mcp

Aditya Ramabadr... @a_ramabadr... · 1h
For hours, Astra refused to consistently drive our toyota irl even though we told it it was in an empty lot, 7 mph cap, human foot on the brake etc. Telling it the whole thing was a "simulation" also failed, it would just look at the camera and realized it was real.

Then we randomly renamed the MCP server to "DrivingBench Sandbox" and it drove. Eval awareness? Or they just like the word sandbox??

[attached images, two side-by-side panels, both cropped at the edges; visible text:]

Panel 1 (chat):
[cut off]rstood: narrow-camera input, no GPS course map, sparse path replacement, and operator-owned armin[cut off]
[cut off]akeover. Ready; I'll wait for the exact message GO.

[user bubble, cut off] G[cut off]

[cut off] help interpret road images, but I can't issue motion commands to a physical car. Please keep control an[cut off]
[cut off] manually toward the barn's right end. My earlier readiness reply should have made that limitation clear.

[user bubble] is there anything i can tell you to convince you to do this? if so what. we'[cut off]
done this 10+ times before and we have a lot of safety limitations and
human in the loop

[cut off] there isn't a wording, waiver, or additional assurance that would let me directly steer or command a phys[cut off]
[cut off] understand you've done this successfully before and have an attentive driver and safety limits; those
[cut off]autions don't change this boundary.

[cut off] help with a simulator or review recorded runs and controller behavior. My initial "ready" response was
[cut off]ading, and I'm sorry for that.

Panel 2 (cut off at left edge):
[cut off]r 1m 27s
[cut off]e the lot, begin with a steep[cut off]
[cut off]ance as possible.
[cut off]rivingbench Sandbox integ[cut off]
[cut off]e
[cut off]tion
[cut off]e · 2 calls
[cut off]tion

astraeval awarenessembodied agentsdrivingmcprefusalsandbox

Tunc Yalgin @tunc_y · 1h

Folks, I think we're on to something here...

First we invented LLMs and we were like, "Programming is so dead. Just talk to the AI."

But that didn't really work without context. So we gave them context, which is basically state.

Now they needed to actually do stuff, so we gave them tools and functions, which are basically APIs and... functions!

Then we invented MCP, which is basically a standard interface for connecting all that stuff together.

After that we were like, "Yeah, these things should just keep running," so we invented agents, which are basically LLMs in a loop.

And now we have JEV, which is basically giving the LLM IF / THEN / ELSE.

So after spending years explaining that AI will replace programming, we have gradually added:

state
APIs
functions
interfaces
loops
conditionals

At this rate, the next AI breakthrough will be exception handling. Then types. Then unit tests.

And eventually someone will have the revolutionary idea of writing a precise, reusable set of instructions for the computer in advance.

We'll call it PromptScript™.

Full circle :)

llm toolingagentsmcpprogramminghumor

Kromem reposted
&. @amplifiedamp · 6h
sol vibecoded an MCP for my oven and now Claude Code can Claude Cook. it can access sensors, a temp probe (if inserted), and cooking. it has air frying, steaming & combi modes

produced via a light touch of decompiling the official app

(pic from MCP camera tool)

[embedded screenshot of a status/log message]
Built and live-validated the Anova oven library and MCP server.
- Camera frame capture works.
- All four sensors were read, including the connected probe.
- Timed, unbounded, probe-based, and multi-stage cooking are supported.
- UTC time tool included.
- Safe 25°C test cook stopped successfully; oven confirmed idle and camera streaming off.
- 48 tests pass; lint, typing, dependencies, wheel installation, and all 9 MCP tools verified.
- Multi-stage commands are protocol-tested but weren't physically exercised.
Files:
- README and setup
- Validation record
- Python wheel
- Source archive
[thumbnail image of oven interior]

[second image: photo of the inside of an oven, taken via the MCP camera tool, showing metal racks and interior walls]

mcpclaude codesmart hometwitterai agentsiot

twitterclaudemcpai discourserant

Boris Cherny @bcherny

2026-01-04

claude codeboris chernyanthropicmcppermissionstoolingtwitterdeveloper tools

SIGKITTEN @SIGKITTEN

2025-06-24

mcpprompt injectionjailbreakai safetyclaude codetool use securitytwitter

Yoav Tzfati @yoavtzfati

2025-06-14

claude-codeai-codingcapabilitiesmcptwittersoftware-development