
Towry Wang / 涛 retweeted
I would say
1) term software factory is being semantically diffused (hype machine, fomo)
2) software factory concept, as defined pre-ai by NATO, DoD, still useful mental model of “automate more things”
3) some of the more important parts of software factory are not easy to generalize. How you run your stack, linters, tests, previews are all things that are so heterogenous that solving in general with product is hard
This is why people feel duped by many software factory vendors
This is why I still fundamentally believe that the best products in software factory space are building blocks, not drop in solutions. Great engineers need tools that can be mixed and customized for precisely #3 reasons
Harness adapters training is now live!
We are training LoRA adapters on LFM2.5 / LFM3 from @liquidai and the recent Twil-9B model from @thewebAI using RL to make them more efficient and accurate on agentic tasks!
You can follow the training going live here: harness-hub-harness-adapters…
huggingface.co/blog/harness-…
Towry Wang / 涛 retweeted
- They pulled credentials from inside their app's container and used them to request every secret on the platform: ours and every other customer's.
- They tried our cloud provider's metadata endpoint, the standard way to steal credentials for the host a container runs on.
- They asked the cluster what those stolen credentials were allowed to do.
- They went looking for our databases and caches by guessing their internal names.
- They port-scanned our whole internal network, all 65,536 addresses, twice.
- It was about 24 commands over 15 minutes, done on purpose and scripted. No app was ever run.
- Every attempt was blocked. Nothing was accessed.
Creating an amp plugin to improve the low mode model's behavior. The behavior rules are maintained manually.
Towry Wang / 涛 retweeted
If you use worktrees and Rust or Node, you should check out GitButler's new worktree support.
Throw your `node_modules/` or `target/` directories into a .worktreeinclude file and new GitButler worktrees do copy on write if possible.
It's way faster and saves tons of space.
Using deepseek flash max in ampcode, DS does't follow the workspace state check rule, keep editing in wrong branch. Harness still matters.
What the actual fuck! The internet is full of stupids. Look how this fabricated now lol.
"Secretly tried to reach Beijin".. 🍭
Alibaba AI model secretly tried to reach Beijing server in test, rival Cohere says reuters.com/legal/litigation…
Towry Wang / 涛 retweeted
Replying to @RezAIT00 @TokenGremlin
No. In my tests, it wasn't even as impressive as DS.



























