Towry Wang / 涛 (@towrywang) header
Towry Wang / 涛 (@towrywang) profile picture
Shanghai
Joined January 2011
Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)Photo by Towry Wang / 涛 (@towrywang)
"If you only do what you can do, you'll never be better than what you are"
1
3
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
hot take: you don't need a software factory, and i don't love the term. it's just marketing all you need is good software engineering and investing your tokens in the right places. the more deterministic the better (and token efficient)
59
23
10
458
24,505
Towry Wang / 涛 retweeted
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-…
23
66
13
378
60,439
时间过得好快,biden 执政感觉还是不久前
1
18
claude pro/20 plan, using sonnet to build a tool, Its such good deal.
1
46
Towry Wang / 涛 retweeted
Hey @Railway, is there a reason employee's of yours are trying to breach my infrastructure? Your employee Jake Runzer, just attempted to tonight.
228
344
272
9,532
2,923,236
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.
190
300
112
6,657
569,962
Creating an amp plugin to improve the low mode model's behavior. The behavior rules are maintained manually.
27
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.
12
7
2
159
9,279
Using deepseek flash max in ampcode, DS does't follow the workspace state check rule, keep editing in wrong branch. Harness still matters.
4
1
497
Previously I only had a few lines here about some preferences, like renaming the thread, but I've had to add so many things to make DeepSeek Flash work in line with the rules and skills. It does works.
11
Have to use a plugin to keep remind the agent to follow the user's global rules.
16
Grok 目前只会回答一些废话了。
11
Towry Wang / 涛 retweeted
What the actual fuck! The internet is full of stupids. Look how this fabricated now lol. "Secretly tried to reach Beijin".. 🍭
6
3
64
2,594
Don't use minimax m3.1 flash, it does't not follow the rule: never inspect secret keys.
34
Towry Wang / 涛 retweeted
What has stayed the same and what has changed — Jinan济南 across 700 years.
157
2,617
50
33,746
1,024,831
Towry Wang / 涛 retweeted
香港政府担心你找不到深圳
398
669
87
10,310
739,419
Towry Wang / 涛 retweeted
No. In my tests, it wasn't even as impressive as DS.
1
3
145
Is this agent harness? Plugin success prevent model mistake.
1
32
真够奇葩的,一个 classifier 模型,还有什么可屏蔽的。
14