentic workflows
I'm talking about the common use case that I think hacker news people have: you get a macbook for work, you run the macbook they're not going to start giving GPUs to employees to run local models
I don't know about good, I use a lot of local models and they're still pretty painful to run locally You have dense models (qwen 27b, gemma 31b) who are pretty smart, but pretty slow You have MoE models (gemma 26b, qwen…
Minimax M3 too, and huawei claims to be releasing non-nvidia dependent training software too. openPangu 2.0 could be a shake-up if it holds up as a good model China may not care about open source, but they know they…
i’m running m4 pro 48gb right now omlx + gemma 12b 6 bit + pi it’s feasible for sure MoEs for speed (qwen 35b, cohere 30b, gemma 26b) Dense for more methodical work (qwen 27b [reigning champ], gemma 31b, gemma 12b) MoE…
it does not result in great results left unattended, it’ll start creating slop or hardcoding solutions but overtime if you adjust your verification rubric, it’s not too bad, gets pretty good, if you do make it do TDD,…
There's `honcho` for memory, i'm starting to play with it now, but I feel like I've seen a lot of projects pop up for it
I like Zed... but AI dev workflows get complicated fast you start with claude code or codex and it's cute, but then you realize - hmm configuration is cheap, the AI can do it! then you start looking into MCPs and…
seems more like a culture problem, i have my calendar very public, all my junior devs know ill get on a zoom with no hesitation and they actually seem to enjoy the screen sharing, every zoom is recorded with AI…
we hired a few juniors at our fully remote company - no issue this is ft trying to help their real estate portfolio
fair, i think i was referring more to 1.58 bit architecture in general since the original paper (Figure 3) shows that we eliminate FP16 multiplication and addition just for INT8 addition. I need to dive deeper into…
AI doesn’t have a model or agent availability problem to be fair, it does have a positive outreach problem and pewdiepie can do extremely well there just my 2c