←
Diffco258 posts
Diffco avatar

Diffco

@Diffco_us

Your trusted AI software development partner

◷ Joined May 2014▧ 62 Photos and videos
Diffco avatar
Diffco@Diffco_us·Oct 8

"It's not models, it's always harness." Our CEO Vadim Peskov on the @GoodFirms podcast: why AI coding tools speed up typing but not teams, and what delivers 5-30X on real systems.

Coding was never the bottleneck in software. Deciding what and how to build is. On the @GoodFirms podcast I explained why AI coding tools speed up developers but rarely speed up teams, and why the harness matters more than the model. youtu.be/mzIGQUUgCYY

Vadim Peskov avatar
⟳ Diffco retweeted
Vadim Peskov@vadimpeskov·Aug 29

Soon you will be to can generate movie in real time and stream different view to each viewer

Today is a very historical moment for AI video generation You can now generate AI video faster than you can watch it Before it'd take let's say 2-5 minutes to generate 15 seconds of video @fal made a post-trained Minimax H3 variant called Max which is 50x faster than the original but still maintains quality It generates 15 seconds of video in 9 seconds! That means you can now do new things like build a perpetual livestream with it that never ends!

Vadim Peskov avatar
⟳ Diffco retweeted
Vadim Peskov@vadimpeskov·Aug 1

Better models don't mean better software. I went on @PaleBlueNexus to explain why — after 18 years of building software and a year of building it agentically. 4x cost reduction. ~100% AI-written code on new projects. And the one rule that makes it work 🧵 youtube.com/watch?v=4Zcf0qmP…

Vadim Peskov avatar
⟳ Diffco retweeted
Vadim Peskov@vadimpeskov·Jul 30

Multi-agent support system teardown: 4 iterations, 58% → 87% resolution. We didn't start at multi-agent. Single-agent failed first, and we earned each layer. diffco.us/blog/multi-agent-s…

Diffco avatar
Diffco@Diffco_us·Jul 30

AI Self-hosting math people skip: A GPU fleet sized for peak runs at 30–60% utilization → effective cost 1.5–3x the headline rate. Break-even is usually sustained hundreds of millions of tokens/day. Below that the API wins. diffco.us/blog/self-hosted-v…

Post attachment
Diffco avatar
Diffco@Diffco_us·Jul 30

Our hard rule for AI in regulated finance: Models propose. Deterministic services execute. The model never holds the keys to a money-moving API. Policy gates are unit-tested code, not prompts. The model can be wrong. The gate can't. diffco.us/blog/ai-in-fintech…

Post attachment
Vadim Peskov avatar
⟳ Diffco retweeted
Vadim Peskov@vadimpeskov·Jul 30

A vibe-coded product typically lasts 3–9 months before the foundations crack. The answer isn't "stop vibe coding." It's "don't vibe code forever." One engineer in the first 60 days costs a fraction of the rebuild at month 12. diffco.us/blog/why-you-still…

Diffco avatar
Diffco@Diffco_us·Jun 20

3/ Low cost + low complexity → automation Low cost + high complexity → agent (cautiously) High cost + low complexity → automation with human review High cost + high complexity → copilot Agents aren't the destination. They're one of three shapes.

Diffco avatar
Diffco@Diffco_us·Jun 20

2/ A framework for choosing agent vs copilot vs automation: Plot the work on 2 axes: — Cost of a wrong answer — Complexity of the path The quadrant tells you the shape. The buzzword doesn't.