g023

5K posts

g023 banner
g023

g023

@g023dev

developer/programmer/ai nerd

Canada Sumali Ekim 2023
2.3K Sinusundan515 Mga Tagasunod
Naka-pin na Tweet
g023
g023@g023dev·
So I optimized the model, i optimized the harness, now I'm optimizing the endpoint by making an openai api to deepseek endpoint proxy that has some context compression features automatically integrated to attempt to save $$$ (works well with copilot): gist.github.com/g023/c2bb7b540…
English
0
0
4
291
Tristan Rhee
Tristan Rhee@Tristanrhee3·
how do you know if you’re building stuff people actually want?
English
62
1
38
2.7K
g023
g023@g023dev·
They should have an Opus slow version at half price by utilizing more available hardware even if it results in slower performance.
English
0
0
0
2
g023
g023@g023dev·
@merlinaudio_ I prefer it for remembering what was done where, but still like to make excuses to burn my opus rips.
English
0
0
1
42
merlin
merlin@merlinaudio_·
in the age of AI at least some of us still code by hand
English
43
35
758
73K
g023
g023@g023dev·
Check out Matthew Wesley on Facebook from Regina, Sask
g023 tweet media
English
0
0
0
10
g023
g023@g023dev·
@n3r4 @vineerpasam Yep. They pointed at a mazak and said can you program this, and I was like yup and bam I got that job. Modern problems = modern solutions and all.
English
0
0
2
16
quick
quick@n3r4·
that's a dumb interviewer. As a machinist/fabricator for 30+ years. we dont ask ppl to recite the machinery handbook, or specifics on weld amperage/wire speeds or pen depth.. or all of gd&t or cad/cam post processors. Even the most skilled 'engineers' cant answer them on the spot. bottom line is.. can they use their tools. id fire the interviewer. find someone that knows how to find talent.
English
1
0
1
140
Vineer
Vineer@vineerpasam·
My vibe coder friend built multiple AI apps over the past year. He went into an interview yesterday thinking the company would be impressed by his project showcase. The interviewer asked him the difference between Git merge and Git rebase. My friend has never even pushed code without Claude Code's help 😭
English
82
20
796
157.4K
g023
g023@g023dev·
Do you believe in Magic? (@deepseek_ai v4 powered)
English
0
0
1
18
g023
g023@g023dev·
@tapodhana_ use llamacpp server. Way faster and more compatible.
English
0
0
0
16
tapodhana
tapodhana@tapodhana_·
Spent 2–3 hours setting up ollama, only to end up with dumb models that can’t even use hermes tools properly. Any local models that actually work well for instruction following and tool calling on 16gb ram and 6gb vram? Currently using gemma4:e2b(doesn't work!)
tapodhana tweet media
English
3
0
6
337
Yoshinori Oota
Yoshinori Oota@oota_yoshinori0·
ほう。試してみるか。
ollama@ollama

Gemma 4 Quantization-Aware Training (QAT) weights are now available on Ollama! They reduce memory requirements while maintaining model quality. E2B: ollama run gemma4:e2b-it-qat E4B: ollama run gemma4:e4b-it-qat 12B: ollama run gemma4:12b-it-qat 26B: ollama run gemma4:26b-a4b-it-qat 31B: ollama run gemma4:31b-it-qat Try them with ollama launch integrations to use with your favorite tools 👇👇👇

