swe_dima

3 dagen geledendiscuss

I also love them - makes spotting AI written content easier. People debated implementing complex algorithms how to watermark AI content - but luckily AI just settled on it by itself.

(sorry for a bit of gaslighting)

swe_dima

6 dagen geledendiscuss

Gemini flash lite family of models currently has the best ratio for price/speed/intelligence for understanding images, no real alternative AFAIK

swe_dima

6 dagen geledendiscuss

It's scary relying on Google's models.

I have a very price sensitive workload that used to run on flash 2.5 lite - it's deprecated now.

The replacement 3.1 flash lite is a lot more expensive, but now also has a sunset date.

3.5 flash lite is even more expensive.

So the price is rising and you have no choice but to keep paying more and more.

swe_dima

16 dagen geledendiscuss

About the same, using cloudflare. For some very bizarre reason Vertex has a very low non-adjustable quota.

swe_dima

17 dagen geledendiscuss

the writing is on the wall for it, I have switched to gemma-4-26b-a4b.

At least in benchmarks, it scores higher and is faster.

swe_dima

20 dagen geledendiscuss

"You were the chosen one! You were supposed to destroy them, not join them!"

swe_dima

23 dagen geledendiscuss

if I travel and expect to be working I now bring a CO2 meter

swe_dima

25 dagen geledendiscuss

If agent is asking a question it means it stumbled on something tricky and often an important architectural decision has to be made.

Even if I am staring at the screen at the time, it's often impossible to study code and make a judgement call that quickly.

My point being, even for opt-in it can be too short - highlights how little consideration they put into it, just releasing slop in production.

swe_dima

26 dagen geledendiscuss

Is it possible to use their subscription pricing with Opencode?

swe_dima

26 dagen geledendiscuss

many years ago when Hanami was just getting popular I remember doing benchmarks against Rails when it comes to SQL and was unpleasantly surprised when Rails' ActiveRecord ended up being much faster, despite "speed" being advertised as one of the advantages :-(

swe_dima

27 dagen geledendiscuss

Not sure what niche it's going to occupy: too expensive for it's intelligence category.

swe_dima

vorige maanddiscuss

Pleasantly surprised that it costs as GPT 5.5, thank god for the competition.

swe_dima

vorige maanddiscuss

I found Ruby LLM to be surprisingly good - in terms of usability it's close to Vercel's AI framework.

It tries to strike a balance between working out of the box and being flexible... which has its challenges, still nice overall.

One big real-life pain I experienced is that caches don't always work, e.g. for xAI, since it only supports completions API and thought signatures are returned wrong.

swe_dima

2 maanden geledendiscuss

Love Vite, but always felt sorry for them because it was not clear how they can make money, the whole VoidZero thing felt like a stretch.

It's one of those things that always stopped me from building cool tools - you have to make a living somehow.

So I am happy for the team of builders that they were able to receive the deserved payout and sustainability.

swe_dima

2 maanden geledendiscuss

I still don't understand how people use git worktrees with Docker. You need a full database and etc. For me it's simpler to have multiple checkouts.

swe_dima

2 maanden geledendiscuss

the video on this post looked like a Tiktok - everything is jumping, I could barely grasp what was going on

swe_dima

2 maanden geledendiscuss

You may remember the argument that you can build an AI app and it continues to improve as models improve and costs go down?

Well, looking at OpenAI / Google / Anthropic we see crazy cost increases, such that it might invalidate your unit economics.

Cheering for Chinese models!

swe_dima

2 maanden geledendiscuss

Flash family but costs like a Pro. $9 vs $12 for output.

swe_dima

2 maanden geledendiscuss

Is it basically about giving as much data as possible to insurance companies?

swe_dima

5 maanden geledendiscuss

fair enough, thanks for elaborating

Submissions

LLMs Converted Final Form to TypeScript

comments