Tommi Somersuo

@tommis

AI Tech Lead @ Solita.fi | Agentic engineering, architecture & governance. Offline: Runner, angler, RES/SRA, Tibetan Terrier owner.

798 Following2,154 Followers1,308 Posts

YouTube Bluesky

Is this your profile?Claim it and tommis.dirty.social is yours.Claim profile

Tommi Somersuo@tommis· 9d

Managing Docker telemetry 2030:

Tommi Somersuo@tommis· 20d

Fetch https://math.mino.mobi/conjectures (table is JS-rendered; crawl
the linked context pages for rows). For every entry tagged plain
"counterexample" — skip "deep" and "existence" — spawn an isolated
agent that first writes an executable exact-arithmetic verifier for a
candidate refuting object (if it can't, it stops), then authors its
own breakthrough prompt naming a concrete structural ansatz (in the
style of "Construct a counterexample to the general non-planar case
of X. You should do a breakthrough and find a structured
counterexample."), then loops propose → verify → log failed ansatz to
a ledger, never repeating a ledger entry, until the verifier passes
or a disk-based iteration cap the agent cannot edit runs out. Success
is only ever declared by the verifier. Report every terminal state;
nothing merges without my review.

Tommi Somersuo@tommis· 23d

Tommi Somersuo@tommis· Jul 11

Tommi Somersuo@tommis· Jun 3

microsoft.ai/news/introdu...

Tommi Somersuo@tommis· Jun 3

microsoft.ai/news/introdu...

Tommi Somersuo@tommis· Jun 3

New Microsoft AI models: microsoft.ai/news/buildin...

Tommi Somersuo@tommis· Apr 22

Visual Studio Code Agents is a new preview companion app that ships alongside VS Code Insiders: code.visualstudio.com/updates/v1_1...

Tommi Somersuo@tommis· Apr 13

x.com/marmaduke091...

Tommi Somersuo@tommis· Apr 3

Claude Code 2.1.9.1 includes likely fix for token consumption bug: github.com/anthropics/c...

Tommi Somersuo@tommis· Apr 2

docs.z.ai/guides/vlm/g...

Tommi Somersuo@tommis· Mar 24

Typoglycemia is a thing:

A plain three-column, nine-row table on a white background with no headers or borders, containing 27 typoglycemic variations of the word “Dependabot”

Tommi Somersuo@tommis· Mar 4

claude.com/blog/improvi...

Tommi Somersuo@tommis· Jan 31

hypercontext.sh : Hypercontext is a knowledge skill for Claude Code. Invoke /hypercontext and the agent introspects — threads, files, tools, remaining context — and renders a spatial ASCII map.

Tommi Somersuo@tommis· Jan 19

This implies that Hobbits were the OG 10x engineers.

Tommi Somersuo@tommis· Jan 19

Why does Edge ask this even with all these settings disabled?

Tommi Somersuo@tommis· Jan 19

Microsoft Edge dark patterns part 75:

Tommi Somersuo@tommis· Nov 24

"Programmatic Tool Calling enables Claude to orchestrate tools through code rather than through individual API round-trips, allowing for parallel tool execution."

Tommi Somersuo@tommis· Nov 24

Opus 4.5 www.anthropic.com/news/claude-...

Tommi Somersuo@tommis· Nov 8

The core idea of how it works in smolagents and here is really simple:

Tommi Somersuo@tommis· Nov 8

With a little bit of tweaking and help from github copilot - CodeExecutionAgent.cs came out and it actually works. Its really messy, but it shows how much potential there is in just using code directly instead of having the agent process endless tool calls. 2/

Tommi Somersuo@tommis· Oct 25

Firefox layout.css.prefers-color-scheme.content-override:0

Tommi Somersuo@tommis· Oct 24

vscode copilot chat team cooking a new agent spec file format, to supplement chatmodes/prompt file format named *.agent.md. Havent seen any blog posts/news about this yet: github.com/microsoft/vs...