日本語
2
0
6
3.2K
g023
g023@g023dev·
@RoyShilkrot ... also a lot less reading to see what it messed around with.
English
0
0
0
10
g023
g023@g023dev·
@RoyShilkrot it truly does help to isolate and work on the problem as a component, rather than the whole, for speed and token efficiency. Especially when dealing with smaller models for tasks.
English
1
0
1
11
Roy Shilkrot
Roy Shilkrot@RoyShilkrot·
The bigger your software project is - the higher the context token cost is. Therefore the KISS principle in software dev still holds, 40 years after its inception. Intelligence is intelligence. Artificial or Human. Holding too much in context doesn’t scale. Keep small. Pay less
English
1
0
2
268
g023
g023@g023dev·
@hyuki I mean 12b would be a bit large for that task for most people and might be really slow on large volumes of pics. You can find some nice ~2b models that can do a good enough job for most purposes.
English
0
0
0
137
結城浩 / Hiroshi Yuki
結城浩 / Hiroshi Yuki@hyuki·
LM Studio + gemma-4-12b-qat でOpenAI コンパチなAPI持つローカルサーバ立ち上げると、無課金で画像処理AIが使える。たとえば大量のスクリーンショットや写真の分類整理やタグ付けにはぴったりではないだろうか。クラウドに出すのに抵抗があり、分量が多く、スピードと精度はそこそこで良い。
日本語
12
79
510
51.4K
antirez
antirez@antirez·
@ivanfioravanti No, if it misrepresents models in random ways, how is it good? Only because 5.5 happens to be on top?
English
4
1
14
2.1K
antirez
antirez@antirez·
For days, many folks here are citing DeepSWE as the benchmark that restores reality only because it shows GPT 5.5 on top. But actually, it almost gets a single entry right: the top one, and all the rest is shuffled.
English
16
2
158
27.3K
g023
g023@g023dev·
@lmrankhan depending on the task, cleaving out the subagents altogether gives some surprisingly good results.
English
0
0
0
24
Imran
Imran@lmrankhan·
A lot of people are talking about running tons of agents, parallel workflows, skills, and orchestration layers. Honestly, for building an app, I've found two coding agents running in async works perfectly fine, Codex for backend and Opus/Claude Code for frontend. Haven't had to use more than that, skills, or complex workflows. The bottleneck is usually figuring out what to build, not how many agents you're running or using any of the advanced workflows. I'm sure there are more advanced things people are doing, but for most MVPs or early stage products, simplicity works
English
65
18
323
31.5K
g023
g023@g023dev·
@yuhasbeentaken wow thats a pretty good incentive to burn tokens
English
0
0
0
12
Yum⋆₊˚
Yum⋆₊˚@yuhasbeentaken·
at tencent (china’s largest internet company), the token reimbursement quota is dynamic. the more you use, the more you get when it refreshes next month. so… it kinda looks like you’re incentivized to build side projects at work? 😂😂
Zack Korman@ZackKorman

Companies are like "we are spending all this money on AI but we don't know what the devs are even doing with it." Let me answer that for you: They're working on their personal side projects.

English
3
0
12
1.4K
g023
g023@g023dev·
@djcows Does give a bit of an esteem bump for the day when some bigwig top-dawg gives a response to your random yellings on the internet.
English
0
0
0
32
djcows
djcows@djcows·
you can dm some of the smartest people on earth here and they'll sometimes just answer casually, it's honestly crazy and humbling
English
22
3
153
3.2K
g023
g023@g023dev·
@RoguePoma I share a lot of my things in public, and yes sometimes they are pretty raw but useful to me. Always like to learn from others too.
English
1
0
1
7
Alex Poma 🏗️
Alex Poma 🏗️@RoguePoma·
I’m building construction SaaS in public while working full-time as an architect. I’d like to connect with more people doing the same kind of thing: - Building products. - Learning in public. - Sharing the messy times - Sharing the good times What are you building?
English
45
0
37
1.4K
g023
g023@g023dev·
@shyamalanadkat I think what would qualify as AGI would be a session that is always on, has infinite history that doesn't need to be cleared, and carries out its business on its own, either seeding itself with roles, or being directed to a role as a seed role.
English
0
0
0
43
shyamal
shyamal@shyamalanadkat·
early days of agi are going to be so special
English
5
3
51
3.1K
g023
g023@g023dev·
@rajyaligar @smhanov try using deepseek as a subagent and opus as orchestrator to stretch out the window
English
0
0
0
15
Raj
Raj@rajyaligar·
@smhanov Had to upgrade my codex sub this month from 5x to 20x cause the 5 hour window wasn’t cutting it for my workflows Big month for shipping
English
2
0
0
22
Steve Hanov
Steve Hanov@smhanov·
What was your AI bill? I've been using Claude Code and Hermes pretty heavily and up to $33 last month
Steve Hanov tweet mediaSteve Hanov tweet media
English
2
0
5
277
g023
g023@g023dev·
Made a deepseek powered agentic html editor tonite that runs amazing (of course because deepseek is amazing). Man we've come a long ways since Dreamweaver lol. Oh ya, deepseek made it too.
g023 tweet media
English
0
0
1
31

Tuklasin

@Tristanrhee3 @merlinaudio_ @n3r4 @vineerpasam @deepseek_ai @tapodhana_ @oota_yoshinori0 @RoyShilkrot