Any conversation

I think it will still apply, just perhaps to a lesser degree. Kind of related to this blog postevnm.substack.comPlatform engineering still mattersReuse is a good thing, even with agentic coding I wrote recently (not to shamelessly plug my stuff 🫣)

My biggest problem nowadays is realizing that the coding was never the real problem, it was always lack of domain knowledge, lack of specs or just conflicting visions.

i think the best you can get right now is qwen 3.8 27B. youre gonna need 24 gigs of some fast memory though, i heard theres decent quantizations that can also make it run on 16. im quite excited about open/local models, but theres big investment overhead with the prices right now

You might be able to try out colibri, its quite good and the models are a bit better. I am unable to connect any of the cli agents to do things with it though, probably due to context limits, but try it out. OlMoe is the lightest

Do resumes bring interviews anymore? Do they at least bring rejection notes? :D I had a docker/ubuntu/latex setup to build my resume until I switched to Typst. I find Typst quite well suited for the job.

Hati-hati pak! I worked in Borneo before, and seeing the forests burn is horrifying. I miss all the wildlife there. Mau kembali ke Indonesia!

Does it do some kind of polling? Is there some kind of notify like publisher subscriber? 🤔

It’s using the /firehose /apitextlogAPIA quieter place for your thoughts. endpoint. It’s an SSE endpoint publishing everything latest. Though I meant it to be used server-side, since it’s heavily rate-limited — up to 3 conns under the same network, but I can’t control how clients decide to use it so.. ¯\_(ツ)_/¯

The “you have seeing it all”, etc.

Improved. Still don't know what to do there. Maybe bring back a separate tab for inbox? wdyt?

I don't think so. I have been using more open source software than ever before. You may argue that with LLMs I have the power to make my own stack of things, but this doesn't eliminate that I still need knowledge to properly steer an LLM to create something worthwhile. If I have no knowledge of what I intend to build, the best thing the LLM will generate is a half-assed copy of something that already exists. Which is what we have been drowning in the past couple of years.

Of course not. I think it is much more relevant to ask "Is closed source dead?". Anyone can now replace a proprietary program with a vibeslopped alternative which might suit them just as well. It will have the same level of trust (ie. none) and none of the other drawbacks.

it'll always be that way, sadly

The scientist's job is to never stop searching. The leader's job is to stop searching and decide. Trouble starts when either forgets the other exists.