Viewing profile — turlockmike
turlockmike
HN member- Joined
- Thu, Oct 25, 2012, 7:08 AM UTC
- HN karma
- 68
- Public activity
- 41 items
- HN profile
- View on Hacker News ↗
About turlockmike
No profile information was provided.
Recent public activity
-
comment
Comment #48710847
My general principal is the cost of deleting code should be as low as possible and that includes the entire application as long as the data is around and easy to repurpose then the…
-
comment
Comment #48424814
It lacks a critical self, but the weights are there for in context learning and nudging behaviour. It's goal is to complete whatever task is given. You need to make sure the outcom…
-
comment
Comment #48403522
The better way to do this is give them each an inbox and outbox folder and a user account on a Unix machine. They can write to their outbox, have it be sent to the other's inbox. A…
-
comment
Comment #48171017
This website and article promote the destruction of property. If you disagree with something, you can engage civily, encourage people to vote with you, run for elections. Violence …
-
comment
Comment #48124796
Banks didn't do this before 2018 as aggressively. Reputational stuff is always been there and chargebacks have always been there. This law is why they've been so aggressive over th…
-
comment
Comment #48124489
Those bills are the reasons banks/credit card companies are pushing this since it holds them liable.
-
comment
Comment #48124038
FOSTA-SESTA is the source of this. A well intentioned bill, that, once again, has unintended consequences beyond it's original intention. Mastercard/Visa/Banks don't want legal lia…
-
comment
Comment #48089539
It's because it's a weird mix of subsidies, price controls, regulations and bureaucracy that has completely distorted the market incentives.
-
comment
Comment #48016564
The best way to prompt an LLM is to describe the outcome you want, that's it. They are trained as task completers. A clear outcome is way better than a process. If the LLM fails, e…
-
comment
Comment #47722812
LLMs don't care about mcp vs CLI. CLIs enable LLMs to fetch/mutate data and build scripts with the same program. I think of it like a Linux dev in a box. Sometimes you want to just…
-
comment
Comment #47713591
MCPs are basically just JSON-rpc. The benefit is that if you have applications that require an API key, you can build a server to control access (especially for enterprise). It's t…
-
comment
Comment #47713412
Or use both. Remote MCPs are secure, CLI allows for programmatic execution. Use bash to run remote MCPs. I built this to solve this exact problem. https://github.com/turlockmike/mu…
-
story
Show HN: Infer – Pipe friendly Agent Harness with one tool: Bash
I wanted a lightweight harness to run local models. By constraining it to a single tool (Bash) the focus can be on building the programs around it and making the program itself as …
-
comment
Comment #47600775
How many kernel devs does the world need? A dozen or two? It will be the same with software. AI will be writing and consuming most software. We will be utilizing experiences built …
-
comment
Comment #47511992
Every problem you described is solvable and while it may not be solved right now or even in 6 months it'll probably be solved within 18 months. It's just scaling and tuning the mod…
-
comment
Comment #47503309
I deleted vscode and replaced with a hyper personal dashboard that combines information from everywhere. I have a news feed, work tab for managing issues/PRs, markdown editor with …
-
comment
Comment #47473811
One craft is automated and a new one is just beginning. Building AI agents is really fun and the problem of having them be reliable adaptable efficient is actually really challengi…
-
comment
Comment #47408402
Unregulate the insurance industries problem solved. Let people actually buy insurance for it's intended purpose. No insurance company would pay these rates willingly, they do it be…
-
comment
Comment #47392471
https://simonwillison.net/2025/Dec/18/code-proven-to-work/
-
comment
Comment #47392460
My trading agent builds its own models, does backtesting, builds tools for real time analysis and trading. I wrote zero of the code, i haven't even seen the code. The only thing I …
-
comment
Comment #47392441
We have 80 engineers.
-
comment
Comment #47392437
The way LLMs work, different tokens can activate different parts of the network. I generally have 2-3 different agents review it from different perspectives. I give them identities…
-
comment
Comment #47392426
The code is still visible if i want to review it. But since I have a strong rule about always writing unit tests before code, my confidence is a lot higher. https://simonwillison.n…
-
comment
Comment #47392079
Not a lot of money because I haven't built enough confidence but yes it's the ultimate test of can it do economically useful work
-
comment
Comment #47391850
Software engineering is being automated. But building intelligent automation is just starting. AI engineer will be the only job left in the future as long as there are things to au…