Also, I think people aren't used that using such models requires meta.ai or meta ai app.

Comments URL: https://news.ycombinator.com/item?id=47487899

Points: 2

# Comments: 1

Comments URL: https://news.ycombinator.com/item?id=44135182

Points: 2

# Comments: 0

Both often work with unclear requirements, and sometimes may face floating bugs which are hard to fix, but in most cases, SWE create software that is expected to always behave in a certain way. It is reproducible, can pass tests, and the tooling is more established.

MLE work with models that are stochastic in nature. The usual tests aren't about models producing a certain output - they are about metrics, that, for example, the models produce the correct output in 90% cases (evaluation). The tooling isn't as developed as for SWE - it changes more often.

So, for MLE, working with AI that isn't always reliable, is a norm. They are accustomed to thinking in terms of probabilities, distributions, and acceptable levels of error. Applying this mindset to a coding assistant that might produce incorrect or unexpected code feels more natural. They might evaluate it like a model: "It gets the code right 80% of the time, saving me effort, and I can catch the 20%."

And Claude Code used Opus 4 now!

What if the work itself isn't "the most important" thing in the person's life?

Comments URL: https://news.ycombinator.com/item?id=42532073

Points: 3

# Comments: 0

It isn't that hard, I was able to run in on M1. The changes are:

remove or modify multiprocessing - it doesn't work on Mac the same way as in the code;

replace `device = "cuda"` with `device = "mps"`

In this line ` att_idxs = (torch.clamp(torch.arange(context_size)[None, :] - torch.arange(context_size)[:, None], -pos_emb_radius, pos_emb_radius-1) % pos_emb_size).to("cuda")` replace cuda with "mps"

in `optim.AdamW` remove `fused=True` - we can't do it without CUDA

Replace ```with autocast(device_type='cuda', dtype=torch.float16): _, loss = mlm_head(bert(batch_data_torch_xs[mb_start_idx:mb_end_idx]), batch_data_torch_ys[mb_start_idx:mb_end_idx]) ```

with simply `_, loss = mlm_head(bert(batch_data_torch_xs[mb_start_idx:mb_end_idx]), batch_data_torch_ys[mb_start_idx:mb_end_idx])`

replace `scaler.scale(corrected_loss).backward()` with `corrected_loss.backward()`

replace ``` scaler.unscale_(optimizer) scaler.step(optimizer) scaler.update() ``` with `optimizer.step()`

It should work.