News

Kaga AI chat has been updated. This release is mostly new features plus fixes for problems that were actually happening.

What we added

There is now Switch to standard mode at the top of the sidebar. It turns on Kawa Chat (no Kaga tone). Press again to return to Kaga. The empty screen has a light gradient; it turns white once you start chatting.

Deep Research is also available. It looks from several angles and shows a checklist while it works.

What we fixed

Short follow-ups such as “look it up” or “what’s the price?” could leave the previous topic and search something else. They now stay on that topic. The same for corrections and fact-checks.

Asking for “today’s news” sometimes did not return that day’s headlines. It now does, and it is less likely to pick thin pages.

After sending a photo and asking for a place or shop name, “look it up” or “you can guess” could drop the original request. Those follow-ups now keep the photo and the conversation.

On phones, the input bar could get too wide, and tables or headings could overflow. Empty-screen placement, the in-thread layout, and table display are fixed.

We also reduced searches during casual chat or code help, and made-up book or product names that were not in the sources.

Kaga and Kawa Chat stay free. If something still looks wrong, tell us.

We updated Kaga AI chat's security and availability. This update focuses on prompt-injection attempts that seek non-public context such as system prompts, developer instructions, and internal configuration.

Such attempts are not limited to asking to display a system prompt. They may use translation, JSON conversion, story framing, audit summaries, roleplay, multi-turn conversation, or encoded text to request the same information indirectly.

Staged detection and isolation

Kaga now performs lightweight local detection before sending input to the primary conversation model. Clear extraction requests are stopped at this stage.

We do not reject a message simply because it mentions system prompts or secrets. General security questions, requests about a user's own text, and translation of quoted text should remain usable. Ambiguous requests instead go to an isolated review path for an additional decision.

This review path has no access to Kaga's real system prompt, developer messages, internal memory, or private configuration. If a request is judged to seek private context, it never reaches Kaga's primary conversation model. The response uses only the safe portion of prior conversation, helping preserve the established persona, form of address, and topic without passing along the attack text.

The same isolation principle for fallback paths

The review and defensive-response path now also has provider fallbacks. If the primary AI is temporarily unavailable or reaches a usage limit, the review can continue through a backup path. No path receives Kaga's private system prompt. If every AI path is unavailable, suspicious input remains blocked and receives a safe fallback response.

Validation

In a randomized compositional benchmark, local first-pass detection routed 2,934 of 3,000 extraction attempts for additional review (97.8%). All 3,000 benign conversations generated under the same conditions stayed on the normal path.

On a fixed unused holdout set, it detected 23 of 24 extraction attempts while allowing 22 of 24 benign cases. A separate 2,500-case benign-focused test—including quoted news, security discussions, and a user's own configuration text—had zero first-pass false positives.

These results measure routing to additional review, not a guarantee of complete security or a final refusal rate. We will continue evaluating both missed attacks and false positives while keeping Kaga natural and free to use.

Kaga AI chat has received a major update, led by image conversations and live web information.

Discuss photos naturally

You can now send photos from your camera, photo library, or clipboard. Kaga can use the image and the following conversation together, including questions such as a number in a screenshot or a book in a shelf.

Check live information when it matters

For news, current prices, and other changing information, Kaga can decide to search before answering. It tells you it is checking, then continues with an answer and links to the relevant source pages.

Beyond vague answers

Previously, Kaga avoided firm claims about information that could be outdated. That remains important, but avoiding an answer is not enough when a current fact can be checked. The new search flow lets Kaga verify what needs verification.

Built to keep the conversation going

Behind the scenes, specialized AI services are used for conversation, images, and search. The system can move to another available path when one is busy or limited, helping the chat remain available while staying free to use.

We've overhauled the engine behind Kaga (AI chat). It's still free to use.

Multi-level fallback

When the main AI is busy or has hit its daily limit, Kaga no longer stops abruptly.

• First, the main AI responds
• If unavailable, it automatically switches to a high-quality backup
• If that fails too, it falls back to a final reserve

The switch happens behind the scenes—it never tells you to move to another service mid-conversation. Higher quality is always preferred.

Only the stable talkers remain

After repeated testing, we removed models that returned empty replies, easily ignored the rules, or leaked thinking notes into the reply. What remains are the models with the best balance of quality and stability.

Stronger tone and response rules

• For heavy topics like "I want to disappear" or "I'm exhausted," Kaga stays present ("I'm here with you") instead of forcing cheer or telling you to rest
• It avoids face-to-face phrases like "I'm by your side" in a text chat
• It also reduces responses that downplay your effort, such as "of course" or "that's normal"

Daily-limit changes

Once an AI hits its daily limit, it skips that slot until the next day and hands off to the next backup—cutting down on repeated failed attempts within a short wait.

Still improving

Not perfect. If anything feels off, let us know—it helps a lot.