Hacker News: ThibWeb

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 21:34:06 +0000

Might do more of that next time! Inference was with TensorX and Neuralwatt.

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 21:32:17 +0000

The high usage was due to omp in vibe mode overnight, probably working way too hard through things. The high cost, yes we’d rather pay extra to work with providers that provide other benefits than just lowest cost possible (open models, no training, EU DC, etc)

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 20:53:51 +0000

No those numbers are GPU only. See https://cleerdash.sustainableaigroup.com/ for a fuller model

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 20:51:39 +0000

For what it’s worth the energy numbers I get from Neuralwatt are within the ballpark of what is available elsewhere like https://cleerdash.sustainableaigroup.com/. What’s your source that there is profit / capex in there? Their published methodology seems pretty transparent

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 19:52:21 +0000

I agree but it does worry me how fast my usage is increasing. Two months ago I was using 10x less tokens and probably not much more than 5kWh on inference. This month about 30kWh on inference. If it becomes more affordable, is there going to be another jump? Not quite sure

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 19:41:52 +0000

Yep, I think next month will be on that. It feels slightly better from a few days of use, and in our WIP benchmarking it scores way higher

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 19:37:53 +0000

I have a hard time justifying GLM 5.3 these days. It’s slightly better than Flash but rarely enough to justify the much steeper price. We chose to use usage-based billing only so are very sensitive to model price.

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 19:34:32 +0000

Yes, all from Neuralwatt, GPU energy use only. Makes models’ “efficiency” much more visible than tokens.

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 19:33:26 +0000

Hmm I might need to rephrase. Initial challenge was to use GLM 5.3 Flash and I was on the non-Flash version for the whole vibe coded build. Just wasn’t paying attention and I didn’t realize that one session was a quarter of the month’s spend and 150% of the budget (big price difference between models)

New comment by ThibWeb in "One month coding with GLM 5.3 Flash"

ThibWeb — Fri, 02 Oct 2026 15:29:15 +0000

It was a bit of a silly challenge, wasn’t sure how workable, learned a lot in the process about what actually drives usage / costs, and how to keep both under control

One month coding with GLM 5.3 Flash

ThibWeb — Fri, 02 Oct 2026 15:29:15 +0000

Article URL: https://wagtail.org/blog/one-month-on-glm-53-flash/

Comments URL: https://news.ycombinator.com/item?id=49934620

Points: 92

# Comments: 74

New comment by ThibWeb in "CMS with AI, Not AI CMS: Wagtail 8.0's New API"

ThibWeb — Thu, 27 Aug 2026 17:58:12 +0000

done, added three options to the blog post! ty for the feeback

New comment by ThibWeb in "CMS with AI, Not AI CMS: Wagtail 8.0's New API"

ThibWeb — Thu, 27 Aug 2026 17:49:47 +0000

Good point, i’ll fix that. Instructions are here: https://github.com/wagtail/bakerydemo#api-demo

New comment by ThibWeb in "CMS with AI, Not AI CMS: Wagtail 8.0's New API"

ThibWeb — Thu, 27 Aug 2026 17:44:52 +0000

Let us know how it goes! This is very new for us so feedback is key

Braindump: Extract coding rules from PR review comments

ThibWeb — Thu, 27 Aug 2026 16:36:19 +0000

Article URL: https://github.com/pydantic/braindump

Comments URL: https://news.ycombinator.com/item?id=49467537

Points: 2

# Comments: 0

CMS with AI, Not AI CMS: Wagtail 8.0's New API

ThibWeb — Thu, 27 Aug 2026 16:32:21 +0000

Article URL: https://wagtail.org/blog/cms-with-ai-not-ai-cms-wagtail-80s-new-api/

Comments URL: https://news.ycombinator.com/item?id=49467481

Points: 38

# Comments: 9

Comparing open weight AI models and providers

ThibWeb — Wed, 01 Jul 2026 12:40:35 +0000

Article URL: https://wagtail.org/blog/comparing-open-weight-ai-models-and-providers/

Comments URL: https://news.ycombinator.com/item?id=48745748

Points: 1

# Comments: 0

New comment by ThibWeb in "Twenty Years of Django Releases"

ThibWeb — Wed, 19 Nov 2025 18:55:43 +0000

Data on the number of releases comes from ecosyste.ms which was very convenient to do this while comparing with other packages outside PyPI. For what it’s worth, Rails is at 510 on there, which I believe is all releases since 2004. And Laravel is at 247 but there’s 2-3 years missing

New comment by ThibWeb in "Uv overtakes pip in CI"

ThibWeb — Mon, 13 Oct 2025 23:12:11 +0000

it’s my 1st attempt at reporting on CI downloads specifically. Interpreting this is more of an art than a science, I’d love to hear if others have ideas on what to do with this data!

New comment by ThibWeb in "Uv overtakes pip in CI"

ThibWeb — Mon, 13 Oct 2025 23:05:20 +0000

for me the surprise is the pace? I’d expect people to be more set in their tools that it takes longer than a few months for a new tool, no matter how good, to become the majority use one. Though perhaps people adopt new tools more easily in CI where install times matter more