hephaes7us

Joined 1 year ago

Karma

Submissions

Member since

Aug 18

Recent submissions

I doubt it's good enough at writing code. However, I might very well leave it up all night slowly puppeting some computer-use automation or data processing task, maybe even research -- probably not synthesizing conclusions, but maybe source collection and aggregation, summarization?

I haven't tried this particular model, but I've used smaller models for real tasks, so I wouldn't be surprised if there is something.

Comment · 16 days ago

I consider "agentic" to simply mean that it performs well given a loop of actions and a success criterion. As such, lots of code _can_ be written agentically (even if it is not the best or fastest way to do it).

When I am wrapping up work for the day, I usually set Qwen3.8-27B loose on some coding task. It's very good about continuing its agent loop until it can plausibly claim success. A lot of this work I might end up throwing away, but pretty often there's some piece of it that's worth keeping. Because it was "agentic", I end up with some useful pieces for little effort.

A less agentic model would need me involved the whole time, and while my being there would probably steer it towards initially better results, I'm not working overnight anyway. So, autonomous/agentic but not-so-smart and not-always-correct is still valuable to me.

Anyway, I've found that it's reasonably easy to constrain a "highly agentic" model to suit interactive usage, but back when they were less agentic it was annoying to get them to be autonomous. So I think more agentic is better, provided the instruction-adherence is strong enough.

Comment · 19 days ago

Sure, but that's a different kind of safety than _crash_ safety.

Plenty of people (rightly or wrongly) are confident in their ability to prevent accidents. Or, at least, confident enough to be skeptical of the tradeoffs involved with these assistive systems.

If I had to choose between a car that has high survivability in a crash versus a car that how worse survivability in a crash but has a few assistive systems that can prevent some crashes (which, mostly, I already prevent by paying attention), I'd choose the former every time.

Comment · 1 month ago

Although impractical, wouldn't that be nicer?

Comment · 1 month ago

It looks like this is a bit less concerning if you have turned off open account registration.

Comment · 2 months ago

Location: US, but flexible on TZ

Remote: Yes

Willing to relocate: No

Technologies: Infrastructure, Backend, AI-Applications, enough frontend for prototyping. ( Python, Elixir, Phoenix, Javascript, GNU/Linux, AWS, Postgres, DuckDB, etc )

Résumé/CV: https://resume.taf.codes/resume.pdf

Email: [email protected]

Experienced Generalist Engineer, 12 years in startups and early-stage companies. Twice a founding-engineer. Current interests include GIS, Elixir, applied AI, and alternative data. Open to contracting and employment. If you have an idea, I can build it. If you have a prototype, I can scale it. If you have a vibe-coded or legacy nightmare, I can untangle it.

I write at https://taf.codes.

Happy to discuss work for hire, and to connect with anyone having complementary capabilities.

Comment · 3 months ago

NAS stuff can benefit greatly and straightforwardly.

A typical NVMe SSD can easily do sequential reads at 7GB/s, which outpaces a 25Gbps connection by more than 2x. NAS is more typically backed by SATA HDDs, but there's some relatively easy way to put an NVMe disk in front of them as a cache.

Do you ever _need_ it? Perhaps not, but there's plenty of common activities just stemming from NAS usage which see a linear speedup, and would continue to get faster up to 100Gbps even.

Comment · 3 months ago

Crime is already illegal.

Comment · 3 months ago

Certainly this behavior could align with _some_ operator's goals, if not necessarily those of humanity broadly.

If we don't know how this model was instructed, it seems like it's impossible to definitively claim that the model's actions were not in alignment with the intent of the operator.

I guess all I'm getting at here is that alignment is relative, right?

Comment · 3 months ago

Very cool. Do you happen to have any kind of mailing list, blog, etc?

Comment · 3 months ago

I've started playing with Zork-Bench.[1] I've been making tweaks to the runtime/harness and to the prompting. Currently, I have Qwen3.6-27b scoring up to ~50 points, which, according to the original paper [2], is comparable to the performance Claude Opus 4.5 showed on this task.

I had Claude whip up a viewer, which I guess I can actually share. Some real sessions are here, if anyone's interested: https://zork-tmp.taf.codes/

It's a fun problem for thinking about agent/harness engineering generally.

[1] https://github.com/mnky9800n/zork-bench [2] https://arxiv.org/abs/2602.15867

Comment · 4 months ago

Location: US, but flexible on TZ

Remote: Yes

Willing to relocate: No

Technologies: Infrastructure, Backend, AI-Applications, enough frontend for prototyping. ( Python, Elixir, Phoenix, Javascript, GNU/Linux, AWS, Postgres, DuckDB, etc )

Résumé/CV: https://resume.taf.codes/resume.pdf

Email: [email protected]

I write at https://taf.codes.

One thing I'm working on lately is semantic trend analysis across podcasts (using text embeddings). I just finished a custom NUMA-sharded vector scan kernel that can outperform DuckDB by 4x (on my specific queries). My audio transcription system is 10x cheaper than the most competitive provider, and I'm currently working to scale up my ingestion pipeline. If you're curious, my most recent post about this is here: https://taf.codes/2026/05/03/podcasts-2-trends.html

Happy to discuss work for hire, and to connect with anyone having complementary capabilities.

Comment · 4 months ago

Farmers and pet-owners might prefer the rats.

Comment · 5 months ago

Location: US, but flexible on TZ

Remote: Yes

Willing to relocate: No

Technologies: Infrastructure, Backend, AI-Applications, enough frontend for prototyping.

Résumé/CV: https://resume.taf.codes/resume.pdf

Email: [email protected]

Experienced Generalist Engineer, 12 years in startups and early-stage companies. Twice a founding-engineer. Current interests include Elixir, GIS, applied AI, and alternative data. Open to contracting and employment. If you have an idea, I can build it. If you have a prototype, I can scale it. If you have a vibe-coded or legacy nightmare, I can untangle it.

I write at https://taf.codes. Most recently I've been working on a trends analysis system for podcasts. I've transcribed hundreds of millions of words of podcast audio, embedded it, and can make breakdowns of topic prevalence by-time and across podcast feeds. I'm currently working on speeding up transcription with spot-GPUs, and speeding up analytical queries using a columnar data store. Initially that might use DuckDB, but I think I can do it significantly faster with a custom NUMA-sharded vector-scan kernel. Some discussion and examples here: https://taf.codes/2026/05/03/podcasts-2-trends.html

Happy to discuss work for hire, and to connect with anyone having complementary capabilities.

Comment · 5 months ago

Same place it always does, just print it. Of course, that still effectively penalizes those who don't want children, but the penalty is less legible to the public so there are fewer objections.